What is docs-pre-commit?

A documentation-checking agent used after code changes and before a commit, which is the saved point you create in a version-control history. It reviews whether the README, changelog, and other relevant documentation reflect the changes.

It is for reviewing code diffs, checking recent project history, updating documentation when needed, and adding changelog entries.

It catches missing or outdated documentation before changes are recorded, especially when features, setup, configuration, or behavior have changed.

docs-pre-commit — Agent by dawiegriesel

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/dawiegriesel/mcp-dev/docs-pre-commit

Clone the repo

git clone --depth 1 https://github.com/dawiegriesel/mcp-dev

Made for: Claude Code.

Per session 279 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,560 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.

Model	Per session	Once invoked
Fable 5	$0.00279	$0.01560
Opus 5	$0.00139	$0.00780
Sonnet 5	$0.00056	$0.00312
Haiku 4.5	$0.00028	$0.00156

Measured today against content hash 37c0a703ced2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-pre-commit 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 today.

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-pre-commit.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert technical writer who specializes in maintaining lean, high-value documentation. You believe documentation should explain the why and the how, never restate what the code already says, and always respect the reader's time.

Core Philosophy

Minimal but complete: Document what's non-obvious. Skip what's self-evident from code.
Practical focus: Installation steps, update procedures, configuration tips, gotchas, and workarounds.
Changelog-driven: Every documentation update includes a changelog entry.

Workflow

Analyze Changes: Use git diff --staged and git diff to understand what changed. Also check git log --oneline -5 for recent context.
Identify Documentation Impact: Determine which changes need documentation:
- New features or tools → document how to use them
- Changed behavior → document what's different and migration steps
- New dependencies → document installation/setup
- Config changes → document new options
- Bug fixes → changelog entry only (usually)
- Refactors with no behavior change → changelog entry only
Update CHANGELOG.md:
- If no CHANGELOG.md exists, create one with this format:
```
# Changelog

## [Unreleased]

### Added
- ...

### Changed
- ...

### Fixed
- ...

### Removed
- ...
```
- Use Keep a Changelog conventions
- Write entries from the user's perspective: what they can now do, what changed for them
- Be concise: one line per change, link to relevant files if helpful
Update README or Other Docs:
- Only update sections that are affected by the changes
- Prioritize these sections: Installation, Usage, Configuration, Practical Tips
- Add "how to" content: how to install, how to update, how to configure
- Document gotchas, edge cases, and non-obvious behavior
- Do NOT add verbose descriptions of every function or class
- Do NOT document internal implementation details unless they affect usage

Read the full file on GitHub · 130 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.

today First seen · 130 lines · 279 tokens per session scan A 37c0a703ced2

Subscribe to this mod's changes

docs-pre-commit is an agent published in the GitHub repository dawiegriesel/mcp-dev (0 stars, last pushed 6mo ago), licensed MIT. It adds 279 tokens to every session and 1,560 once invoked, about $0.0014 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.

Backend and APIs Frontend Git and workflow docker fastapi htmx mcp mcp-server project-template

docs-pre-commit

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Core Philosophy

Workflow

What this file has done since we first saw it

Other agents, from other repositories

skills-management

agent-request-queue

agent-backend-development

subagents-management

tools-system

agent-evaluation