Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/cyanheads/git-mcp-server/claude-mdgit clone --depth 1 https://github.com/cyanheads/git-mcp-serverWrote 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/cyanheads/git-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/cyanheads/git-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/git-mcp-server/claude-md.svg" alt="Measured on agentmods" 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 | $0.05712 | $0.05712 |
| Opus 5 | $0.02856 | $0.02856 |
| Sonnet 5 | $0.01142 | $0.01142 |
| Haiku 4.5 | $0.00571 | $0.00571 |
Grade A, and why
git-mcp-server 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 4d 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 — 550 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Protocol & Architectural Mandate
Version: 2.15.3 Target Project: git-mcp-server Last Updated: 2026-08-24
This document defines the operational rules for contributing to this codebase. Follow it exactly.
Note on File Synchronization:
AGENTS.mdis a symlink toCLAUDE.md. Edit onlyCLAUDE.md—AGENTS.mdwill reflect changes automatically.
I. Core Principles (Non-Negotiable)
-
The Logic Throws, The Handler Catches
- Tools: Implement pure, stateless business logic inside tool logic functions. No
try/catchblocks. - Resources: Same rule — pure read logic, no
try/catch. - On Failure: Throw
new McpError(...)with the appropriateJsonRpcErrorCodeand context. - Framework's Job:
createMcpToolHandlerwraps tool logic: createsRequestContext, measures execution viameasureToolExecution, formats the response, catches errors.createToolHandlerwraps git-specific logic: resolves DI dependencies and working directory before calling your pure logic.- Resource handlers (
resourceHandlerFactory) validate params, invoke logic, applyresponseFormatter, and catch errors.
- Tools: Implement pure, stateless business logic inside tool logic functions. No
-
Full-Stack Observability
- OpenTelemetry is preconfigured. Logs and errors are automatically correlated to traces.
measureToolExecutionautomatically records duration, success, payload sizes, and error codes for every tool call.- Do not add custom spans in tool/resource logic. The framework handles instrumentation.
-
Structured, Traceable Operations
- Tool logic receives dependencies via
ToolLogicDependencies(which includesappContextandsdkContext). appContext(RequestContext): Internal logging/tracing context withrequestId,sessionId,tenantId,traceId.sdkContext(SdkContext): MCP SDK protocol capabilities —signal,sendNotification,sendRequest,authInfo.- Pass
appContextthrough your internal call stack. Use the globalloggerwithappContextin every log call.
- Tool logic receives dependencies via
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.
- 4d ago First seen · 550 lines · 5,712 tokens per session scan A 38c9bc2e4444
git-mcp-server CLAUDE.md is an instructions file published in the GitHub repository cyanheads/git-mcp-server (239 stars, last pushed 10d ago), licensed Apache-2.0. It adds 5,712 tokens to every session, about $0.0286 per session on Opus 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.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.