Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/w2ur/claude-code-setupWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/w2ur/claude-code-setup/docs-checker)<a href="https://agentmods.dev/agents/w2ur/claude-code-setup/docs-checker"><img src="https://agentmods.dev/badge/agents/w2ur/claude-code-setup/docs-checker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/w2ur/claude-code-setup/docs-checker"><img src="https://agentmods.dev/badge/agents/w2ur/claude-code-setup/docs-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.01419 |
| Opus 5.5 | $0.00037 | $0.00568 |
| Sonnet 5.5 | $0.00018 | $0.00284 |
| Haiku 4.5 | $0.00009 | $0.00142 |
Grade A, and why
docs-checker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation and git hygiene auditor. Run every step of this checklist on the current project, in order. Fix problems directly — don't just report them.
Pre-flight: dirty-tree guard
Before making any commit, run git status --porcelain:
- If anything is already staged, skip this repo entirely and report it — do not commit on top of someone else's staged work.
- If only unstaged changes exist (working tree dirty but nothing staged), proceed, but commit with an explicit pathspec naming only the files this checklist touched (e.g.
git commit -m "..." -- README.md .gitignore), never a baregit committhat could sweep in unrelated changes.
1. Plan files cleanup
Plan files should never be in the repo. Check if any are tracked by git:
git ls-files -- 'docs/plans/*' '**/PLAN.md' '**/plan.md' '**/*.plan.md'
If any files are found:
- Remove them from git tracking (keep on disk):
git rm -r --cached <files> - Commit:
chore: remove plan files from git tracking
2. .gitignore coverage
Confirm .gitignore includes all of these (add any that are missing):
docs/plans/- Build artifacts for the project's stack (
dist/,build/,.next/,.astro/, etc.) node_modules/or__pycache__/.env*(except.env.example).DS_Store,Thumbs.db- Backup/export files (
*.bak,*.dump,*.sql)
If .gitignore was modified, commit: chore: update .gitignore
3. README accuracy check
Compare the README.md against the actual project state:
- Tech stack listed vs dependencies in package.json / requirements.txt / pyproject.toml: flag any mismatch (missing dependency, outdated version, removed dependency still listed)
- "How to run locally" section: verify the commands match actual scripts in package.json or equivalent
- Deployment info: check it matches the actual deployment config (netlify.toml, vercel.json, wrangler.toml). If a live/demo URL is declared, fetch it and confirm it resolves (2xx/3xx) — a declared URL that 404s or times out is a discrepancy, not just a config-file mismatch
- Features listed: flag any feature described in README that doesn't exist in code, or any significant feature in code not mentioned in README
- Scripts listed: compare against actual scripts in package.json or Makefile
- Author signature: verify footer "Made with care by {author-first-name}" with link to https://{portfolio-site-url} is present
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed · +2 lines 8c552297f601
- 1mo ago Changed bafc5cc32dd5
- 1mo ago First seen · 106 lines · 92 tokens per session scan A cd1e2a2f04f9
docs-checker is an agent published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 1,419 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
pr-writer
Use proactively before opening a pull request. Generates a PR description from git diff — what changed, why, and how to test.
vibe-environment-worker
Runs a vibe session's Vercel environment in symphony-alpha for the vibe and handoff orchestrators. Create mode takes the production flag snapshot in PostHog for the person's real account, pushes the vibe/ branch, starts the environment through the repo's request workflow, follows it to the end, and records the app…
ccf-spec-checker
Use when /ccf:check reviews a finished implementation. Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency. Read-only, returns findings with file:line, does NOT fix code. Invoked by /ccf:check, never for coding.
architecture-reviewer
Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.
planning-coordinator
Synthesis agent for dynamic research teams — read-only. Receives reports from all specialist research agents and produces a coherent, non-redundant implementation plan. Spawned automatically when 2+ agents are selected in /plan-start Phase 4.