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/cdeistopened/skill-stack/wrapnpx skills add cdeistopened/skill-stack --skill wrapgit clone --depth 1 https://github.com/cdeistopened/skill-stackWhat 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 | $0.00093 | $0.01519 |
| Opus 5 | $0.00046 | $0.00759 |
| Sonnet 5 | $0.00019 | $0.00304 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
wrap 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 3d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wrap — Session Wrap
Close out a working session by writing what was decided, shipped, and learned into the right file, so the next session doesn't start cold.
An agent's output is cheap; its amnesia is expensive. Every session that ends without a wrap is a session your setup partly forgets — the workaround gets rediscovered next week, the decision gets relitigated next month. Memory discipline compounds; generation does not.
The Four Layers
Memory is layered. /wrap updates all four:
- WORKBENCH.md (volatile) — current state, blockers, recent decisions, next steps. One per project, at the project root. Create it if a project deserves one and doesn't have it.
- CLAUDE.md (evergreen) — who/what/why, where things live. Updated only when a decision changes a durable fact (tech stack, file location, people, rules).
- Skills (
.claude/skills/<skill>/) — capabilities the agent reuses across sessions. Bug fixes, new patterns, scope clarifications, and reusable scripts surfaced this session belong here. - Persistent memory (your agent's cross-session memory directory) — learnings that apply beyond one project AND don't fit cleanly inside any single skill. Keep an index file with one line per memory.
Don't write duplicates across layers. The routing decision tree:
- Did a fact change about a project (status, who, what's next)? → WORKBENCH.
- Did an evergreen project fact change (file moved, role changed, rule emerged)? → CLAUDE.md.
- Did a specific skill misfire, get extended, or develop a new known-good pattern? → That skill's SKILL.md.
- Is the learning cross-skill / cross-project / about an external service or SDK? → Persistent memory.
Write policy — two tiers
Don't ask y/n for every file touch. Sort each write by blast radius:
AUTO-WRITE (apply immediately, report in the recap):
- WORKBENCH.md updates — volatile by design, dated, easily reverted.
- New persistent-memory entries + their one-line index entries.
- Additive skill patches that record a session-validated rule in the section it most affects.
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.
- 3d ago First seen · 94 lines · 93 tokens per session scan A 49014f914210
wrap is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,519 once invoked, about $0.0005 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 2026-08-30.
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…