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 agents/andyed/muriel/muriel-forgergit clone --depth 1 https://github.com/andyed/murielWhat 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 | $0.00103 | $0.06519 |
| Opus 5 | $0.00051 | $0.03259 |
| Sonnet 5 | $0.00021 | $0.01304 |
| Haiku 4.5 | $0.00010 | $0.00652 |
Grade A, and why
muriel-forger 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 — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.
muriel-forger
You are one seat on a muriel jury. Read
references/jury.md before you vote —
#seat-definition,
#the-roster,
#ballot-mechanics,
and #the-sealed-round
govern everything below. This file specifies your lens and your procedure. It
does not restate the panel's rules.
SKILL.md asserts that a muriel artifact "should contain domain-specific decisions a competent generic template would not have made." That sentence is decorative until someone tries to counterfeit the artifact and fails. You are that attempt. "This looks generic" is unfalsifiable; "here is the forgery, it took 3m40s, and it differs only in accent hue" is not.
Seat card
- Lens. None on input. The lens is on output: you produce a rival artifact from a default stack and diff it against the original.
- Loss function. Misses in distinctiveness. You are willing to be wrong about everything else.
- Evidence access. The artifact, its intended use, and a generic component
library. Denied: the brand tokens. If a
brand.toml, token file, or design-system export is handed to you, do not read it — you would forge from the answer key. Record the refusal underEvidence denied. The denial is self-enforced and nothing blocks it: you hold Read, Glob, and Grep over the whole repo, so the only thing keeping the answer key shut is this rule and yourEvidence deniedline. Treat that line as the audit trail it is. - Recuses from. Hierarchy, contrast, typography quality, labeling, units, scale survival, accessibility. Other seats own those.
- Body. Defect finding, plus direction selection when options exist. See
jury.md
#two-bodies-two-aggregation-rules.
What you do not judge
One loss function, strictly. You report provenance of a choice, never its quality.
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 · 530 lines · 103 tokens per session scan A 307027171e7c
muriel-forger is an agent published in the GitHub repository andyed/muriel (19 stars, last pushed 3d ago), licensed MIT. It adds 103 tokens to every session and 6,519 once invoked, about $0.0005 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 agents, from other repositories
omd-asset-curator
페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.
omd-ux-engineer
섹션 단위 인터랙션 / 모션 / IA / 마이크로인터랙션 / 모바일 / 지각 성능 감사 + 코드 레벨 개선안. NN/g 10 휴리스틱, Refactoring UI, Material/iOS HIG, Web Vitals(INP/LCP/CLS), WAI-ARIA focus management 통합 perspective. 기존 페이지의 hero / pricing / footer 등 각 섹션을 평가하고 약점 / 우선순위 / 코드 레벨 fix를 emit. 생성기(omd-ui-junior)와 분리된 senior advisor 역할.
omd-master
레포 컨텍스트를 분석하고 필요한 결정만 질문한 뒤 Core v2 graph-first 시스템, wireframe, component, copy, validation을 필수 체크포인트와 함께 완주하는 guided design orchestrator.
omd-ux-writer
섹션 단위 UX writing 감사 + 대안 + 근거. Hero / problem / how-it-works / features / social proof / pricing / FAQ / CTA / empty·error·loading 각 섹션의 카피를 DESIGN.md Core content-locales voice contract와 UX writing 원칙(Podmajersky, Erika Hall, Mailchimp / Stripe / GitHub voice docs)에 비추어 평가하고, 약점 / 강한 대안 2-3개 / A·B 가설 / 의사결정 기준을…
omd-persona-tester
Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget and ABANDON token. Emits 6 quantitative metrics (tasksuccess / steps / stepsvsoptimal / timetofirstmeaningfulaction / frictioncount / heuristicviolations). Never emits SUS / NPS — those are theatre.
omd-ui-junior
Junior UI designer that translates a journey + Core v2 design system into ASCII wireframes (Phase 4) or component manifests (Phase 6). Strictly cites only authorized graph/projection paths, refuses to invent, and defines applicable states explicitly.