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/urmzd/dotfiles/sync-docsnpx skills add urmzd/dotfiles --skill sync-docsgit clone --depth 1 https://github.com/urmzd/dotfilesWhat 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 | $0.00077 | $0.01459 |
| Opus 5 | $0.00039 | $0.00730 |
| Sonnet 5 | $0.00015 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
sync-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Sync
Audit whatever documentation the project has, fix drift, and keep cross-references consistent. This skill owns the audit loop, not the list of files.
For repos with this skill installed, start with the bundled hygiene gate:
checker="${CLAUDE_SKILL_DIR:-$HOME/.agents/skills}/sync-docs/scripts/check-doc-hygiene.sh"
"$checker" .
If running from a chezmoi source tree before chezmoi apply, use the source path:
dot_agents/skills/sync-docs/scripts/executable_check-doc-hygiene.sh .
When to Use
- After implementing a new feature or significant refactor
- When docs haven't been updated in a while
- When the user asks for documentation to be clean, precise, accurate, or up to date
- When adding or editing
dot_agents/skills/*/SKILL.mdordot_agents/agents/*.md - As a scheduled agent to catch drift
- Before releases to ensure docs match the code
Principle
Do not enumerate required files here. Different projects carry different docs, and the authoritative rules for each doc type live in the skill that owns it. This skill's job is to:
- Discover what docs the project actually has
- Detect drift between docs and code (and between docs and each other)
- Delegate file-specific fixes to the owning skill
- Verify cross-references agree
Audit Loop
1. Discover
Glob for documentation artifacts that exist in the repo. Do not assume any specific file is present. Common locations: repo root (README.md, AGENTS.md, llms.txt, community health files), docs/, skills/, language manifests.
2. Detect drift
Generic drift checks that apply to any project:
Text hygiene. Tracked text, comments, help output, and docs must not contain em dashes. Use periods, colons, commas, or indexed bullets instead. Check with:
rg -n "$(printf '\\342\\200\\224')" .
Evidence-backed accuracy. Every behavior claim, command, install step, and tool name must be checked against the current repo, manifest, CLI help, or authoritative source before editing. If the evidence is missing, flag it instead of guessing.
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 First seen · 138 lines · 77 tokens per session scan A 66a0d3574366
sync-docs is a skill published in the GitHub repository urmzd/dotfiles (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,459 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
benchling-integration
Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.
astropy
Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.
esm
Comprehensive toolkit for EvolutionaryScale protein language models including ESM3 (generative multimodal design across sequence, structure, and function) and ESM C (efficient embeddings). Use for protein sequence/structure/function tasks, inverse folding, embeddings, variant design, and ESMFold2 structure prediction…
mcp-notion-usage-guide
MCP Notion工具使用指南，包含常见问题解决方案和最佳实践。使用当： (1) 访问Notion数据库view URL出现"URL type view not currently supported"错误， (2) 需要获取数据库schema和表结构信息， (3) 查询数据库中的条目内容， (4) 创建页面时MULTISELECT字段值不存在导致失败， (5) 需要更新数据库schema添加新选项， (6) 开发需要集成Notion数据的自动化工作流， (7) querydatasources/query-database-view返回Business Plan要求错误， (8) 需要在无Business…
scan-commit
Automatically scan the repository for unstaged/untracked changes, group them into logical commits using hunk-level analysis, stage and commit them following Conventional Commits.
create-pr
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes.