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/velkyvenik/missingmcp/claude-mdgit clone --depth 1 https://github.com/VelkyVenik/missingmcpWrote 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/velkyvenik/missingmcp/claude-md)<a href="https://agentmods.dev/instructions/velkyvenik/missingmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/velkyvenik/missingmcp/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 | $0.04451 | $0.04451 |
| Opus 5 | $0.02226 | $0.02226 |
| Sonnet 5 | $0.00890 | $0.00890 |
| Haiku 4.5 | $0.00445 | $0.00445 |
Grade A, and why
missingmcp 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 today.
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 — 121 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.
What this is
A multi-user, OAuth 2.1–protected remote MCP gateway that lets a small trusted circle each connect their own upstream-service accounts to Claude (mobile/desktop/web). The gateway terminates OAuth, performs the adapter-specific login — a credential form (garmin) or a redirect to the upstream's own OAuth (whoop: /whoop/oauth/callback) — stores per-account encrypted blobs, and forwards /<adapter>/mcp via one of three strategies: worker (garmin — spawns + reverse-proxies to a per-user subprocess of the unmodified garmin_mcp worker, github.com/Taxuspt/garmin_mcp), remote (no subprocess; forwards to a hosted upstream MCP, injecting the account's credentials as headers), or local (whoop — no subprocess, no shared upstream; the MCP server runs in-process, see adapters/whoop/mcp.py). No in-tree adapter uses the remote strategy today — rohlik used it until Rohlík shipped its own OAuth MCP (2026-07); the strategy stays covered by tests/test_remote_forward.py via a stub adapter.
The canonical design and the task-by-task implementation plan live in docs/superpowers/specs/ and docs/superpowers/plans/ — read them for rationale and the full data flow, but treat them as dated design records: the 2026-07-05 multi-adapter spec still describes a rohlik adapter that was implemented and then retired (2026-07-06, Rohlík ships its own OAuth MCP) — don't re-add it. Operator-facing docs (env-var reference, monitoring, deploy checklist) live in README.md; operational scripts (status, revoke, usage) live in scripts/ and are documented in README → Monitoring.
Commands
# Tests — the `--extra dev` is REQUIRED: pytest lives in [project.optional-dependencies].dev,
# so plain `uv run pytest` fails with "no module named pytest".
uv run --extra dev pytest -q # full suite
uv run --extra dev pytest tests/test_oauth.py -v # one file
uv run --extra dev pytest tests/test_oauth.py::test_metadata_shape -v # one test
# Run the gateway locally (no Garmin needed to exercise the OAuth surface).
# DATA_DIR defaults to /data (not writable locally) — point it somewhere writable.
# GATEWAY_SECRET must be >=32 chars AND must not start with "change-me" (startup guard).
# To exercise the full /<adapter>/mcp path locally, also set GARMIN_MCP_CMD (garmin-mcp isn't on
# PATH): GARMIN_MCP_CMD="uvx --python 3.12 --from git+https://github.com/Taxuspt/garmin_mcp garmin-mcp"
GATEWAY_SECRET="$(openssl rand -base64 48)" PUBLIC_URL=http://localhost:8088 PORT=8088 \
DATA_DIR=./.localdata uv run missingmcp
# After changing adapters/whoop/mcp.py's TOOLS table, regenerate the landing
# page's tool listing:
python scripts/gen_whoop_tools.py
# After changing the link-preview card's copy or palette, redraw static/og.png
# (Pillow is not a project dependency, hence --with). The `?v=` cache-buster in
# pages.py is derived from the file's hash, so a redraw invalidates scraper caches
# by itself:
uv run --with pillow python scripts/gen_og_image.py
# Production (missingmcp.com) runs on Railway, built from the Dockerfile, and
# auto-deploys on every push to main — pushing = deploying. Verify after push:
# railway deployment list --json. (Self-host: plain `docker run` — see README.)
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.
- today Changed · +1 lines · +219 tokens per session bdb231432d84
- 5d ago First seen · 120 lines · 4,232 tokens per session scan A 22494bbf4df5
missingmcp CLAUDE.md is an instructions file published in the GitHub repository VelkyVenik/missingmcp (4 stars, last pushed yesterday), licensed MIT. It adds 4,451 tokens to every session, about $0.0223 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
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).
spec-kit AGENTS.md
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.
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.
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).
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.
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.