Borrowing it
Nothing to install: this file belongs to scopweb/mcp-go-github. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/scopweb/mcp-go-github/main/CLAUDE.mdgit clone --depth 1 https://github.com/scopweb/mcp-go-githubWrote 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.
[](https://agentmods.dev/instructions/scopweb/mcp-go-github/claude-md)<a href="https://agentmods.dev/instructions/scopweb/mcp-go-github/claude-md"><img src="https://agentmods.dev/badge/instructions/scopweb/mcp-go-github/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.
<a href="https://agentmods.dev/instructions/scopweb/mcp-go-github/claude-md"><img src="https://agentmods.dev/badge/instructions/scopweb/mcp-go-github/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01728 | $0.01728 |
| Opus 5.5 | $0.00691 | $0.00691 |
| Sonnet 5.5 | $0.00346 | $0.00346 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
mcp-go-github 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - MCP GitHub Server v4.0
Status: ✅ Production Ready | Tools: 26 (consolidated from 85) | Architecture: Hybrid (Local Git + GitHub API + Admin Controls)
Core Architecture
Go-based MCP server providing GitHub integration for Claude Desktop via JSON-RPC 2.0.
Key Files
cmd/github-mcp-server/main.go- Entry point with multi-profile supportinternal/server/server.go- MCP handler with 26 consolidated toolspkg/git/operations.go- Local Git operations (0 tokens)pkg/github/client.go- GitHub API client wrapper with 11 methodspkg/admin/admin.go- Administrative operations clientinternal/hybrid/operations.go- Smart Git-first operationspkg/dashboard/dashboard.go- GitHub dashboard operationspkg/safety/- Safety layer with risk classification and auditinternal/server/admin_tools.go- 4 consolidated admin tools (22 operations)internal/server/admin_handlers.go- Admin operation handlersinternal/server/safety_middleware.go- Safety execution wrapper
Design: Consolidated Operation Pattern
Tools use an operation parameter to expose multiple operations under one tool name.
This reduces the tool count from 85 to 26, preventing AI model confusion from tool reading limits.
Example: git_branch with operation: checkout|checkout_remote|list|merge|rebase|backup
Safety uses composite keys tool:operation (e.g., github_webhooks:delete) for risk classification.
Features
- Multi-profile: Single executable, multiple GitHub accounts via
--profileflag - Protocol auto-detection: Automatically detects and responds with client's MCP protocol version
- Hybrid ops: Local Git first (0 tokens) → GitHub API fallback
- 26 consolidated tools: All 85 operations accessible via operation parameter pattern
- 4-tier safety system: Risk-based classification with confirmation tokens
- Audit logging: JSON-based operation tracking with automatic rotation
- Dry-run mode: Preview destructive operations before execution
- Security: Path traversal prevention, command injection protection, SSRF prevention
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 · 158 lines · 1,728 tokens per session scan A 568bce84c3af
mcp-go-github CLAUDE.md is an instructions file published in the GitHub repository scopweb/mcp-go-github (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,728 tokens to every session, about $0.0069 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.