docs-sync

A documentation-maintenance skill that keeps project docs aligned with code changes. It supports documentation sites built with MkDocs, Docusaurus, or VitePress.

In plain words
What is it for?
Use it after a pull request merges, when updating or auditing docs, or when maintaining documentation navigation and site structure.
Why use it?
It helps find instructions and reference pages that became outdated after code changes. It also helps organize the documentation site and audit it for stale content.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/chriscox/agent-skills/docs-sync
Any agent
npx skills add chriscox/agent-skills --skill docs-sync
Clone the repo
git clone --depth 1 https://github.com/chriscox/agent-skills

Made for: Claude Code, Codex.

Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,088 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00147 $0.02088
Opus 5 $0.00073 $0.01044
Sonnet 5 $0.00029 $0.00418
Haiku 4.5 $0.00015 $0.00209

Measured 2d ago against content hash 700b78d43ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-sync 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 2d 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.

skills/docs-sync/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Sync

Prerequisites

  • git
  • gh (GitHub CLI, authenticated via gh auth login)

Keep project documentation current with code changes. Three modes:

  1. Content sync — update doc content after code changes
  2. Site management — maintain doc site structure and navigation
  3. Docs audit — identify stale docs that need attention

Repo Discovery

Before doing anything, discover the project's documentation setup:

  1. Run git rev-parse --show-toplevel to find the repo root
  2. Check for .docs-sync.yml at the repo root — if it exists, read it and use its values for all paths, roles, and site config
  3. If no config file, auto-discover:
    • Doc site engine: look for mkdocs.yml, docusaurus.config.js, .vitepress/config.*
    • Doc directory: look for docs/, documentation/, wiki/
    • Known doc files: scan for common patterns (see Doc Roles below)
    • Convention files: CLAUDE.md, AGENTS.md, CONTRIBUTING.md
  4. Run gh repo view --json name,owner to confirm the repo

Config File: .docs-sync.yml

Optional config file at repo root. All fields are optional — auto-discovery fills gaps. See docs-sync.yml in the skill directory for a starter.

# Map your doc files to roles so the skill knows what content belongs where
docs:
  - path: docs/features.md
    role: features

  - path: docs/architecture.md
    role: architecture

  - path: CHANGELOG.md
    role: changelog
    format: keep-a-changelog

  - path: CLAUDE.md
    role: conventions

  - path: README.md
    role: readme

# Doc site configuration (optional)
site:
  engine: mkdocs               # mkdocs | docusaurus | vitepress
  config: mkdocs.yml           # path to site config
  auto_nav: true               # update navigation when docs change

Doc Roles

Roles tell the skill what kind of content a file contains, so it knows how to update it.

Role Content Updated when...
features User-facing feature descriptions, shortcuts, status New feature added, feature behavior changes
architecture App structure, data flow, patterns, diagrams New components, changed patterns, refactors
conventions Dev setup, coding rules, build commands Build process changes, new conventions adopted
changelog Version-based change history Any significant change (follows format: keep-a-changelog, conventional, custom)
readme Project overview, install instructions, quick start Major features, install process changes
api API reference, endpoints, function signatures Public API changes
guide Tutorials, how-tos, walkthroughs Workflow changes, new capabilities
custom Anything else — describe in the description field Based on your description

Read the full file on GitHub · 203 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 203 lines · 147 tokens per session scan A 700b78d43ef9

Subscribe to this mod's changes

docs-sync is a skill published in the GitHub repository chriscox/agent-skills (10 stars, last pushed 5mo ago), licensed MIT. It adds 147 tokens to every session and 2,088 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

api-security-patterns

Skill "api-security-patterns" from frank-luongt/faos-skills-marketplace, covering advanced api security patterns, when to use this skill, how it works, step 1: threat model the api surface and step 2: implement the authentication layer.

frank-luongt/faos-skills-marketplace · 0 tokens

llm-app-patterns

Skill "llm-app-patterns" from frank-luongt/faos-skills-marketplace, covering 🤖 llm application patterns, when to use this skill, 1. rag pipeline architecture, 1.1 document ingestion and chunking strategies.

frank-luongt/faos-skills-marketplace · 0 tokens

embedding-strategies

Skill "embedding-strategies" from frank-luongt/faos-skills-marketplace, covering embedding strategies, do not use this skill when, instructions, use this skill when and core concepts.

frank-luongt/faos-skills-marketplace · 0 tokens

llm-evaluation

Skill "llm-evaluation" from frank-luongt/faos-skills-marketplace, covering llm evaluation, do not use this skill when, instructions, use this skill when and core evaluation types.

frank-luongt/faos-skills-marketplace · 0 tokens

multi-agent-patterns

Skill "multi-agent-patterns" from frank-luongt/faos-skills-marketplace, covering multi-agent architecture patterns, when to activate, core concepts, detailed topics and why multi-agent architectures.

frank-luongt/faos-skills-marketplace · 0 tokens

langchain-architecture

Skill "langchain-architecture" from frank-luongt/faos-skills-marketplace, covering langchain architecture, do not use this skill when, instructions, use this skill when and core concepts.

frank-luongt/faos-skills-marketplace · 0 tokens