agentmods.dev

aha-mcp: Instructions file for Claude Code

CLAUDE.md

aha-mcp CLAUDE.md is an instructions file for Claude Code from cedricziel/aha-mcp. It costs 11,221 tokens per session, scanned A, original, MIT.

A set of development instructions for the aha-mcp repository, an MCP server that connects tools to Aha. It documents commands for installing, running, testing, building, and packaging the server.

In plain words
What is it for?
Use it when developing, testing, building, or packaging the aha-mcp server and its MCP bundle.
Why use it?
It prevents common development mistakes, including accidentally running tests against a real Aha account or changing the build in unsupported ways.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument; mentions Claude Code.

This is cedricziel/aha-mcp's own configuration. It tells Claude Code how to work on aha-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 aha-mcp configures →

not rated 6repo changed 1mo ago A scan 11,221 tokens original MIT
View source ↗ cedricziel/aha-mcp
Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cedricziel/aha-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cedricziel/aha-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11,221 This file is loaded in full into every session.
When invoked 11,221 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 $0.11221 $0.11221
Opus 5.5 $0.04488 $0.04488
Sonnet 5.5 $0.02244 $0.02244
Haiku 4.5 $0.01122 $0.01122

Measured 1mo ago against content hash 9fffa8565d8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aha-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 1mo 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 · 737 lines

How it starts

The opening of the file, as written. The whole thing — 737 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.

Development Commands

  • bun install - Install dependencies
  • bun start - Start the MCP server with stdio transport
  • bun run dev - Start server in development mode with auto-reload (stdio)
  • bun run start:http - Start the HTTP server
  • bun run dev:http - Start HTTP server in development mode with auto-reload
  • bun build - Build the stdio server for production
  • bun run build:http - Build the HTTP server for production
  • bun run test - Run the test suite. Prefer this over a bare bun test: it passes --env-file=/dev/null, because Bun auto-loads .env and a populated AHA_TOKEN makes the suite issue live API calls against a real Aha account.
  • bun run mcpb:validate - Validate manifest.json against the MCP bundle schema
  • bun run mcpb:pack - Build and pack the Claude Desktop extension to dist/aha-mcp.mcpb

Notes for changing the build

  • There are no native dependencies, and it should stay that way. The bundle produced by bun build runs on its own; nothing is resolved from node_modules at runtime. Adding a native module reintroduces the failure that made every packaged artifact crash on startup, because bindings resolves the compiled .node relative to build/index.js. Verify with node build/index.js --help after any build change.
  • Do not run the tests with a --preload setup file. Forcing MockAhaService in-process breaks the unit tests that patch the real AhaService; the e2e tests get the mock via AHA_TOKEN=test-token in the spawned server's environment instead.
  • src/core/uri-template.ts vendors the still-unmerged upstream fix from modelcontextprotocol/typescript-sdk#1083. Delete it once that lands, not before - without it, resource URIs carrying query parameters do not match.
  • manifest.json's tool list must match what the server actually registers. Regenerate it with bun run manifest:sync, which spawns the real server and copies tools/list verbatim, rather than editing by hand - bun run manifest:check fails without writing, for CI. Changing a tool's description in src/core/tools.ts and forgetting this leaves the desktop extension advertising the old behaviour. Keep prompts as prompts_generated: true - the schema requires a text field on any statically declared prompt, which the server generates at runtime instead.

Read the full file on GitHub · 737 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. 1mo ago Changed · +15 lines · +207 tokens per session 9fffa8565d8c
  2. 2mo ago First seen · 722 lines · 11,014 tokens per session scan A 772b1ed46b53

Subscribe to this mod's changes

aha-mcp CLAUDE.md is an instructions file published in the GitHub repository cedricziel/aha-mcp (6 stars, last pushed 2d ago), licensed MIT. It adds 11,221 tokens to every session, about $0.0449 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.

ahaaha-ideas
Related

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).

microsoft/vscode · 9,719 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,516 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 3,048 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,269 tokens