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/aaoa-dev/sleak/sleaknpx skills add aaoa-dev/Sleak --skill sleakgit clone --depth 1 https://github.com/aaoa-dev/SleakWhat 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 | $0.00066 | $0.02405 |
| Opus 5 | $0.00033 | $0.01203 |
| Sonnet 5 | $0.00013 | $0.00481 |
| Haiku 4.5 | $0.00007 | $0.00241 |
Grade A, and why
sleak 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sleak
Better design decisions for interfaces that feel intentional, not assembled from defaults.
Works for designers reviewing work, engineers implementing UI, and agents assisting either. The rules are craft and hierarchy, not tool-specific. Read them directly or load this skill when you want a structured audit.
Core principles
These rules define this skill. Check them first on every audit.
1. Concentric corner radius
Nested rounded elements must follow one relationship:
parent − padding = child
parent − child = padding
child + padding = parent
Either the parent or child radius drives; padding is the gap between curves. Never reuse the same radius on both layers when padding > 0.
→ Full rules, CSS, and audit: references/concentric-radius.md
2. Section eyebrows
Small kickers above section headings ("Features", "About", pills, overlines). Fine on one section; weak when repeated on every block. Hero: almost never, only a rare release/status callout, and even then prefer a badge, not an eyebrow.
→ Limits and fixes: references/section-eyebrows.md
3. Intentional accent use
Full accent color is scarce. Use it to pull the eye to the most important task on the page, not to decorate icons, borders, headings, or every card.
- One primary focal point at full saturation (main CTA or critical action)
- Secondary controls → neutral or outline
- Opacity tints of the accent → only where they support that primary path (selected, focus, progress)
- Extra full-chroma accent dilutes brand impact and scatters attention
→ Full tiers, tokens, and audit: references/color.md
Strength of guidance
Read every Sleak rule at the right strength:
- Invariant: correctness, accessibility, semantics, or broken geometry. Do not violate it without a concrete platform constraint.
- Strong default: Sleak's opinionated starting point. Depart when the product, content, or established system gives a better reason, and preserve the intent behind the rule.
- Contextual heuristic: a diagnostic, not a pass/fail law. Verify it on the rendered result.
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 · 238 lines · 66 tokens per session scan A e2ef1279e276
sleak is a skill published in the GitHub repository aaoa-dev/Sleak (2 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 2,405 once invoked, about $0.0003 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…