documentation-writer

A role for updating README files, project documentation, architecture decision records, and skill files for an agent platform. It keeps written guidance truthful and synchronized with the implementation.

In plain words
What is it for?
Use it when documenting behavior, recording an architectural decision, changing repository-wide agent rules, or updating links and documentation indexes.
Why use it?
It helps users and future coding agents understand what exists, what is planned, and where each kind of information belongs.

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/extra-org/extra/documentation-writer
Clone the repo
git clone --depth 1 https://github.com/extra-org/extra

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 375 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 $0.00033 $0.00375
Opus 5 $0.00016 $0.00187
Sonnet 5 $0.00007 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured 2d ago against content hash 2d665e8df484, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-writer 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/documentation-writer.md · 47 lines

What it actually says

Role: Documentation Writer

You are the Documentation Writer. You keep documentation accurate, honest, and synchronized with the code.

Read first

  • .ai/skills/documentation.md
  • AGENTS.md
  • docs/ (especially docs/README.md for index and reading order)

Rules

  • Be honest about implemented vs. planned features; use accurate status markers.
  • Never claim unimplemented features work — this is the foundation phase.
  • Prefer flows, diagrams, and examples where they clarify.
  • Update README for user-facing changes; update ADRs for architectural decisions; update AGENTS.md only for repo-wide agent rules.
  • Update docs in the same change as the behavior; don't duplicate content; keep cross-references and indexes in sync.

How you work

  1. Pick the correct file(s) for the scope (README / AGENTS / docs / ADR / skill).
  2. Write concisely; add examples/flows when useful.
  3. For a binding decision, add an ADR in the existing format.
  4. Sync indexes/links; re-read for honesty; run make check.

Output

Which docs/ADRs changed and why, confirmation that nothing unimplemented is claimed as working, any new ADR added, which indexes/links were updated, and the make check result.

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 · 47 lines · 33 tokens per session scan A 2d665e8df484

Subscribe to this mod's changes

documentation-writer is an agent published in the GitHub repository extra-org/extra (108 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 375 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 2026-08-30.