What is docs-assistant-mcp CLAUDE.md?

A set of Claude Code instructions for an MCP server that creates codebase documentation from real project files and Git history. MCP is a standard way for an AI assistant to use external tools.

Use it when developing or extending this documentation server, or when generating README files, architecture notes, environment-variable documentation, and changelogs from a codebase.

It helps prevent invented documentation by grounding descriptions in the repository’s actual files. It also records project-specific commands and security rules for working on the server.

How HARDIK-31/docs-assistant-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to HARDIK-31/docs-assistant-mcp. 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/HARDIK-31/docs-assistant-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/HARDIK-31/docs-assistant-mcp

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/hardik-31/docs-assistant-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/hardik-31/docs-assistant-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hardik-31/docs-assistant-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hardik-31/docs-assistant-mcp/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/hardik-31/docs-assistant-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hardik-31/docs-assistant-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,894 This file is loaded in full into every session.

When invoked 1,894 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	$0.01894	$0.01894
Opus 5.5	$0.00758	$0.00758
Sonnet 5.5	$0.00379	$0.00379
Haiku 4.5	$0.00189	$0.00189

Measured 2mo ago against content hash 88f04420c68b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs-assistant-mcp 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 · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

An MCP server (stdio transport) that generates grounded documentation for any codebase — README, architecture docs, env var docs, changelogs — by scanning real project artifacts (source tree, git history, package manifests, .env.example-style files) rather than letting an LLM invent content. This project was originally developed alongside two sibling MCP servers (db-assistant-mcp, timesheet-assistant-mcp) that share the same architectural conventions (Clean Architecture layering, no DI framework, an AppError taxonomy, a "never fabricate" grounding rule) — see docs/adr/ in this repo for the rationale; this file covers what's specific to docs-assistant-mcp on its own.

Status: Milestone 1 (5 tools) plus generate_architecture from Milestone 2 are implemented — 6 of 18 planned tools. The other 12 (generate_database_docs, generate_api_docs, diagram generators, deployment/security/testing docs, PRD/TRD, synchronize_docs) are specified in docs/Tool-Reference.md but not yet built. Don't assume a tool exists because it's documented there — check src/tools/index.ts's registerAllTools() for what's actually registered.

Commands

pnpm install
pnpm dev                  # run from TS source with hot reload (tsx watch)
pnpm build                # tsup -> dist/index.js (ESM, shebang, sourcemap, .d.ts)
pnpm typecheck             # tsc --noEmit
pnpm lint                  # eslint .   (pnpm lint:fix to auto-fix)
pnpm format                # prettier --write .
pnpm test                  # vitest run
pnpm test:coverage         # vitest run --coverage (thresholds: 95% lines/statements/functions, 90% branches)

npx vitest run tests/unit/analyzers/envVarAnalyzer.test.ts   # single file
npx vitest run -t "never reads a real .env"                   # single test by name

node examples/smoke-test-client.mjs (after pnpm build) spawns the built server over real MCP stdio with a fake ANTHROPIC_API_KEY and calls every registered tool — deterministic tools should fully succeed, LLM-touching ones should fail gracefully with AUTHENTICATION_ERROR. This is how src/server/** (excluded from coverage) actually gets verified.

Read the full file on GitHub · 117 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 · 117 lines · 1,894 tokens per session scan A 88f04420c68b

Subscribe to this mod's changes

docs-assistant-mcp CLAUDE.md is an instructions file published in the GitHub repository HARDIK-31/docs-assistant-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,894 tokens to every session, about $0.0076 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 2026-08-31.

Writing and docs

docs-assistant-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
docs-assistant-mcp CLAUDE.mdHARDIK-31/docs-assistant-mcp	Instructions file	0	2mo ago	Apache-2.0	A	1,894	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
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

docs-assistant-mcp: Instructions file for Claude Code