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/upgrade-projectnpx skills add SongshGeo/Python-Project-Template --skill upgrade-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 | $0.00083 | $0.00720 |
| Opus 5 | $0.00042 | $0.00360 |
| Sonnet 5 | $0.00017 | $0.00144 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
upgrade-project 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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
upgrade-project
Bring an existing repository (one already created from an older version of this template) up to the current Claude Code workflow. This skill is idempotent: every step checks current state first and skips what already exists, so it is safe to run more than once.
1. Detect current state
Report what you find before changing anything:
- Does
.cursor/cache/exist (old memory-bank location)? - Does
memory-bank/already exist? - Do
CLAUDE.mdand.claude/skills/exist? - Is
pyproject.tomlstill using the placeholder namesongshgeo? - Is the build still on poetry (
[tool.poetry]present /poetry-corebackend)?
2. Migrate the memory bank
- If
.cursor/cache/*.mdexist andmemory-bank/does not:git mvthe four docs (architecture,model-design,tech-stack,progress) intomemory-bank/, andgit mv .cursor/plans/.keep memory-bank/plans/.keep. - If both locations have content: merge without overwriting — bring any
unique content from
.cursor/cache/intomemory-bank/, then remove the stale copies. Never clobber existing memory-bank content. - Update
.cursor/rules/cursorrules.mdcso it points atmemory-bank/and notesCLAUDE.mdas the authoritative rules source.
3. Add missing scaffolding
For each of these, create it only if absent (otherwise show a diff/summary and let the user decide):
CLAUDE.md.claude/skills/{setup-project,upgrade-project,update-memory-bank,quality-check,commit}/SKILL.md.claude/settings.json.claude/recommended-skills.md
4. Optional: modernize tooling
If the repo is still on poetry, offer (do not force) to migrate to uv-only:
drop [tool.poetry], switch [build-system] to hatchling, and make the Makefile
uv-only. Confirm before editing build config on an established project.
5. Optional: install external skills
npx skills@latest add SongshGeo/skills
Point the user at .claude/recommended-skills.md for the recommended set.
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.
- 2d ago First seen · 67 lines · 83 tokens per session scan A 7da5953d28ae
upgrade-project is a skill published in the GitHub repository SongshGeo/Python-Project-Template (8 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 720 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.