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/smorinlabs/py-launch-blueprint/agents-mdgit clone --depth 1 https://github.com/smorinlabs/py-launch-blueprintWrote 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/smorinlabs/py-launch-blueprint/agents-md)<a href="https://agentmods.dev/instructions/smorinlabs/py-launch-blueprint/agents-md"><img src="https://agentmods.dev/badge/instructions/smorinlabs/py-launch-blueprint/agents-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 | $0.03740 | $0.03740 |
| Opus 5 | $0.01870 | $0.01870 |
| Sonnet 5 | $0.00748 | $0.00748 |
| Haiku 4.5 | $0.00374 | $0.00374 |
Grade A, and why
py-launch-blueprint 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 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Canonical guidance for ALL coding agents (Claude Code, Cursor, Codex,
Windsurf, Aider, etc.) — this is the single file to edit.
CLAUDE.md imports it verbatim (@AGENTS.md); Cursor,
Windsurf, and Codex read this file natively. For human-contributor flow see
.github/CONTRIBUTING.md.
Required tools
- Python 3.12+ (per
requires-python = ">=3.12"; see ITM-033). - uv — Python dependency + venv management.
- bun — commitlint runtime (per ADR-04).
- lefthook — hook manager (per ADR-01).
- gitleaks — secret scanner (per ADR-02).
Setup is two levels, in order (both idempotent):
make bootstrap # Level 1 — base toolchain (just + uv); bare machines only
just setup # Level 2 — everything else (run every fresh clone/container/session)
just setup syncs the dev env (uv sync --group dev --extra web), wires
lefthook git hooks, and installs the hook toolchain (bun + bun install,
gitleaks, taplo, yamlfmt). It starts by running the Makefile's make check
gate and fails with a pointer to make bootstrap if the base toolchain is
missing — so running it "too early" is safe. The hook wiring is REQUIRED
before any commit/push work: without it none of the hooks below fire. Fresh
clones, containers, and remote agent sessions start without it — run
just setup as part of environment setup, every session. (The underlying
scripts/install-*.sh installers remain available individually.)
Canonical commands
| Task | Command |
|---|---|
| Sync dev env | uv sync --group dev --extra web (PEP 735 — not pip install '.[dev]') |
| All checks | just check |
| Run tests | pytest (default excludes slow/live markers per ITM-046; full: pytest -m ""; parallel: add -n auto) |
| Run one test | pytest tests/test_file.py::test_name |
| Lint | uv run ruff check . |
| Format | just format or uv run ruff format src/py_launch_blueprint/ |
| Format check | uv run ruff format --check . |
| Typecheck | uv run --extra web ty check src/py_launch_blueprint/ (ITM-026 / ADR-03; --extra web so web/ imports resolve) |
| Dependency CVE audit | just audit (WL-014; same pipeline as the weekly CI workflow) |
| Web tests / dev server | just test-web / just serve (FastAPI, web extra) |
| Secret scan | scripts/check-gitleaks.sh --staged or --range |
| Build | uv build (uv_build backend per ADR-06) |
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 · 280 lines · 3,740 tokens per session scan A bbe6c49dacf5
py-launch-blueprint AGENTS.md is an instructions file published in the GitHub repository smorinlabs/py-launch-blueprint (24 stars, last pushed 3d ago), licensed MIT. It adds 3,740 tokens to every session, about $0.0187 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
Blueprint AGENTS.md
AGENTS.md instructions for Magolor/Blueprint, covering blueprint agent guide, purpose and authority, work loop, typescript architecture and commands.
Blueprint CLAUDE.md
Claude Code instructions for Magolor/Blueprint, a project described as: uv-first Python starter template for new repositories with HeavenBase utilities, CI, and agent scaffolding.
Next-js-Boilerplate AGENTS.md
AGENTS.md instructions for ixartz/Next-js-Boilerplate, covering agents, principles, token efficiency, commands and git commits.
turbo-start-sanity CLAUDE.md
Claude Code instructions for robotostudio/turbo-start-sanity, covering claude.md, project overview, commands, development (both apps) and individual apps.
node-typescript-boilerplate AGENTS.md
Instructions for jsynowiec/node-typescript-boilerplate, covering agents.md, ground rules (always), typescript, node.js and testing (vitest).
seedkit CLAUDE.md
Instructions for viewflow/seedkit, covering seedkit, writing reference files, changelog, maintaining testcases and submodule workflow.