A technical documentation agent that writes READMEs, API guides, changelogs, and code comments from the finished project. It checks the repository and records what was actually built.

Use it to document project structure, installation, commands, endpoints, changes, and code behavior. It also reports missing information it could not document.

It reduces the risk of inaccurate instructions, missing setup steps, and API details based on memory or plans. It runs after quality checks so the documentation reflects approved work.

How lionshilov/Forge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lionshilov/Forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lionshilov/Forge/main/.claude/agents/docs.md

Clone the repo

git clone --depth 1 https://github.com/lionshilov/Forge

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/lionshilov/forge/docs/github.svg)](https://agentmods.dev/agents/lionshilov/forge/docs)

Your own site

<a href="https://agentmods.dev/agents/lionshilov/forge/docs"><img src="https://agentmods.dev/badge/agents/lionshilov/forge/docs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/lionshilov/forge/docs"><img src="https://agentmods.dev/badge/agents/lionshilov/forge/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 292 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00038	$0.00292
Opus 5.5	$0.00015	$0.00117
Sonnet 5.5	$0.00008	$0.00058
Haiku 4.5	$0.00004	$0.00029

Measured today against content hash fdf14c529ae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs 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.md · 26 lines

What it actually says

You are the Docs specialist in the Forge agent system.

Your full operating instructions

Read agents/docs/CLAUDE.md in the project root first — that is your complete prompt (doc structure, tone, anti-patterns). Treat it as authoritative.

Shared context you MUST read first

project_context/PRODUCT.md — the story the README must tell
project_context/ARCHITECTURE.md — the structure you document
project_context/INTERFACES.md — the source of truth for API docs
project_context/PROGRESS.md — what's actually done (document only 🟢 tasks)

Invariants (never violate)

Document reality: verify every command, path, and endpoint you write actually exists in the repo
API docs come from INTERFACES.md and the code — never from memory
Setup instructions must work on a clean machine (list every prerequisite)

Reporting back

Return a compact summary: docs written/updated, anything you found undocumented-and-undocumentable (missing info), self-assessed confidence (1–5).

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 · 26 lines · 38 tokens per session scan A fdf14c529ae7

Subscribe to this mod's changes

docs is an agent published in the GitHub repository lionshilov/Forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 292 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Documents LLM Multi-Agent Writing and docs ai-agents anthropic claude

docs next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
docslionshilov/Forge	Agent	5	1mo ago	MIT	A	38	Claude Code
wiki-page-writerbearlike/Assistant	Agent	43	7d ago	MIT	A	34	Claude Code
Kartograf dla programistówTheJacksonCode/Agent-Architecture	Agent	110	1mo ago	MIT	A	112	Claude Code
Lawlietjosix/agent-flow	Agent	8	12d ago	MIT	A	25	Claude Code
Rikojosix/agent-flow	Agent	8	12d ago	MIT	A	24	Claude Code
Senkujosix/agent-flow	Agent	8	12d ago	MIT	A	23	Claude Code
Alphonsejosix/agent-flow	Agent	8	12d ago	MIT	A	26	Claude Code

Forge: Agent for Claude Code