What is doc-wiki CLAUDE.md?

A tool for generating and maintaining a searchable documentation wiki from project sources. It includes commands for setting up the wiki, importing material, and asking questions about it.

Use it to create a wiki for a code repository, import source material, connect and index documentation, and search it with questions.

It keeps project knowledge organized and makes information easier to find than scattered files and notes.

How narailabs/doc-wiki configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to narailabs/doc-wiki. 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/narailabs/doc-wiki/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/narailabs/doc-wiki

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/instructions/narailabs/doc-wiki/claude-md/github.svg)](https://agentmods.dev/instructions/narailabs/doc-wiki/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/narailabs/doc-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/narailabs/doc-wiki/claude-md/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/instructions/narailabs/doc-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/narailabs/doc-wiki/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,311 This file is loaded in full into every session.

When invoked 4,311 The same file — it is already loaded in full.

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	$0.04311	$0.04311
Opus 5.5	$0.01724	$0.01724
Sonnet 5.5	$0.00862	$0.00862
Haiku 4.5	$0.00431	$0.00431

Measured 2mo ago against content hash bb2930e68fb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doc-wiki CLAUDE.md 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 2mo 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.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

doc-wiki

Documentation wiki generator and maintainer. Runs entirely inside Claude Code as skills + agents + TypeScript helper scripts.

Documentation

The public-facing documentation lives under docs/. Start there for installation, usage, and architecture details.

Audience	Read
Brand new — installing	`README.md`, `docs/getting-started.md`
Operator — using the commands	`docs/commands.md`, `docs/configuration.md`, `docs/troubleshooting.md`
Contributor — modifying internals	`docs/internals/architecture.md`, `docs/internals/connectors-api.md`, `CONTRIBUTING.md`

This file (CLAUDE.md) is the project-memory layer that Claude Code loads automatically; the sections below are an architecture summary for the orchestrator. The full architecture doc with Mermaid diagrams is at docs/internals/architecture.md.

Quickstart

Three slash commands take a new repo from zero to a working wiki:

/doc-wiki:init         # scaffold + onboard + (optionally) chain /doc-wiki:atlas
/doc-wiki:ingest <src> # fetch a source, compile, link, diagram, index
/doc-wiki:query <q>    # search the wiki, optionally save the answer as a page

/doc-wiki:init Phase 3 (onboarding) walks the user through configuring narai-primitives's ~/.connectors/config.yaml from .connectors/config.example.yaml (in this repo). After that, every /doc-wiki:ingest <jira-url>, /doc-wiki:ingest <github-repo>, etc. routes through gather() to the right connector — no per-service setup needed.

Architecture

Main skill: skills/doc-wiki/SKILL.md — orchestrates all /doc-wiki:* commands
Slash-command wrappers: commands/*.md — 8 thin wrappers so /doc-wiki:init, /doc-wiki:atlas, /doc-wiki:ingest, /doc-wiki:query, /doc-wiki:lint, /doc-wiki:edit, /doc-wiki:unarchive, /doc-wiki:stats appear in Claude Code's slash-command autocomplete and route into the skill
Source-fetch dispatch: /doc-wiki:ingest step 7 calls gather() from narai-primitives, which plans and spawns the bundled connector CLIs in parallel. The wiki-side Mermaid augmentation runs on the raw envelopes via agents/lib/mermaid_augment.ts. There is one path: gather → applyMermaid. The legacy wiki-<svc>-agent subagents + their per-service wrappers were decommissioned — their CLI-resolution and Mermaid responsibilities are now wholly owned by the hub and mermaid_augment.ts.
No standalone CLI — all LLM calls go through Claude Code's session
Runtime: Node 20. All scripts are TypeScript; npm run build emits sibling .js files that are invoked with node.

Read the full file on GitHub · 217 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.

2mo ago First seen · 217 lines · 4,311 tokens per session scan A bb2930e68fb2

Subscribe to this mod's changes

doc-wiki CLAUDE.md is an instructions file published in the GitHub repository narailabs/doc-wiki (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,311 tokens to every session, about $0.0172 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 2026-08-30.

Writing and docs

doc-wiki CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
doc-wiki CLAUDE.mdnarailabs/doc-wiki	Instructions file	13	yesterday	Apache-2.0	A	4,311	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

doc-wiki: Instructions file for Claude Code