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/emaballarin/ccplugins/spinupnpx skills add emaballarin/ccplugins --skill spinupgit clone --depth 1 https://github.com/emaballarin/ccpluginsWhat 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 | $0.00123 | $0.02880 |
| Opus 5 | $0.00062 | $0.01440 |
| Sonnet 5 | $0.00025 | $0.00576 |
| Haiku 4.5 | $0.00012 | $0.00288 |
Grade A, and why
spinup 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mf:spinup — project memory → session prime
Get up to speed on a project without starting any new work. Read persistent memory in priority order, summarise, then stop and wait for user direction.
Important
- Spinup is read-only. Never start work unprompted. Even if the memory says "the next thing to do is X", your job is to report that — not to start doing X.
- Read selectively. Budget 3–6 files for a typical spinup. Reading everything is expensive on context and rarely useful.
- Verify what you're about to cite. Memory is a point-in-time snapshot; file paths, commits, and symbols may be stale.
- Don't re-derive settled decisions. If a feedback memory says "closed as failed", don't re-propose it.
Instructions
Step 1: Open MEMORY.md directly
Auto-memory lives at ~/.claude/projects/<slug>/memory/ where <slug> is $PWD with every / replaced by - (deterministic — form the path inline, no shell call needed). On the happy path, go straight to Read ~/.claude/projects/<slug>/memory/MEMORY.md. If that read succeeds, you've simultaneously located the dir and loaded the index — skip the rest of this step.
Only fall back to diagnostics if the read fails:
- ENOENT on
MEMORY.mdbut the memory dir itself exists → treat as "primed but no memory yet" (step 2 behaviour). - ENOENT on the memory dir → the slug convention may differ on this host. Run
ls ~/.claude/projects/ | grep <project_name_fragment>to find the actual dir; if multiple matches exist, prefer the one with the most recentMEMORY.md.
Step 2: Verify the project is primed
Memory-dir existence under ~/.claude/projects/<slug>/memory/ is the authoritative "has this session been worked on before" signal. AGENTS.md and PROJECT.md in the project root are the secondary "is this project wired up for mindfunnel" signal.
Confirm AGENTS.md and PROJECT.md exist in the project root (real files under the 0.3.0 split model; for projects primed by older versions they may still be symlinks — either works for this check). If either is missing:
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 · 201 lines · 123 tokens per session scan A fc25e79aceff
spinup is a skill published in the GitHub repository emaballarin/ccplugins (3 stars, last pushed 26d ago), licensed MIT. It adds 123 tokens to every session and 2,880 once invoked, about $0.0006 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…