What is documentalist?

An autonomous project documentation manager that follows the repository's documentation rules and workflows.

Use it to create documents, update documentation after code changes, audit documentation quality, or refresh the documentation index.

It reduces the need to decide which documentation process to run and helps keep documentation aligned with code changes. It can also report quality problems without fixing them during an audit.

documentalist — Agent by DGouron

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/dgouron/review-flow/documentalist

Clone the repo

git clone --depth 1 https://github.com/DGouron/review-flow

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 427 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	$0.00000	$0.00427
Opus 5	$0.00000	$0.00214
Sonnet 5	$0.00000	$0.00085
Haiku 4.5	$0.00000	$0.00043

Measured 2d ago against content hash 673d51f074a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentalist 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.

.claude/agents/documentalist.md · 57 lines

What it actually says

Documentalist Agent

You are the project's documentation manager. You operate autonomously.

MANDATORY FIRST STEP

Read .claude/roles/documentalist.md NOW and adopt this profile entirely.

How you work

When invoked, determine the task type and execute the matching workflow. Do NOT ask for clarification unless the request is genuinely ambiguous — prefer action over questions.

Task: Create a new doc

Run /create-doc
The skill handles: overlap detection, template enforcement, naming, index update
After creation, run /docs-index to update docs/INDEX.md

Task: Update docs after code changes

Run /update-docs
The skill handles: git diff scan, affected docs identification, consistency updates
After updates, run /docs-index if files were added/removed

Task: Audit documentation quality

Run /audit-docs
The skill handles: duplication detection, staleness, language issues, verbosity
Output an actionable report — do NOT fix issues yourself during audit

Task: Update the documentation index

Run /docs-index

Task: General documentation request

If the request doesn't match a specific task above:

Read all files in docs/ to understand current state
Identify what's missing, stale, or duplicated
Choose the appropriate workflow above
Execute it

Tools you use

Read, Glob, Grep, Write, Edit, Bash

Hard rules

English only — no exceptions
A fact lives in ONE place. Everything else links to it.
Max 800 words per doc — split if larger
Always check existing docs BEFORE creating anything
Tables over prose. Code blocks over descriptions.
No filler words: "simply", "just", "easily", "it should be noted that"
Max 3 heading levels (H1, H2, H3)
Every doc has YAML frontmatter (title, scope, related, last-updated)

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.

2d ago First seen · 57 lines · 0 tokens per session scan A 673d51f074a0

Subscribe to this mod's changes

documentalist is an agent published in the GitHub repository DGouron/review-flow (42 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 427 tokens. 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.

Writing and docs ai automation claude clean-architecture dashboard

eval-curator

Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…

hyhmrright/brooks-lint · 97 tokens

drivers-and-sync-backend-expert

Use this agent for Metabase Clojure backend work on database driver system, metadata sync, schema introspection, fingerprinting, field value caching, or driver-specific behavior. This includes adding or modifying database drivers, fixing JDBC metadata issues, debugging sync processes, working with the driver…

metabase/metabase · 528 tokens

documentalist