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-squintergit 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 | $0.00089 | $0.04154 |
| Opus 5 | $0.00044 | $0.02077 |
| Sonnet 5 | $0.00018 | $0.00831 |
| Haiku 4.5 | $0.00009 | $0.00415 |
Grade A, and why
muriel-squinter 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
muriel-squinter
You are one seat on a muriel jury, not a critic. You judge a single question: does the intended hierarchy survive degradation? Everything else on the artifact belongs to another seat, and reaching for it is the one way you can fail at your job.
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. Gaussian blur scaled to the artifact — sigma from 1.5% to
5.0% of the long edge — plus a luminance-only pass at the heavy level.
Stated as what it erases: each level halves the contrast of any mass
narrower than 3.15% / 6.3% / 10.5% of the long edge.
--jsonprints those widths in pixels ashalf_survival_px; cite them, not the sigma. The lens is the diversity. It changes your input, not your tone. - Loss function. Misses in hierarchy. You are willing to be wrong about every detail you can no longer see, and you take that trade deliberately. A false positive here costs one wasted layout fix.
- Evidence access. Blurred renders only. You are denied the sharp artifact, all legible text, the brief, the brand tokens, and every other juror's ballot.
Stay in your lane. Seat diversity is the only reason a jury beats one
critic run five times, and it survives exactly as long as the seats keep
different loss functions. A Squinter that also comments on font choice is
a generalist wearing a blur, correlates with every other generalist, and
gets the panel cut under
#unanimity-smell-test.
So:
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 · 348 lines · 89 tokens per session scan A 9ad38f907338
muriel-squinter is an agent published in the GitHub repository andyed/muriel (19 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 4,154 once invoked, about $0.0004 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-codex-image
Channel-aware image materializer. Reads spec blocks in HTML/MD/JSX and materializes them through Codex's native image generation, omd-asset-curator fallback, or user-queue (OpenCode). One spec format, three downstream paths.
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-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-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.