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/musictechlab/mcp-codemagic/claude-mdgit clone --depth 1 https://github.com/musictechlab/mcp-codemagicWrote 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/musictechlab/mcp-codemagic/claude-md)<a href="https://agentmods.dev/instructions/musictechlab/mcp-codemagic/claude-md"><img src="https://agentmods.dev/badge/instructions/musictechlab/mcp-codemagic/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 | $0.00509 | $0.00509 |
| Opus 5 | $0.00254 | $0.00254 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
mcp-codemagic 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.
What it actually says
mcp-codemagic
MCP server for the Codemagic CI/CD REST API.
Tech Stack
- Language: Python 3.10+
- Package manager: Poetry
- HTTP client: httpx
- MCP framework: FastMCP (mcp[cli])
- Config: python-dotenv (reads
CODEMAGIC_API_KEYfrom.env) - Linter: Ruff
- Test framework: pytest
Commands
| Action | Command |
|---|---|
| Install | poetry install |
| Run server | poetry run python -m mcp_codemagic |
| Test | poetry run pytest |
| Lint | poetry run ruff check . |
| Format | poetry run ruff format . |
Architecture
src/mcp_codemagic/server.py— FastMCP tool definitions (one tool per Codemagic action). The_safedecorator turnsCodemagicErrorinto JSON instead of raising.src/mcp_codemagic/codemagic.py— Thin httpx client for the Codemagic REST API. Auth via thex-auth-tokenheader, token fromCODEMAGIC_API_KEY.src/mcp_codemagic/__main__.py— Entry point (python -m mcp_codemagic/mcp-codemagic).
Codemagic API notes
- Base URL:
https://api.codemagic.io(override withCODEMAGIC_BASE_URL). - Auth header:
x-auth-token: <token>(NOT Bearer). GET /apps→ applications + their workflow ids.POST /buildswith{appId, workflowId, branch|tag}→{buildId}.GET /builds/{id}→ build status (queued,building,finishing,publishing,finished,canceled,timeout).POST /builds/{id}/cancel→ cancel.
Conventions
- Never catch broad exceptions — catch
CodemagicError/ specifichttpx.HTTPError. - Run
ruff check .andruff format --check .before every push. - Secrets only via env /
.env(gitignored). Never hardcode the token.
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 · 45 lines · 509 tokens per session scan A 44c5de4e971f
mcp-codemagic CLAUDE.md is an instructions file published in the GitHub repository musictechlab/mcp-codemagic (0 stars, last pushed 2mo ago), licensed MIT. It adds 509 tokens to every session, about $0.0025 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
MobiAI-Core CLAUDE.md
Claude Code instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.
ConsultMe CLAUDE.md
Claude Code instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
dev-challenge CLAUDE.md
Claude Code instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.
android-media-pack CLAUDE.md
Instructions for sunnat629/android-media-pack, covering claude.md, what this repository is, commands, markdown lint (config in .markdownlint-cli2.jsonc) and shell script lint.