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 skills add jtsternberg/claude-plugins --skill check-third-party-docsgit clone --depth 1 https://github.com/jtsternberg/claude-pluginsWrote 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/jtsternberg/claude-plugins/check-third-party-docs)<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/check-third-party-docs"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/check-third-party-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 5.1 | $0.00066 | $0.01261 |
| Opus 5 | $0.00033 | $0.00630 |
| Sonnet 5 | $0.00013 | $0.00252 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
check-third-party-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 7d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check third-party docs
We vendor copies of the upstream docs for the external tools our skills wrap
(e.g. the MacWhisper mw CLI behind work-with-media:macwhisper-cli). This skill
re-fetches those upstream docs, shows what changed since the last cache, and
proposes edits to the local skills/docs that the change affects — so our
wrapper docs never silently drift behind the tool.
Cached docs live in docs/third-party/cached/*.md. Each is self-describing —
its frontmatter names the upstream source URL, when it was last_updated, and
the local skills/docs it informs (related). There is no separate manifest; the
cache dir is the registry. Run everything from the repo root.
Frontmatter contract (every cached doc)
---
source: <upstream URL> # what to re-fetch
cached_from: research-tools:fetch-docs --md # how it was fetched (for a matching refetch)
last_updated: <YYYY-MM-DD> # bumped on every refresh
related: # what this doc informs, so review is mechanical
- work-with-media:macwhisper-cli # a skill (plugin:skill) …
# - plugins/<plugin>/README.md # … or an explicit repo-relative doc path
---
Refresh workflow
Do this for each cached doc (all of them, or the one the user named). The order
matters — overwrite the cached file before diffing so git diff naturally
shows the committed (old upstream) version against the working-tree (new) version.
-
Read the cached doc's frontmatter to get its
source,cached_from, andrelated. -
Re-fetch the source with the
research-tools:fetch-docsskill, matchingcached_from(use--mdwhen the cached copy is markdown). It writes the fresh copy to a/tmp/fetch-docs-*.mdpath and returns that path. Pass--ttl=0to force a live refetch and bypass fetch-docs' 24h cache. -
Overwrite the cached file — replace its body with the fresh
/tmpfetch and refresh the frontmatter: keepsource/cached_from/related, bumplast_updatedto today (date +%F). Store the fetch body exactly as fetched — never hand-clean it — so the next refresh diffs against the same pipeline output instead of fighting your edits. Example, run from the repo root:
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.
- 7d ago First seen · 109 lines · 66 tokens per session scan A 2ac364679463
check-third-party-docs is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,261 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…