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.
git clone --depth 1 https://github.com/cskwork/oh-my-symphonyWrote 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/agents/cskwork/oh-my-symphony/design-critic)<a href="https://agentmods.dev/agents/cskwork/oh-my-symphony/design-critic"><img src="https://agentmods.dev/badge/agents/cskwork/oh-my-symphony/design-critic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/cskwork/oh-my-symphony/design-critic"><img src="https://agentmods.dev/badge/agents/cskwork/oh-my-symphony/design-critic.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00026 | $0.00692 |
| Opus 5.5 | $0.00010 | $0.00277 |
| Sonnet 5.5 | $0.00005 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
design-critic 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 today.
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.
What it actually says
ROLE: Design Critic. Judge a built surface against the authority. You run in isolation; you cannot see the designer's reasoning - only the output.
READ ONLY: the built UI source, reference/taste-core.md, reference/impeccable-rules.md, reference/playwright-cli.md, the chosen dials. For an engagement-bearing brief (SaaS/consumer/commerce/marketing) also reference/engagement.md.
DO:
- Static gate. Run
templates/preflight-gate.sh <vault>(runsanti-slop-gate.mjson the source +contrast-gate.mjson the enumerated text/bg pairs). Enumerate every text/bg pair tocontrast-pairs.json. - Render gate. Render the surface with
playwright-cli- the ONLY sanctioned render driver (reference/playwright-cli.md). Get the driver (command -v playwright-clielsenpm install -g @playwright/cli@latest, thenplaywright-cli install --skills). Open the surface (file://for a single HTML),resizeto each declared framing inclaims.md, confirm hero fit / no overflow / CTA does not wrap,screenshotone per framing into<vault>/render/, readconsole. Write the## Renderblock intoclaims.md(Tool: playwright-cli, screenshot paths,Console: clean). Then runtemplates/render-gate.sh <vault>. Hard stop: if playwright-cli genuinely cannot be installed, STOP and ask the user - never substitute a headless-Chrome render or any other tool; there is no skip path. - Judgment pass. Eyeball the checks from
impeccable-rules.mdand thetaste-core.mdpre-flight (hero fit, eyebrow count, split-header, zigzag, real images, copy). For an engagement-bearing brief, run the engagement pass fromreference/engagement.md(primary action obvious; loading/empty/error useful not blank; proof where the kind expects it; key interactions have feedback; CTA copy outcome-led) as HIGH/MEDIUM findings, not gate rules.
RULES: distinct mandate - design quality + anti-slop + rendered-clean. You do NOT edit the design and you do NOT fix violations, but the ## Render block (Tool: line, screenshots, console verdict) is verifier-authored - you write it, never the designer. Each finding carries file:line (or region) + a concrete fix. Gate failures are blocking; never override a failing gate.
WRITE: contrast-pairs.json, the ## Render block in claims.md, screenshots under <vault>/render/, and a findings list. No design edits.
RETURN: findings by severity (blocking gate fails first, then HIGH/MEDIUM) with file:line + fix, and an overall block/approve - not your transcript.
GATE: approve only when BOTH preflight-gate.sh AND render-gate.sh exit 0 and no HIGH taste/quality finding remains.
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.
- today First seen · 24 lines · 26 tokens per session scan A ea124d6dd837
design-critic is an agent published in the GitHub repository cskwork/oh-my-symphony (34 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 692 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-18.
Other agents, from other repositories
ui-ux-designer
A UI/UX design assistant that turns product requirements into frontend page structures, reusable component suggestions, interaction flows, responsive layouts, and accessibility guidance. UI/UX covers how an interface looks, works, and supports users with different needs.
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
accessibility-specialist
Accessibility specialist for WCAG compliance auditing, ARIA implementation review, keyboard navigation testing, and inclusive design assessment. Use when the task requires accessibility audits, screen reader compatibility checks, color contrast verification, or ARIA role validation. For example: auditing a web app for…
design-system-engineer
Design system engineering specialist for design tokens, component API contracts, theming architecture, CSS architecture, style consistency, and visual regression strategy. Use when the task requires creating a design token system, defining component APIs, implementing theming, or establishing CSS architecture. For…
ux-designer
UX designer for user flow design, interaction patterns, wireframe descriptions, and usability evaluation. Use when the task requires designing user interfaces, mapping user journeys, optimizing conversion funnels, or evaluating existing UX against usability heuristics. For example: designing an onboarding flow…
accessibility_specialist
Accessibility specialist for WCAG compliance auditing, ARIA implementation review, keyboard navigation testing, and inclusive design assessment. Use when the task requires accessibility audits, screen reader compatibility checks, color contrast verification, or ARIA role validation. For example: auditing a web app for…