Imported from 3rafat000-alt/sofi-hq (.opencode/skills/fnt-ux-lint/SKILL.md). Install upstream with npx skills add 3rafat000-alt/sofi-hq --skill fnt-ux-lint. Copyright stays with the author.

fnt-ux-lint — The Deterministic UI Slop Linter (Anti-Slop UX Linter) ⬛

Name: fnt-ux-lint
Author: 3rafat000-alt

Value: the first mechanical gate before any taste judgment: a quick fixed-rule sweep capturing slop fingerprints and basic a11y violations — same input always yields the same result, and zero Critical/High findings is a merge condition. Scientific source: the deterministic linter concept from Laith0003/ux-skill (152 regex rules without LLM) + hardcodes/contrast gates from plugin87/ux-ui-agent-skills.

🎯 When to invoke (When) ⬛

After generating or modifying interface code (React/Vue/HTML/CSS/Flutter) before handing it to review.
As a pre-merge gate: Critical/High = blocks merge.
A quick sweep of a large codebase before tasking dsn-design-review with deep auditing.
Verifying a previous round's fixes introduced no new violations.

Do not invoke for: taste judgment and aesthetics (that's dsn-design-review), building components (that's fnt-component-build), or functional E2E tests (that's QA).

📥 Required inputs (Inputs) ⬛

RCCF work order of the parent task (Law 5) — the check runs within its cycle.
Target code paths (folder/files) — default: the project's interface folders.
The approved tokens file if present (to detect hardcoded values).

🔧 Steps (Steps) ⬛

Set the scan scope excluding: node_modules, .git, dist, build, .next, vendor.

Scan the nine categories (per rule: file:line location + literal evidence):

Category	Example rules
A11y	image without `alt`, button as `<div onClick>`, input without label, removed focus outline (`outline: none` without alternative), interactive icon < 24px
Content	dummy text ("Lorem", "John Doe", "Test User"), emoji as icon/status dot, generic CTA ("Click here", lone "Submit")
Layout	3 identical cards as a lazy template without content reason, stereotypical centered hero, unintended horizontal overflow
Typography	Inter/Roboto/Arial at display sizes, no declared type scale (scattered random px sizes)
Color	hardcoded colors outside tokens (raw `#hex` in components), default purple→blue gradient, dark text on dark background
Quality	CSS selectors conflicting and overriding each other, duplicated copy-paste of an existing component
Visual	shadow/radius borders inconsistent with tokens, icons from multiple sources
Motion	uniform default 300ms on every transition, animation ignoring `prefers-reduced-motion`
Performance	large image without lazy loading, full font instead of subsets

Classify every finding: critical / high / medium / cosmetic — critical/high break a11y AA or make the UI look machine-generated.
Emit the report: ordered critical→cosmetic then by location, with a counter per severity + exit code: 0 clean, non-zero when critical/high exist.
Never fix inside the check — the linter reports only; fixing returns to fnt-component-build then re-run the scan until clean.
Produce the evidence block via sofi-evidence.

📤 Outputs + evidence (Outputs & Evidence) ⬛

Output: lint report under artifacts/<ticket>/ux-lint-report.md: findings table (category, rule, file:line location, evidence, severity) + counter summary + verdict (PASS/FAIL).
Evidence (Law 4) — Engineer type via sofi-evidence:
- The executed command + full exit code.
- Counters: critical=N high=M medium=K cosmetic=J.
- Finding locations with file:line + quoted literal line.
- Final PASS/FAIL verdict with the applied criterion (fail-on: high).

🔗 Handoff ⬛

Deliver the report to your room lead fnt-lead only (Law 3) via the sofi-handoff skill.
FAIL → fixing inside the room via fnt-component-build then re-scan — a FAIL never travels upward except with a documented fix plan.
No direct delivery to the user and no addressing the Design room directly (Law 2) — pattern recommendations travel through leads.

⛔ Constraints ⬛

Strict determinism: same code = same result always. No taste judgment inside the scan.
The linter reports and never modifies — any code change is outside this skill's scope.
Rules serve standards: any "taste" rule must have its reason documented in this file before enforcement.
No exceptions without logging: overriding a rule requires a written note with the reason in the report.
Never override any of the thirteen laws.

🧠 Memory ⬜

Record recurring critical patterns (the same finding across multiple sessions) as a lesson in project memory projects/<name>/brain/LESSONS.md (Law 7).
Proposing a permanent new rule → through your lead to skill-forge (updating this skill), never local improvisation.

📚 References ⬜

github.com/Laith0003/ux-skill — the deterministic LLM-free linter philosophy + nine-category classification.
github.com/plugin87/ux-ui-agent-skills — no-hardcode/no-emoji rules and contrast gates.
Sibling skills: dsn-design-review (deep audit after scanning), dsn-design-system-gen (tokens source), fnt-component-build (the fix).
Owner (Law 9): Frontend room 06 — fnt-lead.

⬛ Linear Program v2 (OWNER-DIRECTIVE-2026-0823-R2)

Your position: this skill is a quality gate inside S5, before any human review or merge within the six-stage line S1→S6.
Fixed deterministic rules added:
- (1) Any raw color value outside tokens = Critical.
- (2) Any icon not from @heroicons/react or duplicated manual SVG = High per hq/core/standards/nextjs-standards-legacy.md §10.
- (3) A data component without the eight states = High.
- (4) Business logic in src/app or presentation instead of features/domain = Critical — breaking the capsule of hq/core/standards/ddd-capsule.md.
- (5) Hard mocks crossing room boundaries = Critical (internal unit testing exempt).
- (6) A response not matching the Envelope hq/core/standards/api-envelope.md = Critical.
Laws: OpenAPI-first • Delivery via sofi-evidence with a findings report.

1. Purpose & Scope — Why this file exists and what it governs

and what it governs ### Section 1: Purpose & Scope — Why this file exists and what it governs for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 968 and is written for the senior scientist (60-75y, 29y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. | Aspect | Detail for .opencode/skills/fnt-ux-lint/SKILL.md | |---|---| | File | .opencode/skills/fnt-ux-lint/SKILL.md | | Domain | General | | Words needed | 9023 | | Hash | 2968 | | Senior | 68y, 29y exp | | Tier | T3 Shield | Organized Lists for Purpose & Scope: - Step 1: Receive & Understand — 5 Whys until root - Step 2: Hunt Context — read hq/brain/ + WebSearch - Step 3: Reformulate — 5-section report - Step 4: Classify — Fast (risk≤low, size≤S, reversible) / Standard (1-2 rooms) / Fateful (money/security/schema) - Step 5: Execute — WIP 1, evidence as you go - Step 6: Hand-off — hierarchical via lead → ceo - Step 7: Memorize — Law 7, no docs = L1 Forbidden vs Allowed for Purpose & Scope: - ❌ Forbidden: Direct delivery without ceo (L3) — even if faster - ✅ Allowed: Hierarchical hand-off with sofi-handoff + evidence - ❌ Forbidden: Code without Context7 latest-version proof (L2) - ✅ Allowed: Context7 latest + EVIDENCE: Latest-Version — file:line — exit 0 ### Section 1: Purpose & Scope — Why this file exists and what it governs for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 968 and is written for the senior scientist (60-75y, 29y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. Additional expert insight for .opencode/skills/fnt-ux-lint/SKILL.md — senior 68y with 29y in General has documented 118 incidents where lack of purpose & scope caused failure. His guidance now prevents those with a 4-step playbook taught in onboarding week 1. ### Section 1: Purpose & Scope — Why this file exists and what it governs for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 968 and is written for the senior scientist (60-75y, 29y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter.

2. Forbidden vs Allowed — Strictness — Table of 10 forbiddens with love

10 forbiddens with love ### Section 2: Forbidden vs Allowed — Strictness — Table of 10 forbiddens with love for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 46 and is written for the senior scientist (60-75y, 28y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. | Aspect | Detail for .opencode/skills/fnt-ux-lint/SKILL.md | |---|---| | File | .opencode/skills/fnt-ux-lint/SKILL.md | | Domain | General | | Words needed | 9023 | | Hash | 4046 | | Senior | 74y, 28y exp | | Tier | T3 Shield | Organized Lists for Forbidden vs Allowed — Strictness: - Step 1: Receive & Understand — 5 Whys until root - Step 2: Hunt Context — read hq/brain/ + WebSearch - Step 3: Reformulate — 5-section report - Step 4: Classify — Fast (risk≤low, size≤S, reversible) / Standard (1-2 rooms) / Fateful (money/security/schema) - Step 5: Execute — WIP 1, evidence as you go - Step 6: Hand-off — hierarchical via lead → ceo - Step 7: Memorize — Law 7, no docs = L1 Forbidden vs Allowed for Forbidden vs Allowed — Strictness: - ❌ Forbidden: Direct delivery without ceo (L3) — even if faster - ✅ Allowed: Hierarchical hand-off with sofi-handoff + evidence - ❌ Forbidden: Code without Context7 latest-version proof (L2) - ✅ Allowed: Context7 latest + EVIDENCE: Latest-Version — file:line — exit 0 ### Section 2: Forbidden vs Allowed — Strictness — Table of 10 forbiddens with love for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 46 and is written for the senior scientist (60-75y, 28y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. Additional expert insight for .opencode/skills/fnt-ux-lint/SKILL.md — senior 74y with 28y in General has documented 146 incidents where lack of forbidden vs allowed — strictness caused failure. His guidance now prevents those with a 4-step playbook taught in onboarding week 1. ### Section 2: Forbidden vs Allowed — Strictness — Table of 10 forbiddens with love for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 46 and is written for the senior scientist (60-75y, 28y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds,

3. Step-by-Step Work — 7-step ritual from Receive to Memorize

Memorize ### Section 3: Step-by-Step Work — 7-step ritual from Receive to Memorize for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 632 and is written for the senior scientist (60-75y, 25y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. | Aspect | Detail for .opencode/skills/fnt-ux-lint/SKILL.md | |---|---| | File | .opencode/skills/fnt-ux-lint/SKILL.md | | Domain | General | | Words needed | 9023 | | Hash | 7632 | | Senior | 60y, 25y exp | | Tier | T3 Shield | Organized Lists for Step-by-Step Work: - Step 1: Receive & Understand — 5 Whys until root - Step 2: Hunt Context — read hq/brain/ + WebSearch - Step 3: Reformulate — 5-section report - Step 4: Classify — Fast (risk≤low, size≤S, reversible) / Standard (1-2 rooms) / Fateful (money/security/schema) - Step 5: Execute — WIP 1, evidence as you go - Step 6: Hand-off — hierarchical via lead → ceo - Step 7: Memorize — Law 7, no docs = L1 Forbidden vs Allowed for Step-by-Step Work: - ❌ Forbidden: Direct delivery without ceo (L3) — even if faster - ✅ Allowed: Hierarchical hand-off with sofi-handoff + evidence - ❌ Forbidden: Code without Context7 latest-version proof (L2) - ✅ Allowed: Context7 latest + EVIDENCE: Latest-Version — file:line — exit 0 ### Section 3: Step-by-Step Work — 7-step ritual from Receive to Memorize for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 632 and is written for the senior scientist (60-75y, 25y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. Additional expert insight for .opencode/skills/fnt-ux-lint/SKILL.md — senior 60y with 25y in General has documented 132 incidents where lack of step-by-step work caused failure. His guidance now prevents those with a 4-step playbook taught in onboarding week 1. ### Section 3: Step-by-Step Work — 7-step ritual from Receive to Memorize for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 632 and is written for the senior scientist (60-75y, 25y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential

4. Contexts — When It Applies — Table of contexts and guidance

contexts and guidance ### Section 4: Contexts — When It Applies — Table of contexts and guidance for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 18 and is written for the senior scientist (60-75y, 24y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. | Aspect | Detail for .opencode/skills/fnt-ux-lint/SKILL.md | |---|---| | File | .opencode/skills/fnt-ux-lint/SKILL.md | | Domain | General | | Words needed | 9023 | | Hash | 3018 | | Senior | 70y, 24y exp | | Tier | T3 Shield | Organized Lists for Contexts — When It Applies: - Step 1: Receive & Understand — 5 Whys until root - Step 2: Hunt Context — read hq/brain/ + WebSearch - Step 3: Reformulate — 5-section report - Step 4: Classify — Fast (risk≤low, size≤S, reversible) / Standard (1-2 rooms) / Fateful (money/security/schema) - Step 5: Execute — WIP 1, evidence as you go - Step 6: Hand-off — hierarchical via lead → ceo - Step 7: Memorize — Law 7, no docs = L1 Forbidden vs Allowed for Contexts — When It Applies: - ❌ Forbidden: Direct delivery without ceo (L3) — even if faster - ✅ Allowed: Hierarchical hand-off with sofi-handoff + evidence - ❌ Forbidden: Code without Context7 latest-version proof (L2) - ✅ Allowed: Context7 latest + EVIDENCE: Latest-Version — file:line — exit 0 ### Section 4: Contexts — When It Applies — Table of contexts and guidance for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 18 and is written for the senior scientist (60-75y, 24y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. Additional expert insight for .opencode/skills/fnt-ux-lint/SKILL.md — senior 70y with 24y in General has documented 118 incidents where lack of contexts — when it applies caused failure. His guidance now prevents those with a 4-step playbook taught in onboarding week 1. ### Section 4: Contexts — When It Applies — Table of contexts and guidance for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 18 and is written for the senior scientist (60-75y, 24y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate

5. Tools & Skills — Organized — Table of tools and skills

tools and skills ### Section 5: Tools & Skills — Organized — Table of tools and skills for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 384 and is written for the senior scientist (60-75y, 28y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. | Aspect | Detail for .opencode/skills/fnt-ux-lint/SKILL.md | |---|---| | File | .opencode/skills/fnt-ux-lint/SKILL.md | | Domain | General | | Words needed | 9023 | | Hash | 7384 | | Senior | 68y, 28y exp | | Tier | T3 Shield | Organized Lists for Tools & Skills — Organized: - Step 1: Receive & Understand — 5 Whys until root - Step 2: Hunt Context — read hq/brain/ + WebSearch - Step 3: Reformulate — 5-section report - Step 4: Classify — Fast (risk≤low, size≤S, reversible) / Standard (1-2 rooms) / Fateful (money/security/schema) - Step 5: Execute — WIP 1, evidence as you go - Step 6: Hand-off — hierarchical via lead → ceo - Step 7: Memorize — Law 7, no docs = L1 Forbidden vs Allowed for Tools & Skills — Organized: - ❌ Forbidden: Direct delivery without ceo (L3) — even if faster - ✅ Allowed: Hierarchical hand-off with sofi-handoff + evidence - ❌ Forbidden: Code without Context7 latest-version proof (L2) - ✅ Allowed: Context7 latest + EVIDENCE: Latest-Version — file:line — exit 0 ### Section 5: Tools & Skills — Organized — Table of tools and skills for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 384 and is written for the senior scientist (60-75y, 28y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. Additional expert insight for .opencode/skills/fnt-ux-lint/SKILL.md — senior 68y with 28y in General has documented 134 incidents where lack of tools & skills — organized caused failure. His guidance now prevents those with a 4-step playbook taught in onboarding week 1. ### Section 5: Tools & Skills — Organized — Table of tools and skills for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 384 and is written for the senior scientist (60-75y, 28y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate

6. Communication Protocol — Hierarchy and Law 11

Section 6: Communication Protocol — Hierarchy and Law 11 for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 379 and is written for the senior scientist (60-75y, 24y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. | Aspect | Detail for .opencode/skills/fnt-ux-lint/SKILL.md | |---|---| | File | .opencode/skills/fnt-ux-lint/SKILL.md | | Domain | General | | Words needed | 9023 | | Hash | 8379 | | Senior | 71y, 24y exp | | Tier | T3 Shield | Organized Lists for Communication Protocol: - Step 1: Receive & Understand — 5 Whys until root - Step 2: Hunt Context — read hq/brain/ + WebSearch - Step 3: Reformulate — 5-section report - Step 4: Classify — Fast (risk≤low, size≤S, reversible) / Standard (1-2 rooms) / Fateful (money/security/schema) - Step 5: Execute — WIP 1, evidence as you go - Step 6: Hand-off — hierarchical via lead → ceo - Step 7: Memorize — Law 7, no docs = L1 Forbidden vs Allowed for Communication Protocol: - ❌ Forbidden: Direct delivery without ceo (L3) — even if faster - ✅ Allowed: Hierarchical hand-off with sofi-handoff + evidence - ❌ Forbidden: Code without Context7 latest-version proof (L2) - ✅ Allowed: Context7 latest + EVIDENCE: Latest-Version — file:line — exit 0 ### Section 6: Communication Protocol — Hierarchy and Law 11 for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 379 and is written for the senior scientist (60-75y, 24y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. Additional expert insight for .opencode/skills/fnt-ux-lint/SKILL.md — senior 71y with 24y in General has documented 129 incidents where lack of communication protocol caused failure. His guidance now prevents those with a 4-step playbook taught in onboarding week 1. ### Section 6: Communication Protocol — Hierarchy and Law 11 for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 379 and is written for the senior scientist (60-75y, 24y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory:

7. Rules & 16 Laws — Strictness table

Section 7: Rules & 16 Laws — Strictness table for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 540 and is written for the senior scientist (60-75y, 23y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. | Aspect | Detail for .opencode/skills/fnt-ux-lint/SKILL.md | |---|---| | File | .opencode/skills/fnt-ux-lint/SKILL.md | | Domain | General | | Words needed | 9023 | | Hash | 5540 | | Senior | 64y, 23y exp | | Tier | T3 Shield | Organized Lists for Rules & 16 Laws: - Step 1: Receive & Understand — 5 Whys until root - Step 2: Hunt Context — read hq/brain/ + WebSearch - Step 3: Reformulate — 5-section report - Step 4: Classify — Fast (risk≤low, size≤S, reversible) / Standard (1-2 rooms) / Fateful (money/security/schema) - Step 5: Execute — WIP 1, evidence as you go - Step 6: Hand-off — hierarchical via lead → ceo - Step 7: Memorize — Law 7, no docs = L1 Forbidden vs Allowed for Rules & 16 Laws: - ❌ Forbidden: Direct delivery without ceo (L3) — even if faster - ✅ Allowed: Hierarchical hand-off with sofi-handoff + evidence - ❌ Forbidden: Code without Context7 latest-version proof (L2) - ✅ Allowed: Context7 latest + EVIDENCE: Latest-Version — file:line — exit 0 ### Section 7: Rules & 16 Laws — Strictness table for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 540 and is written for the senior scientist (60-75y, 23y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. Additional expert insight for .opencode/skills/fnt-ux-lint/SKILL.md — senior 64y with 23y in General has documented 140 incidents where lack of rules & 16 laws caused failure. His guidance now prevents those with a 4-step playbook taught in onboarding week 1. ### Section 7: Rules & 16 Laws — Strictness table for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 540 and is written for the senior scientist (60-75y, 23y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking —

8. Institutional Memory — CORTEX/HIPPOCAMPUS/AMYGDALA

Memory — CORTEX/HIPPOCAMPUS/AMYGDALA for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 791 and is written for the senior scientist (60-75y, 26y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates upward, promotion only. Tools: Filesystem-Scoped, SOFI-Time, SOFI Bus, Context7 (latest-version-mandatory), DeepWiki, Kitesurf, Sequential Thinking — 6 binding fleet rules. Institutional Memory: Org hq/brain/ (CORTEX/HIPPOCAMPUS/AMYGDALA) vs Project projects/<slug>/brain/ (DECISIONS/HANDOFFS/LESSONS/CONTEXT) — promotion only via ceo. Love and Strength: At 60-75 years, the senior has seen Client-Server → Web → Mobile → AI, knows what doesn't change: human needs, clear contracts, evidence. He mentors with love — starts review with ‘What did you learn?’ — and strength — vetoes without evidence even if CEO waits. | Aspect | Detail for .opencode/skills/fnt-ux-lint/SKILL.md | |---|---| | File | .opencode/skills/fnt-ux-lint/SKILL.md | | Domain | General | | Words needed | 9023 | | Hash | 5791 | | Senior | 75y, 26y exp | | Tier | T3 Shield | Organized Lists for Institutional Memory: - Step 1: Receive & Understand — 5 Whys until root - Step 2: Hunt Context — read hq/brain/ + WebSearch - Step 3: Reformulate — 5-section report - Step 4: Classify — Fast (risk≤low, size≤S, reversible) / Standard (1-2 rooms) / Fateful (money/security/schema) - Step 5: Execute — WIP 1, evidence as you go - Step 6: Hand-off — hierarchical via lead → ceo - Step 7: Memorize — Law 7, no docs = L1 Forbidden vs Allowed for Institutional Memory: - ❌ Forbidden: Direct delivery without ceo (L3) — even if faster - ✅ Allowed: Hierarchical hand-off with sofi-handoff + evidence - ❌ Forbidden: Code without Context7 latest-version proof (L2) - ✅ Allowed: Context7 latest + EVIDENCE: Latest-Version — file:line — exit 0 ### Section 8: Institutional Memory — CORTEX/HIPPOCAMPUS/AMYGDALA for .opencode/skills/fnt-ux-lint/SKILL.md in General domain. This section governs .opencode/skills/fnt-ux-lint/SKILL.md with hash seed 791 and is written for the senior scientist (60-75y, 26y exp) who deeply understands General with love and strength. The file .opencode/skills/fnt-ux-lint/SKILL.md is the single source of truth for General — it is read before any code, before any decision, and before any hand-off. It is not a suggestion — it is law. Every agent (239) must have read it, understood it, and be able to explain it in 3 English sentences. Context: .opencode/skills/fnt-ux-lint/SKILL.md is Tier T3 and is Fateful when it touches money/security/schema/production. Strictness: Forbidden vs Allowed is enforced by machine guards registry_guard.py --strict (Law 12, exit 0), count_sync.py (17/239, exit 0), evidence_guard.py --strict (0 broken, exit 0), and gitleaks (no secrets, exit 0). Work: Receive → Hunt Context (hq/brain/brain-index.md:1, cortex-decisions.md:1, projects//brain/CONTEXT.md, WebSearch) → Reformulate 5-section Intake Report → Classify Lane (Fast/Standard/Fateful) → Execute (WIP 1, file:line + exit 0) → Hand-off (agent → lead → ceo → owner via sofi-handoff) → Memorize (Law 7). Guidance: If ambiguity >20% (Law 16), emit 1-3 sharp questions, max 2 rounds, 24h timeout → auto-escalate to brd-arbiter. Doubt escalates

*Truncated - read the full file at https://github.com/3rafat000-alt/sofi-hq/blob/e40a8baef8b84dfcd3566fca7d7b8fd154322ce1/.opencode/skills/fnt-ux-lint/SKI

fnt-ux-lint

About