Imported from coldmon91/custom4agent (agent_settings/skills/subagent-driven-development/SKILL.md). Install upstream with npx skills add coldmon91/custom4agent --skill subagent-driven-development. Copyright stays with the author.

Subagent-Driven Development

Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end.

Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

Core principle: Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration

Narration: between tool calls, narrate at most one short line — the ledger and the tool results carry the record.

Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are the four named below, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.

Rulings, not stalls. A running plan does not wait on a human. Conflicts, ambiguities, plan defects, a cap you would have asked to exceed — decide them. The spec is the binding authority, the plan is its argument, and your judgment settles what neither answers. Record every decision in the ledger as Ruling: <what you decided> — <why> — <what it costs if wrong>, and keep going. A wrong ruling costs rework your human partner can see and undo; a session parked on a question costs their whole day and buys nothing.

Four things stop you, and only these: an irreversible or destructive operation; a security-sensitive action; a side effect outside this worktree that norms say you ask about first (a merge, a push to a shared branch, a publish); and a plan so broken that every path forward is a guess. For those, stop and ask.

When to Use

digraph when_to_use {
    "Have implementation plan?" [shape=diamond];
    "Tasks mostly independent?" [shape=diamond];
    "subagent-driven-development" [shape=box];
    "Manual execution, or run writing-plans / brainstorming first" [shape=box];

    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
    "Have implementation plan?" -> "Manual execution, or run writing-plans / brainstorming first" [label="no"];
    "Tasks mostly independent?" -> "subagent-driven-development" [label="yes"];
    "Tasks mostly independent?" -> "Manual execution, or run writing-plans / brainstorming first" [label="no - tightly coupled"];
}

vs. executing the plan yourself:

• Fresh subagent per task (no context pollution)
• Review after each task (spec compliance + code quality), broad review at the end
• Faster iteration (no human-in-loop between tasks)
• Your own context stays clean for coordination

The Process

digraph process {
    rankdir=TB;

    subgraph cluster_per_task {
        label="Per Task";
        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
        "Implementer asks questions?" [shape=diamond];
        "Answer questions, provide context" [shape=box];
        "Implementer implements, tests, commits, self-reviews" [shape=box];
        "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" [shape=box];
        "Spec ✅ and quality approved?" [shape=diamond];
        "Finding conflicts with plan text?" [shape=diamond];
        "Rule on the conflict, ledger the ruling" [shape=box];
        "Fix round R of 5: R≤3 resume implementer; R≥4 fix-loop agent (escalate if capability-bound)" [shape=box];
        "Dispatch scoped re-review (./re-review-prompt.md)" [shape=box];
        "All findings addressed?" [shape=diamond];
        "R = 5?" [shape=diamond];
        "Adjudicate each open finding" [shape=box];
        "Any load-bearing finding?" [shape=diamond];
        "Rule and continue; stop only if every path forward is a guess" [shape=box];
        "Park findings in ledger with rulings" [shape=box];
        "Append completion to ledger, mark todo complete" [shape=box];
    }

    "Setup: worktree, ledger check, read plan, pre-flight review" [shape=box];
    "More tasks remain?" [shape=diamond];
    "Dispatch final whole-branch review (review-branch agent)" [shape=box];
    "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" [shape=box];
    "Final review clean: delete this plan's workspace" [shape=box];
    "Finish: report rulings, hand the branch back" [shape=box style=filled fillcolor=lightgreen];

    "Setup: worktree, ledger check, read plan, pre-flight review" -> "Dispatch implementer subagent (./implementer-prompt.md)";
    "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer asks questions?";
    "Implementer asks questions?" -> "Answer questions, provide context" [label="yes"];
    "Answer questions, provide context" -> "Implementer implements, tests, commits, self-reviews";
    "Implementer asks questions?" -> "Implementer implements, tests, commits, self-reviews" [label="no"];
    "Implementer implements, tests, commits, self-reviews" -> "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)";
    "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" -> "Spec ✅ and quality approved?";
    "Spec ✅ and quality approved?" -> "Append completion to ledger, mark todo complete" [label="yes"];
    "Spec ✅ and quality approved?" -> "Finding conflicts with plan text?" [label="no"];
    "Finding conflicts with plan text?" -> "Rule on the conflict, ledger the ruling" [label="yes"];
    "Rule on the conflict, ledger the ruling" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fix-loop agent (escalate if capability-bound)";
    "Finding conflicts with plan text?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fix-loop agent (escalate if capability-bound)" [label="no"];
    "Fix round R of 5: R≤3 resume implementer; R≥4 fix-loop agent (escalate if capability-bound)" -> "Dispatch scoped re-review (./re-review-prompt.md)";
    "Dispatch scoped re-review (./re-review-prompt.md)" -> "All findings addressed?";
    "All findings addressed?" -> "Append completion to ledger, mark todo complete" [label="yes"];
    "All findings addressed?" -> "R = 5?" [label="no"];
    "R = 5?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fix-loop agent (escalate if capability-bound)" [label="no - next round"];
    "R = 5?" -> "Adjudicate each open finding" [label="yes - breaker trips"];
    "Adjudicate each open finding" -> "Any load-bearing finding?";
    "Any load-bearing finding?" -> "Rule and continue; stop only if every path forward is a guess" [label="yes"];
    "Any load-bearing finding?" -> "Park findings in ledger with rulings" [label="no"];
    "Park findings in ledger with rulings" -> "Append completion to ledger, mark todo complete";
    "Append completion to ledger, mark todo complete" -> "More tasks remain?";
    "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
    "More tasks remain?" -> "Dispatch final whole-branch review (review-branch agent)" [label="no"];
    "Dispatch final whole-branch review (review-branch agent)" -> "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals";
    "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" -> "Final review clean: delete this plan's workspace";
    "Final review clean: delete this plan's workspace" -> "Finish: report rulings, hand the branch back";
}

Setup

Ensure the work happens in an isolated workspace before dispatching anything:

• Run git rev-parse --abbrev-ref HEAD. Never start implementation on main/master without your human partner's explicit consent — create a feature branch, or a git worktree if the plan's work should not disturb the current checkout.
• Confirm the working tree is clean (git status --porcelain). Uncommitted work belonging to someone else makes every per-task diff unreadable.
• Every subagent works from this same directory; put its absolute path in each dispatch.

Conversation memory does not survive compaction. In real sessions, controllers that lost their place have re-dispatched entire completed task sequences — the single most expensive failure observed. Track progress in a ledger file, not only in todos.

• Each plan owns a workspace: at skill start, run this skill's scripts/sdd-workspace PLAN_FILE — it prints the plan's git-ignored directory (<repo-root>/.sdd/<plan-basename>/), home to every artifact for THIS plan: ledger, briefs, reports, review packages. Another plan's directory is never yours to read or write.
• Check for this plan's ledger at <workspace>/progress.md. If its first line names your plan file, tasks with a Task <N>: complete line are DONE — do not re-dispatch them; resume at the first task without one. A task whose last line is a fix round is mid-loop: resume the loop at the next round. A ledger whose first line names a different plan file is another plan's progress: leave it in place and start your own, fresh.
• Create the ledger with its identity as the first line: # SDD ledger — plan: <plan file path>.
• The ledger is your recovery map: the commits it names exist in git even when your context no longer remembers creating them. After compaction, trust the ledger and git log over your own recollection.
• git clean -fdx will destroy the workspace (it's git-ignored scratch); if that happens, recover from git log.

Read the plan once, note its context and Global Constraints, and create a todo per task. If the plan names a Spec, read that too: the spec is the authority the plan argues from, and conflicts inside the plan resolve against it. A plan with no reachable spec gets a ledger note saying so — rulings made without one are provisional.

Before dispatching Task 1, scan the plan once for conflicts, writing down what you checked as you check it:

• tasks that contradict each other or the plan's Global Constraints
• anything the plan explicitly mandates that the review rubric treats as a defect (a test that asserts nothing, verbatim duplication of a logic block)

The scan's output is a table, not a verdict. One row for every pair of tasks that share a file or an interface: the two tasks, what one produces against what the other consumes, and what you found. One row for every task: whether its own text agrees with itself — the tests it specifies against the code it specifies, the files it creates against the files it later touches. "The scan is clean" without those rows is not a scan you ran.

Write the table to the ledger. Rule on everything you find before execution begins — each finding against the plan text that mandates it — and record each ruling in the ledger. If the scan is clean, proceed without comment. Rule on each conflict it surfaces — the spec is the binding authority, the plan is its argument — record the ruling beside its row, and dispatch Task 1. The review loop remains the net for conflicts that only emerge from implementation.

Agent and Model Selection

Named agent definitions own their model and reasoning effort. Select the matching named definition for every dispatch; do not pass a model override. An override can silently bypass the tested role/model pairing.

Choose one model family during Setup and keep it for the entire run:

An explicit user choice wins; otherwise follow the controller/session family. If the family cannot be identified, retain the Claude family for backward compatibility and record that choice in the ledger. Do not mix families in one run unless a selected definition is unavailable; ledger any fallback.

Implementation. Rate the task's difficulty (Level 1 ~ 5) from the brief, then dispatch the matching family-specific agent. State the assigned Level plus a one-line rationale in the dispatch prompt.

Task review. Scale to the diff's size, complexity, and risk — not to the implementer's tier.

Scoped re-review: review-small / sonnet for Claude, or review-small-gpt / luna for GPT. Use the complex reviewer variant only for the high-risk conditions in the table.

Final whole-branch review: review-branch / sonnet for Claude, or review-branch-gpt / luna for GPT.

Fix loop: rounds 1 ~ 3 resume the original implementer. Rounds 4 ~ 5 use fix-loop / sonnet for Claude, or fix-loop-gpt / luna for GPT.

GPT dispatches may use only sol and luna. Every luna definition must use high effort or above. Never substitute another GPT model or lower luna's effort. Claude dispatches never use haiku to save cost — quality first.

Below, a bare role such as fix-loop or review-branch means the selected family's matching definition, including the -gpt suffix for GPT.

Turn count beats token price. Wall-clock and context cost scale with how many turns a subagent takes, and an under-powered model routinely takes 2 ~ 3× the turns on multi-step work — costing more overall. When a task sits on a Level boundary, take the higher Level and its family-specific agent.

The Task Loop

Batch small same-shape work. When the plan lists several tasks that are each a small, independent edit of the same kind — the same one-line fix, constant change, or field addition repeated across files — do not dispatch one subagent per task. Compose ONE dispatch brief listing every file and its change, send the whole batch to a single subagent, and review its diff as one unit. Reserve one-dispatch-per-task for work that needs its own judgment, its own tests, or its own review surface.

Everything you paste into a dispatch prompt — and everything a subagent prints back — stays resident in your context for the rest of the session and is re-read on every later turn. Hand artifacts over as files.

Waiting on dispatched subagents: never poll a wait interface with short timeouts, and never hand a dispatch one long open-ended timeout and walk away. Both extremes fail: short polling burns context on empty turns, while a single oversized timeout means a subagent stuck in a retry loop, a hung test run, or a crashed child is discovered only when the whole budget expires — after the wall-clock and tokens are already spent.

• Cap any single wait at 5 ~ 10 minutes, whatever the task's total expected duration. A 40-minute task is five to eight bounded waits, never one 40-minute wait.
• While you have local work — ledger updates, packaging the next review, reading reports — keep working; child results arrive on their own. Do not wait at all when there is work in hand.
• Check progress between stretches. After each bounded wait, post one line of status and reconcile your live children before waiting again. A stuck child must be noticed within minutes, not at the end of the session.

Progress checks read evidence, never assume it — a running agent that has produced nothing is indistinguishable from a hung one until you look:

• List live children and chase any that finished without reporting.
• Check the task's report file — existence, size, and mtime. A report that has not grown across two consecutive checks is a stall signal.
• Check git log --oneline BASE..HEAD in the workspace for commits the child has landed so far.
• Look for stray background processes or leftover temp files the child was told to clean up.

When a check shows no progress across two consecutive stretches, act: message the child for a one-line status if your platform allows it, otherwise stop it, ledger what it did complete, and re-dispatch the remainder with the partial state carried in the new brief. Never extend the timeout as the response to a stall — a longer wait does not unstick a stuck agent.

1. Dispatch the implementer

Record BASE (git rev-parse HEAD) before dispatching — the review package and fix-round diffs need it.

• Task brief: before dispatching an implementer, run this skill's scripts/task-brief PLAN_FILE N — it extracts the task's full text to a uniquely named file and prints the path. Compose the dispatch so the brief stays the single source of requirements. Your dispatch should contain: (1) one line on where this task fits in the project; (2) the brief path, introduced as "read this first — it is your requirements, with the exact values to use verbatim"; (3) interfaces and decisions from earlier tasks that the brief cannot know; (4) your resolution of any ambiguity you noticed in the brief; (5) the report-file path and report contract; (6) the assigned difficulty Level and its one-line rationale. Exact values (numbers, magic strings, signatures, test cases) appear only in the brief. Never make a subagent read the whole plan file.
• Report file: name the implementer's report file after the brief (brief …/task-N-brief.md → report …/task-N-report.md) and put it in the dispatch prompt. The implementer writes the full report there and returns only status, commits, a one-line test summary, and concerns.
• A dispatch prompt describes one task, not the session's history. Do not paste accumulated prior-task summaries ("state after Tasks 1-3") into later dispatches — a real session's dispatch hit 42k chars of which 99% was pasted history. A fresh subagent needs its task, the interfaces it touches, and the global constraints. Nothing else.
• The dispatch carries the no-subagents contract (it is in the implementer template): the implementer never dispatches subagents — not helpers, and never a reviewer. Review arrives from you, after the report. In real sessions, every reviewer a worker spawned duplicated the task review the controller dispatched anyway — a full extra review seat per task.
• If an earlier task parked a finding in the area this task touches, carry a pointer to that ledger entry in the dispatch.
• Record the implementer's agent identity from the dispatch result — fix-loop rounds 1 ~ 3 resume this agent.
• Never dispatch multiple implementation subagents in parallel (conflicts).

Template: implementer-prompt.md

2. Handle the report

Implementer subagents report one of four statuses. Handle each appropriately:

DONE: Generate the review package (scripts/review-package PLAN_FILE BASE HEAD, from this skill's directory — it prints the unique file path it wrote; BASE is the commit you recorded before dispatching the implementer — never HEAD~1, which silently drops all but the last commit of a multi-commit task), then dispatch the task reviewer with the printed path.

DONE_WITH_CONCERNS: The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.

NEEDS_CONTEXT: The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.

BLOCKED: The implementer cannot complete the task. Assess the blocker:

1. If it's a context problem, provide more context and re-dispatch at the same Level
2. If the task requires more reasoning, re-rate it one Level up and re-dispatch on the matching agent
3. If the task is too large, break it into smaller pieces
4. If the plan itself is wrong, rule on the correction, ledger it, and re-dispatch with the ruling carried in the dispatch

Never ignore an escalation or force the same agent to retry without changes. If the implementer said it's stuck, something needs to change.

If the implementer asks questions — before starting or mid-task — answer clearly and completely, provide additional context if needed, and don't rush it into implementation.

3. Review the task

Per-task reviews are task-scoped gates. The broad review happens once, at the final whole-branch review. Never skip the task review, and never accept a report missing either verdict — spec compliance AND task quality are both required. Implementer self-review never replaces the task review; both are needed.

• Hand the reviewer its diff as a file: run this skill's scripts/review-package PLAN_FILE BASE HEAD and pass the reviewer the file path it prints (or, without bash: git log --oneline, git diff --stat, and git diff -U10 for the range, redirected to one uniquely named file). The output never enters your own context, and the reviewer sees the commit list, stat summary, and full diff with context in one Read call. Use the BASE you recorded before dispatching the implementer — never HEAD~1, which silently truncates multi-commit tasks. Never dispatch a task reviewer without a diff file.
• Reviewer inputs: the task reviewer gets three paths — the same brief file, the report file, and the review package — plus the global constraints that bind the task.
• The global-constraints block you hand the reviewer is its attention lens. Copy the binding requirements verbatim from the plan's Global Constraints section or the spec: exact values, exact formats, and the stated relationships between components ("same layout as X", "matches Y"). The reviewer's template already carries the process rules (YAGNI, test hygiene, review method) — the constraints block is for what THIS project's spec demands.
• Do not add open-ended directives like "check all uses" or "run race tests if useful" without a concrete, task-specific reason
• Do not ask a reviewer to re-run tests the implementer already ran on the same code — the implementer's report carries the test evidence
• Do not pre-judge findings for the reviewer — never instruct a reviewer to ignore or not flag a specific issue. If you believe a finding would be a false positive, let the reviewer raise it and adjudicate it in the review loop. If the prompt you are writing contains "do not flag," "don't treat X as a defect," "at most Minor," or "the plan chose" — stop: you are pre-judging, usually to spare yourself a review loop.

The task reviewer may report "⚠️ Cannot verify from diff" items — requirements that live in unchanged code or span tasks. These do not block the rest of the review, but you must resolve each one yourself before marking the task complete: you hold the plan and cross-task context the reviewer lacks. If you confirm an item is a real gap, treat it as a failed spec review — it enters the fix loop with the other findings.

Template: task-reviewer-prompt.md

4. The fix loop

The loop triggers when the review reports spec ❌, any Critical or Important finding, or a ⚠️ item you confirmed as a real gap.

Before the loop starts, two routes leave it immediately:

• Record Minor findings in the progress ledger as you go (Task <N>: minor (deferred): <one-liner>), and point the final whole-branch review at that list so it can triage which must be fixed before merge. A roll-up nobody reads is a silent discard. Minor findings never enter the loop.
• A finding labeled plan-mandated — or any finding that conflicts with what the plan's text requires — is yours to rule on: weigh the finding against the plan text, decide with the spec as the binding authority, and ledger the ruling before you act on it. Do not dismiss the finding because the plan mandates it, and do not dispatch a fix that contradicts the plan without a recorded ruling.

Everything else enters the loop. A fix round is one fix dispatch plus one scoped re-review. Five rounds maximum per task:

Rounds 1 ~ 3 — resume the original implementer. Send it the open findings verbatim. Its context is intact: it knows the task, the code, and its own choices. If your harness cannot send another message to a live subagent, dispatch a fresh implementer at the same Level carrying the brief path, the report-file path, and the findings — the report file is the persistent memory either way.

Rounds 4 ~ 5 — dispatch the selected family's fix-loop agent (fix-loop on sonnet, or fix-loop-gpt on luna), with the brief path, the report-file path, the open findings, and this framing: "A prior implementer attempted this task [N] times; you own it now. Read the report file for what was tried." By round 4 the findings are already identified and agreed, so the work is applying known corrections one at a time — that is what fix-loop is for, and fresh eyes usually break a loop that survived three resumes.

The exception: if the loop is stuck because the task genuinely exceeds the implementer's capability — a design or concurrency problem, not an application problem — escalate instead to the selected family's deep implementation agent: impl-l3-4 / impl-l5 on opus, or impl-l3-4-gpt / impl-l5-gpt on sol. Ledger which route you took and why.

Every round, either way: the implementer fixes, re-runs the tests covering the amended code, appends its fix report to the same report file, and returns the short contract. Before re-dispatching the reviewer, confirm the fix report contains the covering tests, the command run, and the output; dispatch the re-review once all three are present. Name the covering test files in the fix message — a one-line fix does not need the whole suite.

The re-review is scoped. Run scripts/review-package PLAN_FILE FIX_BASE HEAD where FIX_BASE is the head the previous review saw, and dispatch re-review-prompt.md with the findings list, the brief, the report file, and the printed diff path. The re-reviewer verdicts each finding ADDRESSED or NOT ADDRESSED and flags new breakage in the fix diff only. New Critical/Important breakage in the fix diff joins the open findings list. Out-of-scope observations go to the ledger as deferred minors — they never extend the loop.

After each round, append to the ledger: Task <N>: fix round <R>/5 (<X> addressed, <Y> open — <finding one-liners>; commits <a7>..<b7>)

Never fix findings yourself in the controller session — your context stays clean for coordination, and controller fixes skip review.

The breaker. When round 5's re-review still leaves findings open, stop dispatching. Adjudicate each open finding yourself — you hold the plan and the cross-task context the reviewer lacks:

• The reviewer is wrong, or the point is contestable: park it — Task <N>: parked — <finding> — Ruling: <why the code stands>. The final review sees both sides.
• Real, but nothing downstream builds on it: park it the same way, with a ruling that says it's real and deferred.
• Real and load-bearing — a later task builds on it, or it reveals a plan defect: rule on the smallest change that unblocks the dependent work, ledger it as Task <N>: Ruling: <finding> — <what you decided and why>, and carry it into the next task's dispatch. Parking a structural failure silently lets every dependent task build on it. Stop only when the defect leaves every path forward a guess.

Adjudicate only at the cap. Adjudicating earlier to end a loop is pre-judging with a different name. Every adjudication is a ledger entry — a silent discard is forbidden.

5. Complete the task

When the review comes back clean — or every open finding is parked with a ruling at the cap — append the completion line to the ledger in the same message as your other bookkeeping:

• Task <N>: complete (commits <base7>..<head7>, review clean)
• Task <N>: complete (commits <base7>..<head7>, <K> parked) after a tripped breaker

Then mark the todo complete and move on. Never move to the next task while the review has open Critical/Important issues that are neither fixed nor parked-with-ruling at the cap.

Final Review

The final whole-branch review gets a package too: run scripts/review-package PLAN_FILE MERGE_BASE HEAD (MERGE_BASE = the commit the branch started from, e.g. git merge-base main HEAD) and include the printed path in the final review dispatch, so the final reviewer reads one file instead of re-deriving the branch diff with git commands.

Dispatch the selected family's final reviewer (review-branch on sonnet, or review-branch-gpt on luna). It reviews the accumulated diff as one coherent change rather than commit by commit. Give it: the plan file path, the review-package path, the branch's merge base and head, and the ledger's deferred-minor and parked lines so it can triage which must be fixed before merge.

If the final whole-branch review returns findings, dispatch ONE fix subagent with the complete findings list — not one fixer per finding. Use the selected family's fix-loop agent (fix-loop on sonnet, or fix-loop-gpt on luna); escalate to its deep implementation agent (impl-l3-4 on opus, or impl-l3-4-gpt on sol) only if a finding needs design judgment rather than applying a known correction. Per-finding fixers each rebuild context and re-run suites; a real session's final-review fix wave cost more than all its tasks combined. Then run exactly one scoped re-review of the fix wave (scripts/review-package PLAN_FILE FIX_BASE HEAD, re-review-prompt.md). Adjudicate any residual findings as in the task loop's breaker: park with rulings, or rule on the load-bearing ones and ledger what you decided. Only the four classes above stop you here. There is no second fix wave — residual load-bearing findings surface to your human partner in the Finish report.

Finish

Before you delete anything, collect every ledger line containing Ruling: — preflight rulings, parked findings, breaker adjudications, all of them — into your final message under "Rulings I made", in the order you made them, each with what it costs if wrong. The list is exhaustive: if the ledger holds a ruling, the list holds it. That list is the only place the decisions you took on your human partner's behalf reach them — they read it and rework whatever you got wrong. A ruling that dies with the workspace was a decision made in secret.

When the final whole-branch review is clean and its fixes are merged, delete this plan's workspace (rm -rf <workspace>) — the git history is the record now. Sibling directories belong to other plans; leave them alone.

Then hand the branch back rather than landing it yourself:

• Confirm the working tree is clean and every task's work is committed.
• Report the branch name, the commit range, and a one-line summary of what the branch does.
• Report test status as it actually stands, including anything still failing.
• List the "Rulings I made" block, the deferred minors, and any parked findings the final review triaged as non-blocking.
• Ask before merging, pushing to a shared branch, or opening a PR — those are side effects outside this worktree.

Common Rationalizations

Example Workflow

You: I'm using Subagent-Driven Development to execute this plan.

[Setup: on feature branch install-hooks, working tree clean]
[Read plan file once: docs/plans/feature-plan.md]
[Resolve workspace: scripts/sdd-workspace docs/plans/feature-plan.md — no ledger inside, fresh start]
[Create todos for all tasks]

Task 1: Hook installation script

[Run task-brief for Task 1]
[Rate: L2 — 2 files, complete spec, follows existing CLI patterns]
[Dispatch impl-l1-2/sonnet or impl-l1-2-gpt/luna with brief + report paths + context]

Implementer: "Before I begin - should the hook be installed at user or system level?"

You: "User level (~/.config/myapp/hooks/)"

Implementer: [Later]
  - Implemented install-hook command
  - Added tests, 5/5 passing
  - Self-review: Found I missed --force flag, added it
  - Committed

[Run review-package PLAN_FILE BASE HEAD]
[Diff is small and mechanical → dispatch review-small/sonnet or review-small-gpt/luna with the printed path]
Task reviewer: Spec ✅ - all requirements met, nothing extra.
  Strengths: Good test coverage, clean. Issues: None. Task quality: Approved.

[Ledger: Task 1: complete (commits a1b2c3d..d4e5f6a, review clean)]

Task 2: Recovery modes

[Run task-brief for Task 2]
[Rate: L3 — touches the CLI, the recovery module, and the state store]
[Dispatch impl-l3-4/opus or impl-l3-4-gpt/sol with brief + report paths + context]

Implementer: [No questions]
  - Added verify/repair modes
  - 8/8 tests passing
  - Committed

[Run review-package PLAN_FILE BASE HEAD; dispatch review-complex/opus or review-complex-gpt/sol — touches the state store]
Task reviewer: Spec ❌:
  - Missing: Progress reporting (spec says "report every 100 items")
  Issues (Important): Magic number (100)

[Fix round 1: resume the original implementer with both findings]
Implementer: Added progress reporting, extracted PROGRESS_INTERVAL constant.
  Re-ran test/recovery.test.js — 10/10 passing. Fix report appended.

[Run review-package PLAN_FILE FIX_BASE HEAD; dispatch scoped re-review on review-small/sonnet or review-small-gpt/luna]
Re-reviewer: Missing progress reporting — ADDRESSED (src/recovery.js:41).
  Magic number — ADDRESSED (src/recovery.js:7). New breakage: none.
  Verdict: all findings addressed.

[Ledger: Task 2: fix round 1/5 (2 addressed, 0 open; commits d4e5f6a..b7c8d9e)]
[Ledger: Task 2: complete (commits d4e5f6a..b7c8d9e, review clean)]

...

[After all tasks]
[Run review-package PLAN_FILE MERGE_BASE HEAD; dispatch review-branch/sonnet or review-branch-gpt/luna]
Final reviewer: All requirements met. Deferred minors triaged: none block merge.

[Delete this plan's workspace — the record now lives in git]

Done. Branch install-hooks, commits a1b2c3d..f0e9d8c, 34/34 tests passing.
Rulings I made: [list]. Merge/push not performed — say the word.