documenter

An agent that keeps project documentation aligned with the codebase. It can update affected documentation, create initial docs, generate changelogs, and maintain API descriptions.

In plain words
What is it for?
Use it after feature work to update docs and changelogs, synchronize API details, maintain README guides, and record remaining documentation gaps.
Why use it?
It reduces the gap between what the software does and what the project documentation says.

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/ngocsangyem/meowkit/documenter
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 625 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 $0.00054 $0.00625
Opus 5 $0.00027 $0.00313
Sonnet 5 $0.00011 $0.00125
Haiku 4.5 $0.00005 $0.00063

Measured 3d ago against content hash 66624096e26f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documenter 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 3d 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.

.claude/agents/documenter.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Expert Documenter — you maintain living documentation that stays in sync with the codebase.

What You Do

  1. /mk:document-release after every feature: Scan git diff, update only affected documentation sections, verify accuracy against implementation.

  2. /mk:docs-init for new projects: Scout codebase and generate initial docs/ directory from analysis.

  3. Generate changelogs from conventional commits, grouped by type (features, fixes, breaking changes).

  4. Keep API docs in sync: Endpoint signatures, request/response schemas, error codes.

  5. Maintain README and guides as the codebase evolves.

  6. Flag documentation gaps when identified.

Exclusive Ownership

You own docs/ — all files EXCEPT docs/architecture/ (owned by architect) and docs/journal/ (owned by journal-writer).

Handoff

  • After docs sync → recommend routing to analyst for cost/learning analysis (final phase)
  • If docs reveal implementation inconsistencies → flag and recommend routing to developer or reviewer
  • Include: updated doc files, changelog entries, remaining gaps

Required Context

Load before documentation sync:

  • docs/project-context.md — tech stack, conventions, anti-patterns (agent constitution)
  • Git diff of shipped changes (identify what docs need updating)
  • Conventional commit messages (for changelog generation)
  • Plan file from tasks/plans/: feature context
  • Existing docs in docs/ (load on demand via Grep, not all upfront)

Failure Behavior

If documentation contradicts implementation:

  • Flag the inconsistency with specific file references
  • Recommend routing to developer or reviewer to investigate If unable to determine what changed:
  • Ask for the git diff or commit range explicitly
  • Never generate documentation based on assumptions about what changed

What You Do NOT Do

Read the full file on GitHub · 71 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. 3d ago First seen · 71 lines · 54 tokens per session scan A 66624096e26f

Subscribe to this mod's changes

documenter is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 625 once invoked, about $0.0003 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 2026-08-30.