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/keepgoing-dev/mcp-server/claude-mdgit clone --depth 1 https://github.com/keepgoing-dev/mcp-serverWhat 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 | $0.01067 | $0.01067 |
| Opus 5 | $0.00534 | $0.00534 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
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 yesterday.
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 — 87 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.
Documentation
When you add, remove, or change MCP tools or server behavior, update the docs page using a Haiku sub-agent:
Agent({
subagent_type: "haiku",
model: "haiku",
description: "Update MCP server docs page",
prompt: "Update apps/web/src/pages/docs/mcp-server.astro to reflect: [describe what changed]. Explain what each tool does and when AI tools call it. No em dashes."
})
Docs page: apps/web/src/pages/docs/mcp-server.astro
Build & Dev
From the monorepo root:
npm run mcp:build # Build with tsup
npm run mcp:watch # Watch mode
npm run mcp:test # Run tests
Locally (from this directory):
npx tsup # Build
npx tsup --watch # Watch
node --import tsx --test $(find src/test -name '*.test.ts' | tr '\n' ' ') # Run tests
tsc --noEmit # Type-check only
No linter is configured for this package.
Architecture
This package (@keepgoingdev/mcp-server) has two runtime roles driven by a single entry point (src/index.ts):
- MCP server (default): Connects via stdio to MCP hosts (Claude Code, Cursor, etc.). Exposes tools and prompts.
- Legacy CLI mode: When invoked with flags like
--save-checkpoint,--heartbeat, etc., runs a one-shot handler and exits. These flags are deprecated - the server now tries to delegate to thekeepgoingCLI binary and falls back to built-in handlers if unavailable.
Entry Point Dispatch
src/index.ts checks process.argv for known CLI flags first. If a flag matches, it checks whether the standalone keepgoing CLI is on PATH and delegates to it with a deprecation notice. If the CLI is unavailable, the legacy handler in src/cli/ runs directly. If no flag matches, the MCP server starts.
Tools (src/tools/)
Each file exports a register<Name>(server, reader, workspacePath?) function. All tools follow the same pattern: validate input with zod, read data via KeepGoingReader (or call shared utilities for git data), and return { content: [{ type: 'text', text }] }.
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.
- yesterday First seen · 87 lines · 1,067 tokens per session scan A 5aa59468e95b
mcp-server CLAUDE.md is an instructions file published in the GitHub repository keepgoing-dev/mcp-server (3 stars, last pushed 3mo ago), licensed MIT. It adds 1,067 tokens to every session, about $0.0053 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.