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/thaitype/chief/shape-upnpx skills add thaitype/chief --skill shape-upgit clone --depth 1 https://github.com/thaitype/chiefWhat 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 | $0.00080 | $0.01010 |
| Opus 5 | $0.00040 | $0.00505 |
| Sonnet 5 | $0.00016 | $0.00202 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
shape-up 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shape Up — Top-Down Design Spec
Shape a vague idea into a clear design spec by working top-down: start from the big picture, confirm alignment at each layer, then go deeper. This is NOT an interview — it's collaborative writing where the agent drafts and the user shapes.
When to Use
- User says "shape up", "design spec", "let's design", "plan a system", "I need to think through this"
- User has a large or ambiguous project and needs to see the big picture first
- Before
/grill-design— when the scope isn't clear enough to grill on details yet
Core Principle
One layer at a time. Confirm before going deeper. Never jump ahead.
If the user can't answer something at the current layer, mark it [TBD] and move on. Don't drill down into unknowns — that's how people lose focus.
Workflow
Layer 1: Vision
Ask the user to describe what they're building in plain language. Then co-write a short vision block:
- What — one sentence describing the thing
- Why — what problem it solves, who it's for
- Done looks like — how you'd know it succeeded
Draft this as a short block (5-8 lines max). Show it to the user. Adjust until they say it's right.
Do NOT ask about tech stack, architecture, or implementation yet.
Layer 2: Scope
Now that the vision is clear, co-write the scope:
- In scope — what this project will do (bullet list)
- Out of scope — what it explicitly won't do (bullet list)
- Constraints — timeline, tech, team, budget, dependencies
- Users / Actors — who interacts with it
Draft and show. The user cuts, adds, moves things between in/out scope. Keep going until scope feels tight.
If scope is getting too big, say so: "This feels like it's growing — want to split it?"
Layer 3: Building Blocks
Break the in-scope work into 3-7 big blocks. Each block is a major component, feature area, or workstream. For each block:
- Name — short label
- Purpose — one line
- Depends on — which other blocks it needs
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 · 92 lines · 80 tokens per session scan A a079332da889
shape-up is a skill published in the GitHub repository thaitype/chief (56 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,010 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 2026-08-30.
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…