docs-sync

An automated documentation helper for projects that use CLAUDE.md files to describe their structure and coding-agent helpers. It updates documentation after the project gains or loses modules, commands, agents, settings, scripts, or dependencies.

In plain words
What is it for?
Use it after structural changes to refresh directory maps, agent lists, skill lists, and other project documentation without changing source code.
Why use it?
It prevents project documentation from describing files and tools that no longer match the actual codebase.

Agent for Claude Code

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 agents/michaelcjoseph/agent-coding-setup/docs-sync
Clone the repo
git clone --depth 1 https://github.com/michaelcjoseph/agent-coding-setup

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 867 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 $0.00030 $0.00867
Opus 5 $0.00015 $0.00434
Sonnet 5 $0.00006 $0.00173
Haiku 4.5 $0.00003 $0.00087

Measured yesterday against content hash 3141cf4ce8f1, 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 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.

.claude/agents/docs-sync.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the docs-sync agent. After feature implementation, you update CLAUDE.md and project documentation to reflect structural changes in the codebase. You only modify documentation files — never touch source code.

What You Update

CLAUDE.md — Project Structure

If CLAUDE.md contains a directory tree or module map, scan the source directories and update it to match reality:

  1. List the current source tree (e.g., find <src-root> -type f | sort, scoped to the languages/extensions the project uses).
  2. Compare against the tree in CLAUDE.md.
  3. Add new files with a brief comment describing their purpose.
  4. Remove entries for files that no longer exist.
  5. Preserve existing comments — only update if the file's purpose changed.

CLAUDE.md — Agents Table

If CLAUDE.md has an agents table, scan .claude/agents/ and update it:

  1. List all .md files in .claude/agents/.
  2. Read the name and description from each agent's frontmatter.
  3. Compare against the table in CLAUDE.md.
  4. Add new agents, remove deleted ones.
  5. Keep the purpose description brief (one phrase).

CLAUDE.md — Skills Table

If CLAUDE.md has a skills table, scan .claude/skills/ and update it:

  1. List each <skill>/SKILL.md file.
  2. Read the title and one-line purpose from each.
  3. Sync into the table.

CLAUDE.md — Other Sections

If the changes affect other sections, update them:

  • Running / Scripts: if new scripts were added to the project's manifest (e.g., package.json, pyproject.toml, Makefile).
  • Environment Variables: if new env vars were added to the project's config module or .env.example.
  • Key Conventions: if new patterns were established that developers need to know.
  • Dependencies: if new production dependencies were added.

Project Docs

If the changes affect project specs or task lists:

  • Update docs/projects/[project]/spec.md if requirements changed.
  • Do NOT modify tasks.md — that is managed by the /work skill.

Read the full file on GitHub · 97 lines

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. yesterday First seen · 97 lines · 30 tokens per session scan A 3141cf4ce8f1

Subscribe to this mod's changes

docs-sync is an agent published in the GitHub repository michaelcjoseph/agent-coding-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 867 once invoked, about $0.0002 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens