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 skills add memi-design/design-skills --skill creative-rendering-auditgit clone --depth 1 https://github.com/memi-design/design-skillsWrote 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/memi-design/design-skills/creative-rendering-audit)<a href="https://agentmods.dev/skills/memi-design/design-skills/creative-rendering-audit"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/creative-rendering-audit/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/skills/memi-design/design-skills/creative-rendering-audit"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/creative-rendering-audit.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 | $0.00041 | $0.00753 |
| Opus 5.5 | $0.00016 | $0.00301 |
| Sonnet 5.5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
creative-rendering-audit 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Rendering Audit
Audit the supplied implementation and rendered behavior. Keep the audit read-only unless the user separately authorizes fixes.
Workflow
- Establish the intended visual behavior, target platforms, supported hardware, quality tiers, fallback, and user-facing acceptance criteria.
- Map the rendering path from host inputs to shader stages, textures, render targets, compositing, and final presentation.
- Gather evidence:
- Read shader and host-language source with file and line anchors.
- Capture compilation, validation, and device-loss messages.
- Exercise deterministic frames with a fixed seed and clock.
- Compare the full effect, reduced-motion path, unsupported-renderer path, and static fallback.
- Profile realistic content at the stated resolution on named hardware.
- Review every dimension in references/audit-rubric.md.
- Use references/platform-evidence.md for surface-specific evidence and failure modes.
- Reproduce or directly observe every high-severity finding. Mark code-only inferences as hypotheses.
- Report missing evidence as unassessed. Do not award a pass for a dimension that could not be tested.
Scoring
Score only verified evidence.
| Dimension | Points |
|---|---|
| Visual intent and interaction fit | 15 |
| Coordinate, sampling, color, and alpha correctness | 20 |
| Dither and temporal stability | 15 |
| Performance and resource bounds | 20 |
| Accessibility, fallback, and failure behavior | 20 |
| Provenance, licensing, and reproducible evidence | 10 |
Apply these caps:
- Missing or incompatible source or asset license: maximum 49.
- No accessible or unsupported-renderer fallback: maximum 69.
- No rendered runtime evidence: maximum 79.
- No named-device performance evidence for an animated effect: maximum 89.
Include a confidence value derived from assessed points divided by 100. Unknown dimensions score zero and lower confidence.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 80 lines · 41 tokens per session scan A 6b3538df7c2e
creative-rendering-audit is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 27d ago), licensed MIT. It adds 41 tokens to every session and 753 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
accessibility-per-component
Audit one design system component's accessibility against WCAG 2.2 AA: keyboard, screen reader, contrast, focus, ARIA, target size. Trigger: a11y audit, is this accessible, WCAG check, screen reader support, keyboard navigation check. Not for page- or product-wide audits.
figma-variable-audit
Audit Figma variable collections: tier mapping, naming, alias chains, modes, orphans; can fix in place with Figma Console MCP. Triggers: audit my Figma variables, review variable collections, Figma variable health. For token files in code use token-audit.
theme-audit
Audit theme parity: tokens missing or unchanged per theme, component tokens bypassing semantics, contrast within each theme, resolver contexts, theme-switch regressions. Triggers: dark mode audit, theme coverage, brand variant parity. For general token structure use token-audit.
token-audit
Audit how design tokens are defined: tiers, naming, alias chains, raw values, orphans, DTCG readiness. Triggers: audit my tokens, token architecture review, token health check. Not for code consuming tokens (token-compliance), theme parity (theme-audit) or Figma variables (figma-variable-audit).
ai-component-description
Write a six-section prose description (purpose, props, anti-patterns, composition, accessibility, examples) for a Figma component's description field so LLMs read it via MCP. Triggers: describe this component for AI, Figma MCP description. JSON metadata files: use metadata-schema-generator.
cicd-integration
Generate CI pipeline files and check scripts (GitHub Actions, GitLab, CircleCI, Bitbucket) that automate design system checks: token validation, hardcoded values, a11y scans, visual regression, bundle size. Trigger: set up CI, quality gates, automate these checks. Not for running an audit.