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/stranma/claude-code-python-template/donenpx skills add stranma/claude-code-python-template --skill donegit clone --depth 1 https://github.com/stranma/claude-code-python-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 | $0.00032 | $0.01186 |
| Opus 5 | $0.00016 | $0.00593 |
| Sonnet 5 | $0.00006 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
done 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 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.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Done
Universal completion command. Call this when work is finished to validate, ship, and document.
Phase 1: Detect Scope
Determine scope from workspace signals:
| Signal | Q (ship) | S (land) | P (deliver) |
|---|---|---|---|
| Branch | main/master | feature branch | feature branch |
| Files changed | <=3 | >3 | any |
| IMPLEMENTATION_PLAN.md | no unchecked phases | no unchecked phases | has unchecked phases |
| Diff size | <100 lines | >=100 lines | any |
Decision logic (first match wins):
- If
docs/IMPLEMENTATION_PLAN.mdhas unchecked phases -> P (deliver) - If on a feature branch -> S (land)
- If on main/master AND small scope (<=3 files, <100 lines changed) -> Q (ship)
- If on main/master AND large scope -> warn user, suggest creating a feature branch
Always report the detected scope and accept user override.
Phase 2: Validate
Absorbs the former /ship checklist. Three tiers of checks:
Blockers (must ALL pass -- stop if any fail)
-
No secrets in codebase
- Search for:
sk-,AKIA,ghp_,password=,secret=,-----BEGIN.*PRIVATE KEY - Zero matches in tracked files (exclude
.env.example)
- Search for:
-
No debug code
- Search for:
breakpoint(),pdb.set_trace()in non-test source files - These are hard blockers -- any match stops the process
- Search for:
-
Pre-commit hygiene
- Search for leftover
TODO,FIXME,HACKmarkers in changed files - List all found with file:line for review
- Search for leftover
High Priority (run via agents in parallel)
Launch two agents simultaneously:
| Agent | File | What it checks |
|---|---|---|
| Code Quality | .claude/agents/code-quality-validator.md |
Lint (ruff check), format (ruff format --check), type check (pyright) |
| Test Coverage | .claude/agents/test-coverage-validator.md |
All tests pass, coverage report |
All agents use subagent_type: "general-purpose".
Recommended
- Git history -- check for WIP/fixup commits that should be squashed
- Branch up to date -- check if behind base branch
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 · 127 lines · 32 tokens per session scan A 4fdfb2061df0
done is a skill published in the GitHub repository stranma/claude-code-python-template (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,186 once invoked, about $0.0002 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 skills, from other repositories
test-guide
Test-writing guide for Backend.AI — propose success/exception/edge scenarios first, refine them with the user, then implement while reporting per-scenario verification status. Covers fixtures, withtables, mock repositories, pants test, optional TDD cadence.
wu5-dev-flow
使用可审计的 SDD、严格 RED-GREEN-REFACTOR TDD 与安全 Git 门禁初始化、开发、修复、重构和交付 Python 项目。用于任何会修改项目源码、测试、规格、依赖或 Git 历史的任务，也用于继续跨 Session 的现有 spec/ 变更、审查代码、验证完成状态、创建提交或准备 GitHub PR。.
simulate-contracts
Compile the contract set in your head — simulate how the real application would run from the specs, and disprove (or confirm) it works before any source .py is written.
model-data-schema
Author the persistence schema as a binding contract from the captured external shapes and the interview — before any test stub is written.
author-test-stubs
Author test stub files (.pyi) whose signatures express the domain, relationships, and compositions, as the first contract surface.
derive-source-stubs
Derive the source stub files (.pyi) from the reviewed tests — every type the tests reference gets a definition.