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/dawiegriesel/mcp-dev/claude-mdgit clone --depth 1 https://github.com/dawiegriesel/mcp-devWrote 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/dawiegriesel/mcp-dev/claude-md)<a href="https://agentmods.dev/instructions/dawiegriesel/mcp-dev/claude-md"><img src="https://agentmods.dev/badge/instructions/dawiegriesel/mcp-dev/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 | $0.00835 | $0.00835 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
mcp-dev 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project overview
MCP server that scaffolds full-stack projects (FastAPI + React/HTMX) with Docker, CI/CD, and database config. Built with FastMCP + Jinja2. Installable as a Python package from GitHub. Public repo, alpha status, MIT licensed.
Commands
# Run the MCP server
uv run project-scaffold
# Install dependencies
uv sync # production
uv sync --extra dev # with pytest + ruff
# Lint and format
uv run ruff check src/
uv run ruff format src/
# Run tests
uv run pytest
Architecture
src/project_scaffold/server.py— FastMCP server, defines 5 MCP tools +main()entry pointsrc/project_scaffold/models.py— Pydantic models:ProjectConfig,ComponentConfigsrc/project_scaffold/config.py— Constants (template dir, type maps, defaults)src/project_scaffold/generator.py— Core engine:ProjectGeneratorclass renders Jinja2 templates to disksrc/project_scaffold/renderers/api.py— Component generators foradd_routerandadd_modelsrc/project_scaffold/templates/— Jinja2 templates organized by category (api, frontend, docker, cicd, alembic, common)
Key patterns
- All templates receive a context dict built by
ProjectGenerator._context()with keys:project_name,project_type,frontend_type,description,db_name,db_user,db_password,include_auth,include_alembic,api_port,frontend_port,is_multi_repo,python_package_name - React projects are multi-repo (separate
{name}-api/and{name}-frontend/dirs). HTMX projects are single-repo. .scaffold.jsonmetadata file is written to project root and used byfrom_existing()to reload config- Type maps in
config.pytranslate user-friendly types (str, int, float, bool, etc.) to SQLAlchemy and Pydantic types - Component generators in
renderers/api.pyproduce Python code as strings (not templates) - Templates live inside the package (
src/project_scaffold/templates/) so they're included in pip installs
Code style
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 · 68 lines · 835 tokens per session scan A 085cce35053e
mcp-dev CLAUDE.md is an instructions file published in the GitHub repository dawiegriesel/mcp-dev (0 stars, last pushed 6mo ago), licensed MIT. It adds 835 tokens to every session, about $0.0042 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
full-stack-ai-agent-template CLAUDE.md
Instructions for vstorm-co/full-stack-ai-agent-template, covering claude.md, project overview, commands, install dependencies and run tests.
better-notion-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-notion-mcp, covering agents.md - better-notion-mcp, build / lint / test commands, run a single test file, run a single test by name and mise shortcuts.
mcp-dockhand copilot-instructions.md
Copilot instructions for strausmann/mcp-dockhand, covering copilot instructions — mcp-dockhand, project context, critical: verify against upstream, code review guidelines and security.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
mcp-dockhand gemini-review.instructions.md
Instructions for strausmann/mcp-dockhand, covering gemini code assist review instructions, upstream verification (critical) and code quality checks.
deckforge CLAUDE.md
Instructions for Whatsonyourmind/deckforge, covering deckforge, tech stack, project structure, key commands and local development.