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/huggingface/openenv/update-docsnpx skills add huggingface/OpenEnv --skill update-docsgit clone --depth 1 https://github.com/huggingface/OpenEnvWhat 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 | $0.00028 | $0.00660 |
| Opus 5 | $0.00014 | $0.00330 |
| Sonnet 5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
update-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 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/update-docs
Find and fix stale documentation after API changes.
EXECUTE THESE STEPS NOW
When this skill is invoked, you MUST execute these steps immediately.
Step 1: Identify Changed Files
Run:
git diff --name-only main...HEAD -- '*.py'
If no changes are found relative to main (e.g., on main or no upstream), fall back to:
git diff --name-only HEAD~1 -- '*.py'
If that also fails, ask the user which files changed.
Collect the list of changed Python files.
Step 2: Extract API Changes
For each changed .py file, compare old vs new signatures using the same ref that worked in Step 1:
# If Step 1 used main...HEAD:
git diff main...HEAD -- <file>
# If Step 1 fell back to HEAD~1:
git diff HEAD~1 -- <file>
Look for changes to:
- Function/method signatures (def lines)
- Class names and init signatures
- Module-level constants and type aliases
- Removed or renamed public symbols
Build a list of (old_signature, new_signature) pairs.
If no API changes are found (only internal logic changes), report "No API changes detected — no docs update needed" and stop.
Step 3: Spawn Docs Updater Agent
Use the Task tool to spawn the docs-updater agent. IMPORTANT: the
description field MUST contain "docs-updater" so the SubagentStop
hook fires correctly.
Task tool:
subagent_type: general-purpose
description: "docs-updater propagation"
prompt: |
You are a docs-updater agent. Read .claude/agents/docs-updater.md
for your full instructions.
Here are the API changes to propagate:
Changed files: <list>
API changes:
- `old` → `new`
...
Search the entire repo for references to the old APIs and update
them to match the new signatures. Follow the process in
.claude/agents/docs-updater.md exactly.
Step 4: Review Results
After the agent returns:
- Review the update report
- Verify no test files were touched
- Verify changes are minimal and correct
Report the summary to the user.
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 · 114 lines · 28 tokens per session scan A f256c73167e9
update-docs is a skill published in the GitHub repository huggingface/OpenEnv (2,531 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 28 tokens to every session and 660 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…