Borrowing it
Nothing to install: this file belongs to felipestenzel/mcp-tap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/felipestenzel/mcp-tap/main/CLAUDE.mdgit clone --depth 1 https://github.com/felipestenzel/mcp-tapWrote 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/felipestenzel/mcp-tap/claude-md)<a href="https://agentmods.dev/instructions/felipestenzel/mcp-tap/claude-md"><img src="https://agentmods.dev/badge/instructions/felipestenzel/mcp-tap/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 5.1 | $0.02083 | $0.02083 |
| Opus 5 | $0.01042 | $0.01042 |
| Sonnet 5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
mcp-tap CLAUDE.md scanned grade A with 1 finding 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 7d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
│ └── subprocess.py # Safe async subprocess wrapper How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-tap — Project Rules
The last MCP server you install by hand. Python 3.11+ | FastMCP | Hexagonal Architecture | MIT License
MANDATORY RULES FOR ALL CODE AGENTS
These rules apply to ANY code agent working on this project. No exceptions.
Before Implementing (Pre-flight)
- Check existing issues: Read both
docs/issues/(active) anddocs/issues/resolved/(closed) to verify if the problem was already documented - Check MEMORY.md: Read
~/.claude/projects/.../memory/MEMORY.mdfor context and lessons learned - Check agent memories: Read relevant
.claude/agent-memory/<agent>/MEMORY.mdfor specialized context - Create issue: Create the GitHub issue first to get an ID, then document it in
docs/issues/YYYY-MM-DD_<issue-id>_slug.mdusingdocs/issues/_TEMPLATE.mdBEFORE starting implementation - Create feature branch: ALWAYS create a branch before starting any work. NEVER commit directly to
main.- Feature:
feature/YYYY-MM-DD-description - Fix:
fix/YYYY-MM-DD-description - Refactor:
refactor/YYYY-MM-DD-description - Register the branch name in the issue doc (Branch field)
- Feature:
- Run baseline tests:
pytest tests/to know the current state before touching code - Use Context7: ALWAYS use MCP Context7 (
resolve-library-id+query-docs) to validate best practices and latest versions of libraries before implementing
During Implementation
- Follow hexagonal architecture strictly:
models.py— Frozen dataclasses, StrEnums (domain layer, ZERO dependencies)errors.py— Exception hierarchy (domain layer, ZERO dependencies)registry/,config/,installer/,connection/— Adapters (infrastructure layer)tools/— Use cases / entry points (application layer)server.py— Composition root (wiring only, no business logic)- Protocols in
base.pyfiles define ports — implementations are adapters - Direction of dependency: tools → models/errors ← adapters. Adapters NEVER import tools.
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.
- 7d ago First seen · 183 lines · 2,083 tokens per session scan A a3ce5f0c3284
mcp-tap CLAUDE.md is an instructions file published in the GitHub repository felipestenzel/mcp-tap (0 stars, last pushed 6mo ago), licensed MIT. It adds 2,083 tokens to every session, about $0.0104 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.
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).
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.
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).
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.