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/refinenpx skills add heiko-braun/draft --skill refinegit 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 | $0.00007 | $0.00628 |
| Opus 5 | $0.00003 | $0.00314 |
| Sonnet 5 | $0.00001 | $0.00126 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
refine 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine Existing Spec
Refine an existing specification based on new insights, feedback, or changing requirements.
Feature to refine: $ARGUMENTS
Instructions
-
Load the existing spec from
/specs/{feature}.md- If no spec exists for this feature, suggest using
/specinstead - If multiple specs match, ask the user which one to refine
- If no spec exists for this feature, suggest using
-
Ask 2-3 focused refinement questions (one at a time):
- What aspect needs refinement? (goals, criteria, approach, scope)
- What new information or feedback has emerged?
- Are there specific pain points with the current spec?
-
Check scope and modularity:
- Does the refinement keep the spec small enough for a single vertical slice?
- If criteria are being added, does the total still stay at ~5 or fewer?
- Does the refinement change which modules are affected? Update the "Affected Modules" section.
- If the refinement significantly expands scope or blast radius, suggest a separate spec instead.
-
Update the spec in place:
- Preserve front-matter: Keep all existing front-matter fields (title, description, author). Keep
status: proposed(refinements don't change status) - Preserve completed acceptance criteria checkboxes
- Update goals, criteria, or approach as needed
- Update "Affected Modules" and "Test Strategy" if the changes alter them
- Add to "Out of Scope" if removing features
- Add refinement notes to the "Notes" section with timestamp
- Preserve front-matter: Keep all existing front-matter fields (title, description, author). Keep
-
Show a diff summary:
- Highlight what changed (goals, new criteria, removed items, affected modules, etc.)
- Ask for confirmation before saving
-
Get user confirmation before proceeding to implementation
- If confirmed, use the implement skill with the refined spec
- If not, ask if they want to refine further
Refinement Guidelines
- Preserve progress: Don't uncheck completed criteria unless they're no longer valid
- Be additive when possible: Add new criteria rather than rewriting existing ones
- Document changes: Always add a timestamped note explaining what was refined and why
- Validate scope: Check if refinements are expanding scope significantly - if so, suggest a new spec
- Validate modularity: If the refinement introduces new module dependencies or widens the blast radius, flag it explicitly
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 · 66 lines · 7 tokens per session scan A dc5d1f629585
refine is a skill published in the GitHub repository heiko-braun/draft (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 628 once invoked, about $0.0000 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…