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/caidish/instrmcp/claude-mdgit clone --depth 1 https://github.com/caidish/instrMCPWrote 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/caidish/instrmcp/claude-md)<a href="https://agentmods.dev/instructions/caidish/instrmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/caidish/instrmcp/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 | $0.02640 | $0.02640 |
| Opus 5 | $0.01320 | $0.01320 |
| Sonnet 5 | $0.00528 | $0.00528 |
| Haiku 4.5 | $0.00264 | $0.00264 |
Grade A, and why
instrMCP 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 5d 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 — 226 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
Environment Setup:
# Always use conda environment instrMCPdev for testing
source ~/miniforge3/etc/profile.d/conda.sh && conda activate instrMCPdev
Package Management:
pip install -e . # Install for development
pip install -e .[dev] # With dev dependencies
python -m build # Build package
instrmcp version # Test installation
Code Quality (CI Requirements - see .github/workflows/lint.yml):
black --check instrmcp/ tests/ # Format check (must pass)
flake8 instrmcp/ tests/ --select=E9,F63,F7,F82 # Critical errors only (must pass)
flake8 instrmcp/ tests/ --max-line-length=127 # Style warnings (non-blocking)
mypy instrmcp/ --ignore-missing-imports # Type check (non-blocking)
Testing: (Only perform it when explicitly asked)
# Unit tests (fast, no hardware required - all mocked)
pytest tests/unit/ # All unit tests
pytest -v # Verbose
pytest --cov=instrmcp --cov-report=html # With coverage
pytest tests/unit/test_cache.py # Single file
pytest -k "test_cache_initialization" # Single test by name
pytest tests/unit/test_cache.py::TestReadCache::test_cache_initialization # Specific test
# E2E tests (requires Playwright and browser automation)
pytest tests/e2e/ -v # All E2E tests
pytest tests/e2e/test_01_server_lifecycle.py -v # Specific E2E test file
pytest tests/e2e/ -v -m p0 # Priority 0 (critical) tests only
# Playwright tests (metadata consistency checks)
pytest tests/playwright/ -v # Playwright-based tests
python tests/playwright/test_metadata_consistency.py --mode snapshot # Update metadata snapshot
Important notes:
- Some tests may stall indefinitely, set a reasonable timeout if needed
- E2E tests launch real JupyterLab servers and use browser automation
- CI excludes E2E and Playwright tests (they run separately or locally)
- Supported Python versions: 3.11, 3.12, 3.13
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.
- 5d ago First seen · 226 lines · 2,640 tokens per session scan A 5d8da06045fd
instrMCP CLAUDE.md is an instructions file published in the GitHub repository caidish/instrMCP (35 stars, last pushed 24d ago), licensed MIT. It adds 2,640 tokens to every session, about $0.0132 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 2026-08-30.
Other instructions, from other repositories
Math-To-Manim tests.instructions.md
Guidelines for writing and maintaining tests in Math-To-Manim.
is-kit AGENTS.md
AGENTS.md instructions for nyaomaru/is-kit, covering repository guidelines, project structure & modules, build, test, and development, coding style & naming and testing guidelines.
copilot-setting testing.instructions.md
Load when writing or reviewing a Test.java / IT.java file — JUnit 4 + Mockito + Spring Test 3.2. Triggers on: @RunWith(MockitoJUnitRunner / SpringJUnit4ClassRunner), org.junit.Test, @Before/@After, @Transactional auto-rollback. Not JUnit 5 (@BeforeEach/@ExtendWith) or @SpringBootTest. Defer non-test Java to…
node-typescript-boilerplate CLAUDE.md
Instructions for jsynowiec/node-typescript-boilerplate, a project described as: Production-ready Node.js TypeScript boilerplate: ESM, Vitest, ESLint, Prettier, GitHub Actions, Mise, and AGENTS.md included.
copilot-instructions unit-and-integration-tests.instructions.md
Unit and integration testing best practices with pytest.
web-explorer-mcp python-testing-rules.instructions.md
Instructions for l0kifs/web-explorer-mcp, covering rules for an ai agent testing a python project (pytest), basic principles, pytest practices (minimal yet sufficient), quality and coverage and isolation and external effects.