Skip to content

dirien/yet-another-agent-harness / .claude/skills/agent-rules

agent-rules

Flagged

Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.

FileKindSize
AGENTS.mdmarkdown3.9 KB
CLAUDE.mdmarkdown9 B
SKILL.mdskill md4.5 KB
assets/example-workflows/validate-agents.ymlconfig2.7 KB
assets/root-thin.mdmarkdown5.7 KB
assets/root-verbose.mdmarkdown5.5 KB
assets/scoped/backend-go.mdmarkdown3.6 KB
assets/scoped/backend-php.mdmarkdown3.0 KB
assets/scoped/backend-python.mdmarkdown2.6 KB
assets/scoped/backend-typescript.mdmarkdown2.8 KB
assets/scoped/claude-code-skill.mdmarkdown3.4 KB
assets/scoped/cli.mdmarkdown2.7 KB
assets/scoped/concourse.mdmarkdown5.2 KB
assets/scoped/ddev.mdmarkdown2.4 KB
assets/scoped/docker.mdmarkdown5.3 KB
assets/scoped/documentation.mdmarkdown3.5 KB
assets/scoped/examples.mdmarkdown3.4 KB
assets/scoped/frontend-typescript.mdmarkdown2.7 KB
assets/scoped/github-actions.mdmarkdown5.2 KB
assets/scoped/gitlab-ci.mdmarkdown4.6 KB
assets/scoped/oro-bundle.mdmarkdown6.5 KB
assets/scoped/oro-project.mdmarkdown5.5 KB
assets/scoped/python-modern.mdmarkdown6.1 KB
assets/scoped/resources.mdmarkdown3.5 KB
assets/scoped/skill-repo.mdmarkdown5.4 KB
assets/scoped/symfony.mdmarkdown5.3 KB
assets/scoped/testing.mdmarkdown3.0 KB
assets/scoped/typo3-docs.mdmarkdown3.6 KB
assets/scoped/typo3-extension.mdmarkdown5.1 KB
assets/scoped/typo3-project.mdmarkdown4.7 KB
assets/scoped/typo3-testing.mdmarkdown3.0 KB
checkpoints.yamlconfig9.0 KB
evals/evals.jsonconfig20.7 KB
references/ai-contribution-guidelines.mdmarkdown2.5 KB
references/ai-tool-compatibility.mdmarkdown7.9 KB
references/analysis.mdmarkdown10.8 KB
references/directory-coverage.mdmarkdown2.4 KB
references/examples/coding-agent-cli/AGENTS.mdmarkdown2.5 KB
references/examples/coding-agent-cli/go.modmanifest45 B
references/examples/coding-agent-cli/scripts-AGENTS.mdmarkdown10.1 KB
references/examples/express-api-ts/.env.exampleother232 B
references/examples/express-api-ts/AGENTS.mdmarkdown3.1 KB
references/examples/express-api-ts/package.jsonmanifest757 B
references/examples/express-api-ts/pnpm-lock.yamlmanifest101 B
references/examples/express-api-ts/src/AGENTS.mdmarkdown3.1 KB
references/examples/express-api-ts/src/config.tsscript917 B
references/examples/express-api-ts/src/controllers/userController.tsscript2.1 KB
references/examples/express-api-ts/src/index.tsscript671 B
references/examples/express-api-ts/src/middleware/errorHandler.tsscript1.0 KB
references/examples/express-api-ts/src/middleware/requestLogger.tsscript471 B
references/examples/express-api-ts/src/routes/health.tsscript428 B
references/examples/express-api-ts/src/routes/users.tsscript397 B
references/examples/express-api-ts/src/utils/errors.tsscript1.2 KB
references/examples/express-api-ts/src/utils/logger.tsscript441 B
references/examples/express-api-ts/tsconfig.jsonconfig630 B
references/examples/fastapi-app/.env.exampleother348 B
references/examples/fastapi-app/AGENTS.mdmarkdown3.2 KB
references/examples/fastapi-app/pyproject.tomlmanifest1.8 KB
references/examples/fastapi-app/src/AGENTS.mdmarkdown2.9 KB
references/examples/fastapi-app/src/__init__.pyscript58 B
references/examples/fastapi-app/src/config.pyscript1.1 KB
references/examples/fastapi-app/src/main.pyscript1.7 KB
references/examples/fastapi-app/src/models/__init__.pyscript278 B
references/examples/fastapi-app/src/models/item.pyscript1.0 KB
references/examples/fastapi-app/src/models/user.pyscript922 B
references/examples/fastapi-app/src/routes/__init__.pyscript110 B
references/examples/fastapi-app/src/routes/health.pyscript470 B
references/examples/fastapi-app/src/routes/items.pyscript1.9 KB
references/examples/fastapi-app/src/routes/users.pyscript1.7 KB
references/examples/fastapi-app/src/services/__init__.pyscript174 B
references/examples/fastapi-app/src/services/item_service.pyscript2.5 KB
references/examples/fastapi-app/src/services/user_service.pyscript2.1 KB
references/examples/fastapi-app/uv.lockmanifest136 B
references/examples/go-api-with-react-admin/.scopesother93 B
references/examples/go-api-with-react-admin/AGENTS.mdmarkdown3.0 KB
references/examples/go-api-with-react-admin/admin/package.jsonmanifest422 B
references/examples/go-api-with-react-admin/admin/src/App.tsxother101 B
references/examples/go-api-with-react-admin/cmd/api/main.goscript75 B
references/examples/go-api-with-react-admin/go.modmanifest31 B
references/examples/go-api-with-react-admin/main.goscript71 B
references/examples/go-with-internal-web-tsx/.scopesother102 B
references/examples/go-with-internal-web-tsx/AGENTS.mdmarkdown3.1 KB
references/examples/go-with-internal-web-tsx/go.modmanifest34 B
references/examples/go-with-internal-web-tsx/internal/web/AGENTS.mdmarkdown3.1 KB
references/examples/go-with-internal-web-tsx/internal/web/package.jsonmanifest328 B
references/examples/go-with-internal-web-tsx/internal/web/src/App.tsxother57 B
references/examples/go-with-internal-web-tsx/internal/web/src/Button.tsxother63 B
references/examples/go-with-internal-web-tsx/internal/web/src/Footer.tsxother63 B
references/examples/go-with-internal-web-tsx/internal/web/src/Header.tsxother63 B
references/examples/go-with-internal-web-tsx/internal/web/src/Sidebar.tsxother65 B
references/examples/go-with-internal-web-tsx/main.goscript85 B
references/examples/go-with-internal-web-tsx/package-lock.jsonmanifest0 B
references/examples/go-with-internal-web-tsx/package.jsonmanifest220 B
references/examples/ldap-selfservice/AGENTS.mdmarkdown2.5 KB
references/examples/ldap-selfservice/go.modmanifest45 B
references/examples/ldap-selfservice/internal-AGENTS.mdmarkdown10.0 KB
references/examples/ldap-selfservice/internal-web-AGENTS.mdmarkdown12.1 KB
references/examples/php-with-frontend/.scopesother89 B
references/examples/php-with-frontend/AGENTS.mdmarkdown3.1 KB
references/examples/php-with-frontend/composer.jsonconfig185 B
references/examples/php-with-frontend/package.jsonmanifest306 B
references/examples/php-with-frontend/pnpm-lock.yamlmanifest0 B
references/examples/php-with-frontend/src/Controller.phpscript41 B
references/examples/php-with-frontend/web/AGENTS.mdmarkdown3.1 KB
references/examples/php-with-frontend/web/package.jsonmanifest514 B
references/examples/php-with-frontend/web/src/App.tsxother63 B
references/examples/php-with-frontend/web/src/Button.tsxother215 B
references/examples/php-with-frontend/web/src/Footer.tsxother125 B
references/examples/php-with-frontend/web/src/Header.tsxother122 B
references/examples/php-with-frontend/web/src/main.tsxother68 B
references/examples/php-with-frontend/web/tsconfig.jsonconfig280 B
references/examples/pnpm-workspace/AGENTS.mdmarkdown2.6 KB
references/examples/pnpm-workspace/package.jsonmanifest105 B
references/examples/pnpm-workspace/packages/web/package.jsonmanifest187 B
references/examples/pnpm-workspace/packages/web/src/index.tsscript258 B
references/examples/pnpm-workspace/pnpm-lock.yamlmanifest920 B
references/examples/pnpm-workspace/pnpm-workspace.yamlconfig27 B
references/examples/simple-ldap-go/AGENTS.mdmarkdown2.5 KB
references/examples/simple-ldap-go/examples-AGENTS.mdmarkdown1.8 KB
references/examples/simple-ldap-go/go.modmanifest43 B
references/examples/t3x-rte-ckeditor-image/AGENTS.mdmarkdown2.5 KB
references/examples/t3x-rte-ckeditor-image/Classes-AGENTS.mdmarkdown12.0 KB
references/examples/t3x-rte-ckeditor-image/composer.jsonconfig174 B
references/feedback-memory-schema.mdmarkdown7.2 KB
references/git-hooks-setup.mdmarkdown2.4 KB
references/output-structure.mdmarkdown4.9 KB
references/scripts-guide.mdmarkdown4.9 KB
references/verification-guide.mdmarkdown5.5 KB
scripts/analyze-git-history.shexecutablescript9.8 KB
scripts/check-freshness.shexecutablescript6.3 KB
scripts/detect-golden-samples.shexecutablescript5.3 KB
scripts/detect-heuristics.shexecutablescript3.2 KB
scripts/detect-project.shexecutablescript19.3 KB
scripts/detect-scopes.shexecutablescript12.1 KB
scripts/detect-utilities.shexecutablescript4.3 KB
scripts/extract-adrs.shexecutablescript6.6 KB
scripts/extract-agent-configs.shexecutablescript9.2 KB
scripts/extract-architecture-rules.shexecutablescript19.9 KB
scripts/extract-ci-commands.shexecutablescript12.5 KB
scripts/extract-ci-rules.shexecutablescript15.4 KB
scripts/extract-commands.shexecutablescript11.0 KB
scripts/extract-documentation.shexecutablescript7.7 KB
scripts/extract-github-rulesets.shexecutablescript3.5 KB
scripts/extract-github-settings.shexecutablescript3.3 KB
scripts/extract-ide-settings.shexecutablescript7.0 KB
scripts/extract-platform-files.shexecutablescript7.9 KB
scripts/extract-quality-configs.shexecutablescript14.8 KB
scripts/generate-agents.shexecutablescript113.6 KB
scripts/generate-file-map.shexecutablescript4.4 KB
scripts/lib/config-root.shexecutablescript5.8 KB
scripts/lib/summary.shscript10.7 KB
scripts/lib/template.shexecutablescript13.1 KB
scripts/validate-structure.shexecutablescript8.6 KB
scripts/verify-commands.shexecutablescript22.0 KB
scripts/verify-content.shexecutablescript9.5 KB

references/feedback-memory-schema.md

View on GitHub
# Feedback Memory Schema

Canonical format for **approved session learnings** materialized as project-rule or user-memory files. This schema is the contract between `retro-skill` (which writes these files) and `agent-rules-skill` (which manages how they integrate with AGENTS.md and project documentation).

## When this schema applies

| Destination | Path |
|---|---|
| **user-memory** (personal preference across projects) | `~/.claude/projects/<project-dir-slug>/memory/feedback_<slug>.md` |
| **project-rule** (project-specific convention) | `<project>/docs/feedback/feedback_<slug>.md` |

### Variable definitions

| Variable | Meaning | Example |
|---|---|---|
| `<project-dir-slug>` | Claude Code's encoding of the absolute working directory for user-memory. Slashes are replaced with `-`. | `/home/sme/p` → `-home-sme-p` |
| `<slug>` | kebab-case filename slug for *this specific learning* | `merge-strategy`, `preserve-commit-signing` |

`<project-dir-slug>` and `<slug>` are distinct. `retro-skill` MUST compute `<project-dir-slug>` deterministically from the absolute working directory at the time of materialization (not from any frontmatter field).

For user-memory **global** scope (not tied to a single project): place under whatever project-dir-slug Claude Code uses for global memory; consult `~/.claude/projects/` for the convention in use.

## Schema

```markdown
---
name: <human-readable title; may be free prose>
description: "<one-line summary; used for relevance scoring across sessions>"
type: feedback
originSessionId: <session-id-from-jsonl-filename>
---
**Why:** <1-2 paragraphs explaining the friction and root cause>

**How to apply:** <1-2 paragraphs describing how the assistant should behave next time>
```

### Field semantics

| Field | Required | Notes |
|---|---|---|
| `name` | yes | Human-readable title for the learning. May be a free-form sentence (e.g. `"Preserve commit signing on rewrite operations"`) or a short slug (e.g. `"merge strategy"`). **Not necessarily kebab-case** — the canonical examples use both natural language and slugs. The **filename** uses an independent kebab-case slug (see "Filename slug" below). |
| `description` | yes | One-line summary, ≤200 chars. Used by retro-skill to score relevance against new friction. **MUST be double-quoted** when it contains any of `: # [ ] { } , & * ! \| > ' " % @` or a leading whitespace, or it may break YAML parsing. Safer rule: quote unconditionally. |
| `type` | yes | always `feedback` (distinguishes from other memory types). |
| `originSessionId` | recommended, not required | Session ID where the friction was first observed (audit trail). If absent, the file is still valid but loses traceability. |
| `**Why:**` body section | yes | Start of line, exact form `**Why:** ` (with trailing space). Without this, the file rots — readers can't judge if it still applies. |
| `**How to apply:**` body section | yes | Start of line, exact form `**How to apply:** `. Vague rules don't change behavior. |

### Filename slug (independent from `name`)

The `<slug>` in the filename `feedback_<slug>.md` is **separately chosen** by retro-skill, kebab-case, descriptive of the learning topic. It is NOT required to match `frontmatter.name`.

Canonical examples demonstrate the freedom: file `feedback_skill-sources.md` has `name: "skill source vs cache"`; file `feedback_no-version-bumps-in-feature-prs.md` has `name: "No version bumps in feature PRs"`.

## Project-rule placement

When `retro-skill` materializes a `project-rule` destination:

1. **Write file:** `<project>/docs/feedback/feedback_<slug>.md` (create `docs/feedback/` if missing).
2. **Add AGENTS.md index entry** under a `## Approved learnings` section:

```markdown
## Approved learnings

- [feedback_<slug>.md](docs/feedback/feedback_<slug>.md) — <one-line summary from frontmatter description>
```

The index entry is a single line; the full prose lives in the linked file.

### Section position in AGENTS.md

`## Approved learnings` should be placed **after `## Key Decisions` and before `## Boundaries`** in the `root-thin.md` template's section order. **Place it outside `<!-- AGENTS-GENERATED:START ... -->` markers** so `generate-agents.sh --update` preserves it — this section is managed by retro-skill, not by the generator.

If the project's AGENTS.md is at or near the 150-line cap (the harness AH-02 threshold), prune older inactive learnings or move to a scoped `AGENTS.md` rather than letting the index grow unbounded.

## User-memory placement

When `retro-skill` materializes a `user-memory` destination:

1. **Compute path:** `~/.claude/projects/<project-dir-slug>/memory/feedback_<slug>.md` for project-scoped learnings, OR the global-scope path (consult `~/.claude/projects/`).
2. **Write file** using the schema above.
3. **Add MEMORY.md index entry** under the existing flat `## Topic Files` section (no sub-sections):

```markdown
- [feedback_<slug>.md](feedback_<slug>.md) — <one-line summary>
```

Do not create a separate `## Feedback` heading — MEMORY.md uses a single flat list.

## Why this schema (rationale)

- **Frontmatter** is machine-readable and tool-discoverable.
- **`description`** lets retro-skill detect duplicates and rank relevance.
- **`Why:` + `How to apply:`** structure forces meaningful content; vague file = vague rule.
- **`originSessionId`** allows tracing back to the friction; supports audit and deprecation.

## Validation

A valid feedback file has:

- YAML frontmatter present and parseable by PyYAML / yq.
- Required fields populated (non-empty): `name`, `description`, `type`.
- `description` is double-quoted (or doesn't contain YAML-special characters).
- Both `**Why:** ` and `**How to apply:** ` body markers present at start-of-line.
- File path matches `feedback_<slug>.md` where `<slug>` is kebab-case (independent of frontmatter `name`).

`originSessionId` is recommended but its absence does NOT invalidate the file.

Optional `scripts/verify-feedback-memory.sh` (not yet implemented; tracked as TODO) can enforce this in CI.

## Validation gap (current state)

`references/verification-guide.md` does **not** yet include a row for feedback files. Adding the check is tracked separately. retro-skill's PR-time validation of materialized files is the de-facto enforcement until the agent-rules-skill validator catches up.

## Examples in the wild

The user's own memory at `~/.claude/projects/-home-sme-p/memory/` contains **9 files** following this schema:

- `feedback_dup-repo-verification.md`
- `feedback_merge-strategy.md`
- `feedback_merge-vs-rollout.md`
- `feedback_no-version-bumps-in-feature-prs.md`
- `feedback_obsolete-docs-prefer-delete.md`
- `feedback_preserve-commit-signing.md`
- `feedback_skill-iteration-cadence.md`
- `feedback_skill-sources.md`
- `feedback_subagent-default.md`

Some include an extended `metadata:` block (e.g. `feedback_merge-vs-rollout.md` has `metadata: { node_type: memory, type: feedback }`); that variant is tolerated, not required.

## See also

- `retro-skill/references/destination-taxonomy.md` — Where this schema applies (in retro-skill repo)
- `retro-skill/references/patch-workflow.md` — How retro-skill writes these (in retro-skill repo)
- `references/output-structure.md` — How AGENTS.md indexes feedback files
- `references/verification-guide.md` — How to validate the resulting AGENTS.md
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall