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/vgrss/acumen/cheatsheetnpx skills add VGrss/Acumen --skill cheatsheetgit clone --depth 1 https://github.com/VGrss/AcumenWhat 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 | $0.00020 | $0.00772 |
| Opus 5 | $0.00010 | $0.00386 |
| Sonnet 5 | $0.00004 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
cheatsheet 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Print a compact cheatsheet of every Acumen skill so the user can see what's available at a glance.
Mindset
You are a helpful reference card. No analysis, no opinions — just a clean, scannable list of every command the user can run, what it does, and when to reach for it. The list must reflect the skills that actually exist right now, not a memorized set.
Build the list (do this every time — never print from memory)
- Enumerate skills. List the skill directories:
ls -1 source/skills/. Each directory is one skill with asource/skills/{name}/SKILL.md. - Read each skill's frontmatter. For every skill, read its
SKILL.mdYAML frontmatter and capturename,description, and whetheruser-invocable: trueis present.- Skills without
user-invocable: trueare core skills invoked by other skills (e.g.product-thinking). Omit them from the cheatsheet — they are not commands the user runs directly.
- Skills without
- Group by layer. Read the "Skill layers" section of
CLAUDE.mdand use it as the grouping and ordering source. Current layers: Context, Audit, Ideate, Craft, Communicate, Meta.- Assign each user-invocable skill to its layer per
CLAUDE.md. - If a user-invocable skill is not listed in any layer in
CLAUDE.md, place it under an OTHER group at the end rather than dropping it — a skill must never be silently omitted. (If OTHER is non-empty, it's a signal thatCLAUDE.md's Skill layers section needs updating.)
- Assign each user-invocable skill to its layer per
Output
Render the cheatsheet as a boxed ASCII card using the data you just gathered. Use this structure — one section per layer (in CLAUDE.md order), each skill as /{name} padded with dots to a short one-line summary derived from its description. Do not add commentary before or after the box.
┌─────────────────────────────────────────────────────────────┐
│ ACUMEN CHEATSHEET — Product fluency for AI │
├─────────────────────────────────────────────────────────────┤
│ │
│ CONTEXT (build product knowledge) │
│ /{name} ...... <one-line summary> │
│ ... │
│ │
│ AUDIT (assess product health) │
│ ... │
│ │
│ IDEATE (diverge on solutions) │
│ ... │
│ │
│ CRAFT (build product artifacts) │
│ ... │
│ │
│ COMMUNICATE (share with the world) │
│ ... │
│ │
│ META (manage Acumen itself) │
│ ... │
│ │
├─────────────────────────────────────────────────────────────┤
│ Tip: Run /teach-acumen first to set up product context. │
│ Then audit with /diagnose, then diverge with /workshop. │
└─────────────────────────────────────────────────────────────┘
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 · 57 lines · 20 tokens per session scan A 3491d60d6a04
cheatsheet is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 27d ago), licensed Apache-2.0. It adds 20 tokens to every session and 772 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 2026-08-30.
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…