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 SteveVitali/agent-skills --skill refresh-repo-docsgit clone --depth 1 https://github.com/SteveVitali/agent-skillsWrote 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/stevevitali/agent-skills/refresh-repo-docs)<a href="https://agentmods.dev/skills/stevevitali/agent-skills/refresh-repo-docs"><img src="https://agentmods.dev/badge/skills/stevevitali/agent-skills/refresh-repo-docs/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/skills/stevevitali/agent-skills/refresh-repo-docs"><img src="https://agentmods.dev/badge/skills/stevevitali/agent-skills/refresh-repo-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.02623 |
| Opus 5 | $0.00038 | $0.01311 |
| Sonnet 5 | $0.00015 | $0.00525 |
| Haiku 4.5 | $0.00008 | $0.00262 |
Grade A, and why
refresh-repo-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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Repo Docs
Converge a repo's human-facing documentation onto the code it describes. Wrong docs are worse than no docs — a reader who follows a stale setup guide or copies a dead example loses both their time and their trust in every other doc in the repo.
Scope boundary: this skill owns README(s), docs/, CHANGELOG, CONTRIBUTING,
guides, examples, ADRs. It does not touch agent-facing docs (AGENTS.md,
CLAUDE.md, agent_docs/) — those have different consumers, quality bars,
and their own skill: agent-docs. If you find agent-doc drift here, note it
in the report and recommend an agent-docs refresh run.
Two rules the whole workflow hangs on:
- Scope by evidence, not by reading everything. The unit of work is a flagged doc, not the codebase. Deterministic signals (broken references, docs older than the code they describe) pick the worklist; reading every source file to "build a mental model" burns the context window before the first fix. Code gets read doc-first: for each claim, read exactly the code that can prove or refute it.
- Never write a claim you didn't verify. Every command, path, flag, default, and code example you write or keep must be checked against the current code — run it if read-only, read the source if not. The failure mode of doc syncing is replacing old guesses with new ones.
Phase 0 — Detect
Run the drift detector from the repo root (read-only):
// turbo
bash scripts/check-repo-docs-freshness.sh <scope>
It writes /tmp/repo-docs-freshness.json:
- the doc corpus discovered in scope (agent docs excluded)
- broken references per doc — links and file paths that no longer exist (critical, deterministic)
- stale suspects — docs whose referenced code files have commits newer than the doc's own last commit, with the recency gap (suspicion, not proof: code can change without invalidating prose)
Build the worklist:
audit: incremental(default) → every doc with broken references or a stale-suspect flag; plus, ifsincewas given, every doc that references files changed ingit diff --name-only <since>..HEAD.audit: full→ every doc in the corpus. (Expensive; use for a first run on a neglected repo or a periodic deep pass.)
What ships with it
1 file 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.
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 Changed · +17 lines 8952f4c929f6
- 11d ago First seen · 210 lines · 76 tokens per session scan A ca6d97383a2f
refresh-repo-docs is a skill published in the GitHub repository SteveVitali/agent-skills (12 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 2,623 once invoked, about $0.0004 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
remove
Remove a deployed framework or addon from the current workspace.
ln-62-repository-publisher
Commits, pushes, and remotely verifies authorized repository changes. Not for releases, package publication, or announcements.