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/matdev83/patch-file-mcp-fork/agents-mdgit clone --depth 1 https://github.com/matdev83/patch-file-mcp-forkWhat 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 | $0.00664 | $0.00664 |
| Opus 5 | $0.00332 | $0.00332 |
| Sonnet 5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
patch-file-mcp-fork AGENTS.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 2d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/patch_file_mcp/: Python package and server entrypoint (server.py).tests/: Pytest suite with unit/integration coverage; markersunit,integration,slow.pyproject.toml: Packaging, pytest config, and console script (patch-file-mcp).mcp_config*.json: Example/config files for MCP clients.- Generated:
logs/(runtime logs),htmlcov/(coverage HTML),.coverage.
Build, Test, and Development Commands
- Install (editable + tests):
- Windows PowerShell
python -m venv .venv; .venv\Scripts\Activate.ps1pip install -e .[test]
- Windows PowerShell
- Run tests
- Quick:
pytest - With coverage HTML:
pytest --cov=src/patch_file_mcp --cov-report=html:htmlcov - Helper:
python run_tests.py
- Quick:
- Run server locally
- Example:
patch-file-mcp --allowed-dir C:\path\to\repo --log-file logs/app.log --log-level INFO - Alt (module):
python -m patch_file_mcp.server --allowed-dir .
- Example:
- Lint/format/type-check (run in project venv)
ruff check --fix .black .mypy src/patch_file_mcp
Coding Style & Naming Conventions
- Python ≥ 3.10, 4-space indentation, type hints required on new/changed code.
- Format with Black; lint with Ruff; keep lint clean before PRs.
- Naming: modules/files
snake_case.py, functions/varssnake_case, classesCapWords. - Tests: files
tests/test_*.py; fixtures intests/conftest.py.
Testing Guidelines
- Framework: Pytest; default options set in
pyproject.toml(verbose, strict markers). - Coverage: enforced minimum 25% (
--covonsrc/patch_file_mcp; HTML inhtmlcov/). - Selection:
pytest -m unit,pytest tests/test_venv_detection.py::TestClass::test_case. - Add tests for new behavior; update existing tests when interfaces change.
Commit & Pull Request Guidelines
- Commits: imperative, concise summary (≤72 chars) + rationale (what/why). Examples: "Add validation for patch block integrity", "Refactor search/replace parsing".
- PRs: clear description, link issues (
#123), list changes, test results, and any config/logging impacts. Include tests and doc updates.
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.
- 2d ago First seen · 49 lines · 664 tokens per session scan A 058b841feb6b
patch-file-mcp-fork AGENTS.md is an instructions file published in the GitHub repository matdev83/patch-file-mcp-fork (1 stars, last pushed 11mo ago), licensed MIT. It adds 664 tokens to every session, about $0.0033 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
claude-code-best-practice CLAUDE.md
Claude Code instructions for shanraisshan/claude-code-best-practice, covering claude.md, repository overview, key components, weather system (example workflow) and skill definition structure.
claude-code-tresor CLAUDE.md
Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.
Forge-Agentic-Coding-CLI AGENTS.md
Instructions for hoangsonww/Forge-Agentic-Coding-CLI, covering agents.md, 1. project identity, 2. commands you'll run, 3. layout and 4. rules.
Forge-Agentic-Coding-CLI CLAUDE.md
Instructions for hoangsonww/Forge-Agentic-Coding-CLI, covering claude.md, identity of this repo, build & verify commands (canonical), repository map and conventions.
codex-cli-best-practice AGENTS.md
Instructions for shanraisshan/codex-cli-best-practice, covering agents.md, what this is, architecture, orchestration flow and key directories.
claude-code-hooks CLAUDE.md
Instructions for shanraisshan/claude-code-hooks, covering claude code hooks, project structure, critical: hook count consistency, agent hooks and workflows.