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/edison-watch/custom-mcps/claude-mdgit clone --depth 1 https://github.com/Edison-Watch/Custom-MCPsWrote 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/edison-watch/custom-mcps/claude-md)<a href="https://agentmods.dev/instructions/edison-watch/custom-mcps/claude-md"><img src="https://agentmods.dev/badge/instructions/edison-watch/custom-mcps/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 | $0.03076 | $0.03076 |
| Opus 5 | $0.01538 | $0.01538 |
| Sonnet 5 | $0.00615 | $0.00615 |
| Haiku 4.5 | $0.00308 | $0.00308 |
Grade A, and why
Custom-MCPs 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 3d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Super-opinionated Python template that ships one codebase, three interfaces (CLI, MCP server, HTTP API) over a shared service registry. Python >= 3.12 required. Uses uv for dependency management (not pip).
Before any other work in this repo, enable prek: uv tool install prek && prek install. Hooks are defined in prek.toml.
MCP terminology: For nuances around frequently-confused MCP terms (Host vs. Client vs. Server, Tools vs. Resources vs. Prompts, Roots vs. Resources, transports, OAuth pitfalls, etc.), see mcp_server/COMMON_TERMS.md. Consult it before naming or designing new MCP-related code.
MCP Apps: an MCP extension for interactive iframe-sandboxed UIs (HTML resources via ui:// URIs) embedded in chat clients, with bidirectional postMessage / JSON-RPC communication. See ext-apps. Not a generic word for "MCP application".
MCP is an actively-evolving spec. Behaviors change frequently (transports, auth, primitives). Don't rely on training-data assumptions for anything MCP-related - always verify against the current spec via a fresh web search before writing or reviewing MCP code.
Common Commands
# Setup
make all # Sync dependencies
# Testing
make test # Run pytest on tests/
make test_fast # Run fast tests (no slow/nondeterministic)
make test_flaky # Repeat fast tests to detect flakiness
make test_slow # Run slow tests only
make test_nondeterministic # Run nondeterministic tests only
make mcp_conformance # MCPJam apps + protocol conformance vs local /mcp (needs node; CI-gated separately)
# Code Quality (run after major changes)
make fmt # Run ruff formatter + JSON formatting
make ruff # Run ruff linter
make vulture # Find dead code
make ty # Run type checker
make lint_links # Check for broken links in markdown files (README, etc.)
make ci # Run all CI checks (ruff, vulture, ty, import_lint, docs_lint, check_deps, lint_links, file_len_check, blind_except_check)
# Dependencies
uv sync # Install dependencies (not pip install)
uv add <pkg> # Add new dependency
uv run python <file> # Run Python files
uv run pytest path/to/test.py # Run specific test
# Release
# 1. Update version in pyproject.toml
# 2. Tag the commit: git tag -a v0.1.0 -m "Release v0.1.0"
# 3. Push the tag: git push origin v0.1.0 (triggers Release workflow)
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.
- 3d ago First seen · 244 lines · 3,076 tokens per session scan A 972e62b0e8c8
Custom-MCPs CLAUDE.md is an instructions file published in the GitHub repository Edison-Watch/Custom-MCPs (0 stars, last pushed today), licensed MIT. It adds 3,076 tokens to every session, about $0.0154 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.
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.
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).
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.