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/haizelabs/annotate/annotate_skillnpx skills add haizelabs/annotate --skill annotate_skillgit clone --depth 1 https://github.com/haizelabs/annotateWhat 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 | $0.00038 | $0.03925 |
| Opus 5 | $0.00019 | $0.01962 |
| Sonnet 5 | $0.00008 | $0.00785 |
| Haiku 4.5 | $0.00004 | $0.00392 |
Grade B, and why
annotate scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST "http://localhost:8000/feedback-config" -H "Content-Type: application/json" -d @.haize_annotations/new_config.json Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**REQUIRED STEP:** Call `curl -s http://localhost:8000/openapi.json` to get documentation on interacting with the FastAPI server. The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- __init__.py 50 B runs code
- frontend/.gitignore 326 B
- frontend/.prettierrc 677 B
- frontend/.yarnrc.yml 25 B
- frontend/components.json 464 B
- frontend/eslint.config.js 621 B runs code
- frontend/index.html 387 B
- frontend/package-lock.json 182 KB
- frontend/package.json 2.0 KB
- frontend/postcss.config.js 154 B runs code
- frontend/public/assets/bird-logo-transparent.ico 6.4 KB
- frontend/public/assets/bird-logo-transparent.svg 2.0 KB
- frontend/README.md 92 B
- frontend/src/@types/index.d.ts 745 B runs code
- frontend/src/api/api.ts 580 B runs code
- frontend/src/api/interactions/queries.ts 722 B runs code
- frontend/src/api/interactions/router.ts 389 B runs code
- frontend/src/api/loader.ts 450 B runs code
- frontend/src/api/query.ts 198 B runs code
- frontend/src/api/testCases/loader.ts 766 B runs code
- frontend/src/api/testCases/queries.ts 770 B runs code
- frontend/src/api/testCases/router.ts 426 B runs code
- frontend/src/api/utils.ts 1.7 KB runs code
- frontend/src/App.tsx 2.2 KB
- frontend/src/assets/react.svg 4.0 KB
- frontend/src/components/agent-node.tsx 3.8 KB
- frontend/src/components/annotations/Annotation.tsx 927 B
- frontend/src/components/annotations/Categorical.tsx 1.3 KB
- frontend/src/components/annotations/Ranking.tsx 3.1 KB
- frontend/src/components/annotations/Score.tsx 717 B
- frontend/src/components/CollapsibleContent.tsx 1.4 KB
- frontend/src/components/Datatable.tsx 13 KB
- frontend/src/components/icons.tsx 2.6 KB
- frontend/src/components/Note.tsx 2.2 KB
- frontend/src/components/Tag.tsx 1.4 KB
- frontend/src/components/TraceView.tsx 4.8 KB
- frontend/src/components/ui/badge.tsx 1.1 KB
- frontend/src/components/ui/button.tsx 1.8 KB
- frontend/src/components/ui/card.tsx 1.8 KB
- frontend/src/components/ui/collapsible.tsx 315 B
- frontend/src/components/ui/dropdown-menu.tsx 7.4 KB
- frontend/src/components/ui/label.tsx 710 B
- frontend/src/components/ui/radio-group.tsx 1.4 KB
- frontend/src/components/ui/resizable.tsx 1.7 KB
- frontend/src/components/ui/scroll-area.tsx 1.6 KB
- frontend/src/components/ui/select.tsx 5.6 KB
- frontend/src/components/ui/separator.tsx 717 B
- frontend/src/components/ui/skeleton.tsx 266 B
- frontend/src/components/ui/slider.tsx 1.0 KB
- frontend/src/components/ui/table.tsx 2.8 KB
- frontend/src/components/ui/tabs.tsx 1.8 KB
- frontend/src/components/ViewInteractionGroup.tsx 841 B
- frontend/src/data/agent-model.ts 11 KB runs code
- frontend/src/index.css 4.6 KB
- frontend/src/lib/utils.ts 2.1 KB runs code
- frontend/src/main.tsx 237 B
- frontend/src/pages/ErrorPage/ErrorPage.tsx 1.3 KB
- frontend/src/pages/TestCases/ViewTestCases/TestCaseAnnotation.tsx 5.0 KB
- frontend/src/pages/TestCases/ViewTestCases/TestCaseInteractions.tsx 1.3 KB
- frontend/src/pages/TestCases/ViewTestCases/TraceSidebar.tsx 24 KB
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 · 328 lines · 38 tokens per session scan B c4f75aeeab70
annotate is a skill published in the GitHub repository haizelabs/annotate (17 stars, last pushed 10mo ago), with no licence file. It adds 38 tokens to every session and 3,925 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). 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.
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.