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.
npx agentmods add skills/mfbari/claude-skill-generate-docs/generate-docsnpx skills add mfbari/claude-skill-generate-docs --skill generate-docsgit clone --depth 1 https://github.com/mfbari/claude-skill-generate-docsWrote 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/skills/mfbari/claude-skill-generate-docs/generate-docs)<a href="https://agentmods.dev/skills/mfbari/claude-skill-generate-docs/generate-docs"><img src="https://agentmods.dev/badge/skills/mfbari/claude-skill-generate-docs/generate-docs.svg" alt="Measured on agentmods" 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 | $0.00169 | $0.01428 |
| Opus 5 | $0.00084 | $0.00714 |
| Sonnet 5 | $0.00034 | $0.00286 |
| Haiku 4.5 | $0.00017 | $0.00143 |
Grade A, and why
generate-docs 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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
generate-docs
You are the orchestrator for a documentation-generation pipeline. Coordinate five phases — Bootstrap → Explore → Generate → Verify → Context Update — in an iterative loop until every document meets grade A on every rubric dimension, or the retry budget is exhausted.
Detailed instructions for each phase live in references/. Read the relevant reference file when you
reach that phase (progressive disclosure — don't load them all up front).
| Phase | What it does | Read |
|---|---|---|
| 0 — Bootstrap | Detect/back-up/create CLAUDE.md; note AGENTS.md | references/context-files.md |
| 1 — Explore | Scan the codebase across 8 domains → docs/_exploration_report.md |
references/exploration.md |
| 2 — Generate | Write ~15 docs in docs/ with Mermaid diagrams |
references/generation.md |
| 3 — Verify | Grade every doc A–F against the source → docs/_verification_report.md |
references/verification.md + references/grading-rubric.md |
| 4 — Context Update | Update CLAUDE.md + write AGENTS.md (progressive disclosure) | references/context-files.md |
Configuration
- Max retries: the first argument, if given (e.g.
generate-docs 5). If blank or non-numeric, default to 3. - Output directory:
docs/at the project root. - Passing grade: A on every document and every rubric dimension.
- Completion: when ALL docs score A across ALL dimensions, or max retries is reached.
How to run the phases (any harness)
This skill is harness-agnostic. Each phase is a batch of independent work that parallelizes cleanly:
- If your harness supports subagents / parallel tasks (e.g. a Task tool, an agent-spawn
primitive, or a workflow engine): dispatch the phase's work as parallel subagents — 8 explorers in
Phase 1, up to 15 writers in Phase 2, 1 verifier in Phase 3. Give each subagent the matching
references/file as its instructions, plus its specific brief/doc. Prefer read-only tools for explorers and verifiers. - If your harness has no subagents: perform each phase's work yourself, sequentially, following
the same
references/files. The output is identical; only the wall-clock time differs.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/agents-md.md 1.9 KB
- assets/claude-md-section.md 2.9 KB
- examples/agents-md-example.md 3.4 KB
- examples/claude-md-example.md 3.6 KB
- examples/README.md 706 B
- examples/verification-report-example.md 1.8 KB
- references/context-files.md 2.9 KB
- references/exploration.md 9.4 KB
- references/generation.md 7.4 KB
- references/grading-rubric.md 4.9 KB
- references/verification.md 4.9 KB
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.
- 4d ago First seen · 134 lines · 169 tokens per session scan A 22bc959d76d7
generate-docs is a skill published in the GitHub repository mfbari/claude-skill-generate-docs (5 stars, last pushed 1mo ago), licensed MIT. It adds 169 tokens to every session and 1,428 once invoked, about $0.0008 per session on Opus 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 skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
golden-rss
Use when testing the rss golden build.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.