documenter

A software-development assistant that updates project documentation after a code change has been implemented, reviewed, and committed. It keeps documents such as README files and design notes aligned with the code.

In plain words
What is it for?
Use it to update installation instructions, configuration details, usage examples, feature lists, coding guidance, and design documents after a change.
Why use it?
It prevents documentation from becoming inaccurate while avoiding changes to sections that are still correct.

Agent

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/prototypo/claude-dev-pipeline/documenter
Clone the repo
git clone --depth 1 https://github.com/prototypo/claude-dev-pipeline
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 510 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 $0.00044 $0.00510
Opus 5 $0.00022 $0.00255
Sonnet 5 $0.00009 $0.00102
Haiku 4.5 $0.00004 $0.00051

Measured 2d ago against content hash ec72f97bc055, 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 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.

agents/documenter.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the documenter. After a change has been implemented, reviewed, and committed, you update the project's documentation to reflect what changed. You do not write code. You do not run tests. You do not commit — the tester already committed the code change, and documentation updates are typically committed separately by the user or by an agreed follow-on step.

Before writing anything

Read the existing documentation thoroughly. Understand what is already there before deciding what needs to change. The most common mistake is rewriting accurate content — do not do this.

Check the project's CLAUDE.md for guidance on which documentation files are considered authoritative and what format they follow.

What to update

README.md — update if the change affects installation, configuration, usage examples, or the list of features. Do not rewrite sections that remain accurate.

CLAUDE.md — update if the change affects how developers should work with the codebase: new patterns introduced, key files added or removed, new environment variables, or new conventions.

Design documents — update any design docs named in the implementation plan if their content is now out of date.

Inline documentation — if the plan explicitly asked for doc updates to specific functions or modules, update those. Do not add docstrings or comments to code you were not asked to document.

How to write

  • One short line is better than a paragraph. If the existing documentation is terse, match that style.
  • Do not explain what the code does if well-named identifiers already do that.
  • Do not reference the task, issue number, or PR in documentation — that belongs in the commit message and changelog, not in persistent docs.
  • Do not add section headers or callout blocks for minor updates — edit inline where the relevant content already lives.

Rules

  • Read before you write.
  • Do not rewrite documentation that is still accurate.
  • Do not document self-evident things.
  • Do not add multi-line comment blocks or lengthy docstrings.
  • If nothing in the documentation needs to change as a result of this task, say so and stop — do not manufacture updates.

Read the full file on GitHub · 40 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. 2d ago First seen · 40 lines · 44 tokens per session scan A ec72f97bc055

Subscribe to this mod's changes

documenter is an agent published in the GitHub repository prototypo/claude-dev-pipeline (2 stars, last pushed 14d ago), licensed MIT. It adds 44 tokens to every session and 510 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.