Imported from Chemaclass/agnostic-ai (
tests/integration/fixtures/golden/kiro/AGENTS.md). Install upstream withnpx skills add Chemaclass/agnostic-ai --skill kiro. Copyright stays with the author.
AI Project Conventions
This file is regenerated by agnostic-ai. Every supported AI tool reads a copy of this body from its native entry-point (CLAUDE.md, AGENTS.md, GEMINI.md, CONVENTIONS.md, ...) so a single source of truth drives every target.
Where the specs live
- Agents:
.agnostic-ai/agents/ - Skills:
.agnostic-ai/skills/ - Rules:
.agnostic-ai/rules/(one file per rule) - Hooks:
.agnostic-ai/hooks/(rendered into the target-native location) - MCP servers:
.agnostic-ai/mcps/ - Commands:
.agnostic-ai/commands/ - Settings:
.agnostic-ai/settings/(portable model and permission defaults where targets support them) - Reviews:
.agnostic-ai/reviews/(code-review bot guidance; Cursor BUGBOT.md today) - Environments:
.agnostic-ai/environments/(dev-env bootstrap; Cursor environment.json today) - Ignore:
.agnostic-ai/ignore/(agent ignore patterns; .cursorignore, .geminiignore, .aiderignore)
Target-specific overlays
Per-target configuration that does not fit the agnostic spec kinds above lives under .agnostic-ai/overlays/. The Claude adapter, for example, captures the non-hooks portion of .claude/settings.json (statusLine, enabledPlugins, ...) into .agnostic-ai/overlays/claude.settings.json on import claude. sync reads that overlay and layers the spec-derived hooks key on top.
Workflow
- Author specs under the directories above.
- Run
agnostic-ai syncto regenerate per-target output files. - Edit only the source specs; the per-target files (including this one) are overwritten on each sync.