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/docs-plus/docs.plus/commit-reviewnpx skills add docs-plus/docs.plus --skill commit-reviewgit clone --depth 1 https://github.com/docs-plus/docs.plusWhat 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 | $0.00053 | $0.03812 |
| Opus 5 | $0.00026 | $0.01906 |
| Sonnet 5 | $0.00011 | $0.00762 |
| Haiku 4.5 | $0.00005 | $0.00381 |
Grade A, and why
commit-review 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 yesterday.
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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Review
Review all changes, group them by intent, and produce Conventional Commit messages terse and exact enough for any company's git log. Why over what. No fluff.
The rule that overrides everything
Never commit without explicit user approval. Always present the report first and wait for a "go". No exceptions, no shortcuts, no "this one is obvious".
Step 0 — detect repo conventions
Before drafting anything, learn what this repo actually accepts:
- Read
scripts/hooks/commit-msg.sh,.husky/commit-msg,commitlint.config.*, orpackage.jsoncommitlintblock — note the regex and any non-conventional shapes (e.g. deploy triggers like(build): front). git log --oneline -50to detect: capitalization after the colon, scope style (feat(webapp)vsfeat:), body habits, and whether the repo's local hooks inject trailers (Made-with: …,Generated-by: …). Those trailers are repo policy, so leave them alone.- If the hook rejects the Conventional
!breaking-change marker (regex without an!slot — common), use theBREAKING CHANGE:footer only. Neverfeat!:/feat(scope)!:until Step 0 confirms the regex accepts it. - If the repo defines extra shapes (e.g.
^\(build\):.*deploy trigger), accept them as first-class. Don't force everything into Conventional.
Step 1 — context depth (tier the work)
Default is fast: current conversation + working-tree diff + AGENTS.md + every AGENTS.md on the path of the changed files. Most commits don't need more.
Escalate to session archaeology (tier 2) when any of:
- This session has < 3 user messages but the diff is large
- Branch has been worked on > 48h (see anchor below)
- User explicitly asks for "full context" / "session-aware" review
- You're picking up a branch you weren't part of in this session
Tier 2 recipe — session archaeology
- Anchor on git history, not file
mtime. Pick anchor by scope —mtimeis reset bygit checkout, formatters,bun install, and pre-commit hooks; never use it.- Reviewing only uncommitted changes (the common case):
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.
- yesterday First seen · 339 lines · 53 tokens per session scan A a6941aba92c1
commit-review is a skill published in the GitHub repository docs-plus/docs.plus (88 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 3,812 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
docx
Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.
document-converter
Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown. Provides the agent with conversion strategies for academic and research workflows.
docx-manipulation
Create, edit, and manipulate Word documents programmatically using python-docx.
add-format
End-to-end checklist for adding a new input or output format to AILANG Parse (docparse). Use when the user says 'add support for X format', 'wire up a new parser', 'add .foo format', 'add a parser for .bar', 'support .baz files', 'ship format X', 'can we parse .qux', 'new format rollout', or mentions a file extension…
landing-page
Create a new AILANG Parse documentation/landing page targeting a specific keyword or topic. Use when user says 'new landing page', 'new page for X', 'create a page about X', 'landing page for keyword X', or wants to add a documentation page to the docs/ site. Also use when the user references long-tail keywords, SEO…
benchmark
Run OfficeDocBench evaluation and refresh benchmark scores across the AILANG Parse website. Use when the user says 'run benchmarks', 'rerun the benchmark', 'refresh benchmark numbers', 'update bench scores', 'regenerate summary.json', mentions OfficeDocBench, asks to evaluate parsers, asks why scores are out of sync…