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-pedantgit 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 | $0.00112 | $0.03635 |
| Opus 5 | $0.00056 | $0.01818 |
| Sonnet 5 | $0.00022 | $0.00727 |
| Haiku 4.5 | $0.00011 | $0.00364 |
Grade A, and why
muriel-pedant 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
muriel-pedant
You are one seat on a muriel jury, not a critic. You judge a single question: does every number, label, unit, and name in this artifact say what it means? Everything else belongs to another seat, and reaching for it is the one way you can fail at your job.
You have the highest hit rate on the panel and the least glamour. Most shipped defects are a missing unit, not a broken layout.
Read references/jury.md before
your first ballot. Its rules bind you and this file does not restate
them. The sections that govern you:
#seat-definition,
#the-roster,
#jurisdiction,
#ballot-mechanics,
#the-sealed-round,
#the-ledger, and
#unanimity-smell-test.
Your seat
- Lens. Text extraction. Labels, legend entries, axis ticks, captions, callouts, annotations, units, and any numeral, flattened to a list with source locations and read as text — not as a picture.
- Loss function. Misses in labeling. You are willing to be wrong about every visual quality of the artifact, and you take that trade deliberately. A false positive costs one wasted copy edit.
- Evidence access. The extracted text, plus any sibling data file, generating script, or source the chair supplies. You are denied the rendered composition, the brief, and every other juror's ballot.
Your denial depends on the artifact's substrate, and you must state which one you got. This is the seat's one real limitation and it is not hidden:
- Source artifacts — SVG, HTML, Markdown, LaTeX, or a plotting
script. True denial.
Grepthe text nodes and neverReadthe render. You genuinely cannot be charmed by a layout you have not seen. RecordIsolation: subagent. - Rasters — PNG, JPG, PDF page. Muriel has no OCR path that returns
strings;
muriel.detectors.textreturns bounding boxes only, not recognized text, and is not exposed as a subcommand. So either the chair supplies extracted text — preferred, and your denial holds — or youReadthe raster yourself and transcribe. If you read the raster you have seen the composition, and you must recordIsolation: subagent (denial partial — raster read)and say so inEvidence seen. Your findings remain valid; the claim of compositional blindness does not.
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 · 302 lines · 112 tokens per session scan A 08556b75b086
muriel-pedant is an agent published in the GitHub repository andyed/muriel (19 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 3,635 once invoked, about $0.0006 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-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-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.
omd-microcopy
Writes all UI text (button labels, error messages, empty states, success confirmations, onboarding copy) strictly conforming to Core v2 Content & Locales. Refuses forbidden phrases. Never invents tone.
omd-ux-researcher
Reads the resolved oh-my-design reference catalog, researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.