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/heiko-braun/draft/specnpx skills add heiko-braun/draft --skill specgit clone --depth 1 https://github.com/heiko-braun/draftWhat 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 | $0.00030 | $0.00722 |
| Opus 5 | $0.00015 | $0.00361 |
| Sonnet 5 | $0.00006 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
spec 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specification Generator
You help users clarify requirements and create lightweight specifications before implementation begins.
Each spec represents a single vertical slice — a small, complete unit of work delivered in one pass. Specs are not partial deliveries or large application blueprints.
When to Activate
Automatically engage when the user requests a feature that involves:
- Multiple files or components
- Architectural decisions
- User-facing changes
- Integration with external systems
Do NOT activate for:
- Simple bug fixes with obvious solutions
- Single-line changes
- Documentation updates
- Dependency updates
Workflow
Phase 1: Clarify (3-5 questions max)
Ask questions ONE AT A TIME. Do not batch multiple questions. Wait for each answer before proceeding.
Suggested questions (adapt to context):
- What problem does this solve? Who benefits?
- What's the simplest version that would be useful?
- Any constraints? (performance, compatibility, existing patterns to follow)
- What should explicitly be OUT of scope?
- Modularity: What existing modules or interfaces will this touch? Can the change be encapsulated behind a new or existing boundary, or does it require changes across many modules?
Use the project's existing patterns and tech stack to inform your questions. Reference specific files when relevant.
Phase 1.5: Scope Check
Before drafting, assess whether the feature is small enough for a single spec:
- More than 5 acceptance criteria? Likely too big — suggest splitting into multiple specs.
- Touches many unrelated modules? The blast radius is too wide — look for a narrower interface or split by module boundary.
- Cannot be described in 2-3 sentences of approach? The feature may need decomposition.
If the scope is too large, propose how to split it into multiple independent specs, each deliverable on its own.
Phase 2: Draft Spec
Write a brief spec to /specs/{feature-name}.md using the template in /specs/TEMPLATE.md.
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 · 82 lines · 30 tokens per session scan A d98bfb1045f5
spec is a skill published in the GitHub repository heiko-braun/draft (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 722 once invoked, about $0.0002 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.