forgejo-mcp: Instructions file for Claude Code

CLAUDE.md

forgejo-mcp CLAUDE.md is an instructions file for Claude Code from Sqcows/forgejo-mcp. It costs 1,609 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that provides tools for Forgejo and Gitea code-hosting platforms.

In plain words
What is it for?
Building or testing the server, running it over local or HTTP connections, registering tool groups, validating configuration, and calling Forgejo or Gitea APIs.
Why use it?
They explain how the server is built, tested, configured, and organized, reducing the risk of changing the wrong layer.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Sqcows/forgejo-mcp's own configuration. It tells Claude Code how to work on forgejo-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything forgejo-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Sqcows/forgejo-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/Sqcows/forgejo-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Sqcows/forgejo-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.

agentmods badge for forgejo-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sqcows/forgejo-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/sqcows/forgejo-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sqcows/forgejo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sqcows/forgejo-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.

agentmods 80×15 button for forgejo-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sqcows/forgejo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sqcows/forgejo-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,609 This file is loaded in full into every session.
When invoked 1,609 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01609 $0.01609
Opus 5.5 $0.00644 $0.00644
Sonnet 5.5 $0.00322 $0.00322
Haiku 4.5 $0.00161 $0.00161

Measured 22d ago against content hash 96cb68e6f99e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

forgejo-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 22d 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 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.

Build & Test Commands

npm run build          # Compile TypeScript to dist/
npm run dev            # Run stdio server (tsx, no build needed)
npm run dev:http       # Run HTTP server on port 3000
npm test               # Run all tests
npm run test:watch     # Watch mode
npx vitest run src/__tests__/tools/repository.test.ts  # Run a single test file
npm run lint           # ESLint

Architecture

This is an MCP (Model Context Protocol) server for Forgejo/Gitea instances, providing 457 tools across 9 categories. It has two transport modes: stdio (for Claude Code/Desktop) and HTTP (for remote access).

Request Flow

Entry point (index.ts or http.ts)
  → config.ts (loads env vars / CLI args, validates URL for SSRF)
  → server.ts (creates McpServer, registers all tool groups)
  → tools/*.ts (each tool calls ForgejoClient methods)
  → client.ts (wraps fetch with token auth, hits /api/v1)

Key Modules

  • server.ts — Factory that creates McpServer and calls nine register*Tools() functions (one per file in tools/). In lazy mode (--lazy / FORGEJO_LAZY_TOOLS, off by default) it registers every tool disabled plus a load_tool_area tool that enables an area's tools and sends notifications/tools/list_changed; this only works in clients that refetch the tool list mid-session
  • client.ts — ForgejoClient class with get/post/patch/put/delete/getRaw methods. Errors are wrapped in ForgejoApiError with sanitized URLs (no token leakage). Refuses request paths containing ./.. segments or unencoded ?, #, or backslashes
  • compact.ts — Wraps the SDK's tools/list handler to strip validation-only schema keywords and boilerplate from the tool list sent to clients (saves context; Zod validation is unchanged). The compacted list is cached by a key that server.ts supplies per request, which must identify the tools currently enabled (in lazy mode this includes the loaded areas)
  • config.ts — resolveConfig() merges CLI args > env vars > defaults. Tool areas (TOOL_AREAS) can be disabled with --disable-<area> / --disable a,b or FORGEJO_DISABLED_AREAS; server.ts skips those groups. validateBaseUrl() blocks SSRF (cloud metadata IPs, private ranges)
  • validation.ts — Centralized Zod schemas (zOwner, zRepo, zFilePath, zPage, zLimit, etc.) shared across all tool files
  • tools/helpers.ts — formatResponse(data) and formatError(err) produce the MCP content format; encodePath(value) percent-encodes a slash-separated value for use in a request path
  • http.ts — HTTP transport: one McpServer + transport per client session (LRU-capped), RateLimiter class, optional Bearer auth (FORGEJO_MCP_API_KEY), Origin check when unauthenticated, security headers, /health endpoint

Read the full file on GitHub · 102 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.

  1. 22d ago Changed · +1 lines · +150 tokens per session 96cb68e6f99e
  2. 25d ago Changed · +9 lines · +434 tokens per session 77fc141442e6
  3. 2mo ago First seen · 92 lines · 1,025 tokens per session scan A b328b133c623

Subscribe to this mod's changes

forgejo-mcp CLAUDE.md is an instructions file published in the GitHub repository Sqcows/forgejo-mcp (15 stars, last pushed 22d ago), licensed MIT. It adds 1,609 tokens to every session, about $0.0064 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.

Related

forgejo-mcp CLAUDE.md compared with instructions from other repositories

forgejo-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
forgejo-mcp CLAUDE.mdSqcows/forgejo-mcpInstructions file1522d agoMITA1,609Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode