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/rwliebs/dossier/extractnpx skills add rwliebs/Dossier --skill extractgit clone --depth 1 https://github.com/rwliebs/DossierWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rwliebs/dossier/extract)<a href="https://agentmods.dev/skills/rwliebs/dossier/extract"><img src="https://agentmods.dev/badge/skills/rwliebs/dossier/extract.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00031 | $0.00766 |
| Opus 5 | $0.00015 | $0.00383 |
| Sonnet 5 | $0.00006 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
extract 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 4d 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.
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 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.
- 4d ago First seen · 91 lines · 31 tokens per session scan A 31e6e3716b78
extract is a skill published in the GitHub repository rwliebs/Dossier (88 stars, last pushed 1mo ago), with no licence file. It adds 31 tokens to every session and 766 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 2026-08-30.
Other skills, from other repositories
design-plan
아프로디테 디자인 오케스트레이터. 사이트 벤치마크 해부, 사용자 과업·메시지·CTA·신뢰·모바일 변환을 담은 Experience Contract, 실제 렌더 방향 탐색, DESIGN.md, 구현, 미학·UX·성능·접근성 검증과 학습까지 프론트 디자인 전 과정을 수행합니다. /aphrodite, 아프로디테, 디자인 계획, 프론트 디자인 요청에 사용합니다.
design-system-starter
Create and evolve design systems with design tokens, component architecture, and accessibility guidelines. Use when user asks to "create design system", "design tokens", "component library", "style guide", or when starting a frontend project that needs consistent UI foundation.
diagram-design
에디토리얼 품질 다이어그램 표현 계층. 파이프라인 .mmd(flowchart/sequence/state/ER) 또는 자연어 설명을 브랜드 토큰 기반 self-contained HTML + inline SVG로 렌더링한다. PRD·기술문서·아키텍처 문서 등 사람에게 전달되는 산출물에 다이어그램이 필요할 때 사용. Mermaid 파이프라인을 대체하지 않음(.mmd가 정본, 이 모듈은 렌더링만). "다이어그램 예쁘게", "editorial diagram", "다이어그램 렌더링", "발표용 다이어그램" 요청에 실행. Credits…
draw-io
Create and edit draw.io diagrams (.drawio files). Use when user asks to "create a diagram", "edit drawio", mentions .drawio files, wants AWS architecture diagrams, or needs to convert diagrams to PNG. Triggers on "drawio", "draw.io", ".drawio", "diagram xml".
excalidraw
Work with .excalidraw and .excalidraw.json diagrams, including reading, explaining, comparing, creating, and editing them. Use context-isolated native agents for JSON-heavy operations when available, with a bounded sequential fallback when delegation is unavailable.
frontend-design
아프로디테(design-plan) 파이프라인의 Experience Contract와 DESIGN.md를 실제 렌더로 구현하고 비평하는 미학 실행 스킬. 레시피/CSV/anatomy/스캐폴드와 공식 플러그인이 없는 CLI(Codex/Antigravity)의 디자인 폴백을 제공한다. Claude Code의 일반 UI 요청은 공식 frontend-design 플러그인이 담당한다.