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 skills/songshgeo/python-project-template/setup-projectnpx skills add SongshGeo/Python-Project-Template --skill setup-projectgit clone --depth 1 https://github.com/SongshGeo/Python-Project-TemplateWhat 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 | $0.00069 | $0.00690 |
| Opus 5 | $0.00034 | $0.00345 |
| Sonnet 5 | $0.00014 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade E, and why
setup-project scanned grade E with 3 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 yesterday.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
point the user at `curl -LsSf https://astral.sh/uv/install.sh | sh`. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .git && git init && git add -A && git commit -m "chore: initial commit from template" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
point the user at `curl -LsSf https://astral.sh/uv/install.sh | sh`. How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
setup-project
Guided, one-stop initialization for a new project created from this template. Run the steps in order, confirming with the user where noted. If a step's tool is missing, stop and tell the user how to install it rather than guessing.
1. Gather metadata
Ask the user (conversationally) for:
- Project name — used as the package/distribution name.
- Project description — one short sentence.
Do not proceed until both are non-empty.
2. Configure project files (non-interactive)
Run the config script with the collected values:
uv run python scripts/configure_project.py --name "<name>" --description "<description>"
This updates [project] in pyproject.toml, fills the ${project_name}
placeholder in .github/workflows/release-please.yml, rewrites README.md, and
clears CHANGELOG.md.
3. Install dependencies
uv sync --all-extras
(or make setup for the guided make path). uv is required — if it is missing,
point the user at curl -LsSf https://astral.sh/uv/install.sh | sh.
4. Set up pre-commit
uv run pre-commit install
uv run pre-commit run --all-files
Report any hook failures; offer to fix them.
5. Offer to reset git history
Ask whether the user wants a clean history for their new project. Only if they say yes:
rm -rf .git && git init && git add -A && git commit -m "chore: initial commit from template"
Never reset history without explicit confirmation.
6. Install the recommended external skills
npx skills@latest add SongshGeo/skills
The CLI is interactive: tell the user to select the recommended set documented in
.claude/recommended-skills.md (grill-me, grilling, to-prd, to-issues, tdd,
diagnosing-bugs, prototype, domain-modeling, codebase-design,
improve-codebase-architecture, code-review, handoff) and to enable them for
Claude Code. This is optional — the user can skip it.
7. Initialize the memory bank
Using the project's stated vision, draft initial content for:
memory-bank/architecture.md— intended module layout and boundaries.memory-bank/model-design.md— the core entities/data shapes, if known.
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.
- yesterday First seen · 90 lines · 69 tokens per session scan E 175675275387
setup-project is a skill published in the GitHub repository SongshGeo/Python-Project-Template (8 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 690 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…