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/syncnpx skills add stranma/claude-code-python-template --skill syncgit 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 | $0.00027 | $0.00491 |
| Opus 5 | $0.00014 | $0.00246 |
| Sonnet 5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
sync 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.
What it actually says
Sync
Pre-flight workspace sync. Run this before starting any work.
Steps
-
Fetch remote refs
- Run
git fetch origin
- Run
-
Check workspace state
- Run
git statusto see dirty files, staged changes, untracked files - Run
git branch -vvto see current branch, tracking info, ahead/behind counts
- Run
-
Auto-reset to master if nothing is blocking
If ALL of the following are true, automatically run
git checkout master && git pull --rebasewithout asking:- Working tree is clean (no staged, unstaged, or untracked changes that matter)
- Current branch is NOT master (already on a feature branch that can be left)
- The feature branch has no unpushed commits (ahead 0, or branch was already merged)
If any blocker exists, do NOT auto-reset. Instead report the blocker and ask what to do:
- Dirty working tree: list the files and ask whether to stash, commit, or discard
- Unpushed commits on current branch: warn and ask whether to push first or switch anyway
- Already on master: just
git pull --rebaseto update
-
Show recent context
- Run
git log --oneline -3to show the last 3 commits (after any branch switch)
- Run
-
Output structured report
# Workspace Sync
Branch: <name> (tracking: <remote>/<branch>)
Status: <clean | N dirty files | N staged, M unstaged>
Remote: <up to date | N ahead, M behind>
## Actions Taken
- <e.g. "Switched to master and pulled 5 new commits", or "None -- already on clean master">
## Blockers (if any)
- <e.g. "Unstaged changes in .claude/settings.json -- stash, commit, or discard?">
## Recent Commits
- <hash> <message>
- <hash> <message>
- <hash> <message>
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 · 56 lines · 27 tokens per session scan A 086ad7263013
sync is a skill published in the GitHub repository stranma/claude-code-python-template (2 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 491 once invoked, about $0.0001 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.