claude-code-app-studio
CLAUDE.md40 starsChanged 7 months agoMITView on GitHub
Technical documentation lives here. The directory has four subtrees, each with its own audience and authoring conventions. Required ADR sections: Title, Status, Context, Decision, Consequences, ADR Dependencies, Framework Compatibility, PRD Requirements Addressed. Status lifecycle: Proposed → Accepted → Superseded. Stories may not reference Proposed ADRs — /story-readiness blocks them. TR Registry: docs/architecture/tr-registry.yaml — stable IDs that link PRD requirements (PRD-AUTH-003.REQ-2) to ADRs and stories. Append-only. Never renumber. Control Manifest: docs/architecture/control-manifest.md — flat programmer rules sheet (Required / Forbidden / Guarded…
In this repository77 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- design/CLAUDE.mdCLAUDE.md
- src/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- asset-auditSkill
- asset-specSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- bug-triageSkill
- changelogSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- create-storiesSkill
- day-one-patchSkill
- design-bibleSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- estimateSkill
- extractSkill
- gate-checkSkill
- helpSkill
- hotfixSkill
- launch-checklistSkill
- localizeSkill
- map-systemsSkill
- milestone-reviewSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- prd-reviewSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- prototypeSkill
- qa-planSkill
- quick-designSkill
- regression-suiteSkill
- release-checklistSkill
- retrospectiveSkill
- reverse-documentSkill
- review-all-prdsSkill
- scope-checkSkill
- security-auditSkill
- setup-frameworkSkill
- skill-improveSkill
- skill-testSkill
- smoke-checkSkill
- soak-testSkill
- sprint-planSkill
- sprint-statusSkill
- startSkill
- story-doneSkill
- The first 60 shown.
The file
We split this CLAUDE.md into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Run /architecture-review after a batch of ADRs to validate that every PRD requirement is covered and that ADRs do not contradict each other.
- Distinctive: line 48
When two PRDs disagree on a name, the registry wins.
- Distinctive: line 65
All docs use Markdown.
- Distinctive: line 71
All docs that reference the framework declare the version they assume in their preamble (e.g., "Verified against React Native 0.76, Expo …
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Docs Directory
Technical documentation lives here. The directory has four subtrees, each with its own audience and authoring conventions.
Subtrees
docs/architecture/
The master architecture document, ADRs, and the control manifest. Owned
by mobile-architect. Use the ADR template under
.claude/docs/templates/architecture-decision-record.md for new
decisions.
Required ADR sections: Title, Status, Context, Decision, Consequences, ADR Dependencies, Framework Compatibility, PRD Requirements Addressed.
Status lifecycle: Proposed → Accepted → Superseded. Stories
may not reference Proposed ADRs — /story-readiness blocks them.
TR Registry: docs/architecture/tr-registry.yaml — stable IDs that
link PRD requirements (PRD-AUTH-003.REQ-2) to ADRs and stories.
Append-only. Never renumber.
Control Manifest: docs/architecture/control-manifest.md — flat
programmer rules sheet (Required / Forbidden / Guarded per layer),
date-stamped. Stories embed the manifest version they were planned
against. /story-done flags stale-manifest stories.
Run /architecture-review after a batch of ADRs to validate that every
PRD requirement is covered and that ADRs do not contradict each other.
docs/framework-reference/
Version-pinned snapshots of the chosen framework's APIs. Always check
here before using any framework API — the LLM's training data predates
the pinned version. Each framework has its own subdirectory with a
VERSION.md file documenting the pinned version and verified docs.
The currently active framework is recorded in
.claude/docs/technical-preferences.md. The corresponding
docs/framework-reference/[framework]/VERSION.md is the canonical
reference.
docs/registry/
Cross-document entity registry — canonical names for screens, data
models, API endpoints, analytics events, and user-facing concepts. See
docs/registry/README.md for the schema.
When two PRDs disagree on a name, the registry wins; raise an issue against the older PRD.
docs/examples/
Reference snippets, example PRDs, example ADRs, and miniature end-to-end flows for new contributors to learn from. Examples are not contracts — do not copy them blindly.
Top-level Docs
COLLABORATIVE-DESIGN-PRINCIPLE.md— Question → Options → Decision → Draft → Approval. The interaction protocol every agent follows.WORKFLOW-GUIDE.md— Phase-by-phase walk through the full lifecycle from Discovery to Live Ops, with example skill invocations.
Authoring Standards
- All docs use Markdown.
- Code samples in docs use fenced blocks with a language tag.
- Internal links use file-relative paths (
./architecture/adr-0001.md), not absolute paths. - Date-stamped docs (changelogs, release notes) include an ISO-8601 date in the frontmatter.
- All docs that reference the framework declare the version they assume in their preamble (e.g., "Verified against React Native 0.76, Expo SDK 52").
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

