Borrowing it
Nothing to install: this file belongs to jeltehomminga/figma-design-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jeltehomminga/figma-design-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/jeltehomminga/figma-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/instructions/jeltehomminga/figma-design-skills/agents-md)<a href="https://agentmods.dev/instructions/jeltehomminga/figma-design-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jeltehomminga/figma-design-skills/agents-md/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/instructions/jeltehomminga/figma-design-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jeltehomminga/figma-design-skills/agents-md.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 | $0.00786 | $0.00786 |
| Opus 5.5 | $0.00314 | $0.00314 |
| Sonnet 5.5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
figma-design-skills AGENTS.md 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for any coding agent working in — or with — this repository.
This repo ships two composable, tool-agnostic skills for design-to-code fidelity. The summaries below work as passive guidance in any agent; the full step-by-step instructions live in the skill files and should be opened when a task matches.
The two skills
- Extract —
skills/figma-design-extract/SKILL.md. Use when implementing UI from a Figma node (afigma.comURL, "build this design", "match the Figma"). Read exact values via the Figma MCP (get_variable_defsfor tokens,get_metadatafor sizes,get_design_contextfor structure;get_screenshotis a visual reference only — never measured). Before concluding a value has no token, check the linked libraries withsearch_design_system(includeVariables: true). Map every value to a repo design token; never hardcode. ConvertletterSpacingfrom Figma's percent (-2means-0.02em). Output a design-spec table. - Verify —
skills/design-fidelity-verify/SKILL.md. Use when checking a built screen ("verify the design", "is this pixel-perfect", "design QA"). Measure the rendered values (web:getComputedStyle; mobile: the resolved style off the rendered React fiber over the Metro/CDP eval channel — not native view props, which have no introspection channel on Android and return less than the fiber read on iOS Fabric). Walk every spec-table row, classify it, fix highest-severity first, bounded to ~3 iterations, and report residuals honestly. Runnable readers ship inskills/design-fidelity-verify/scripts/.
Core rules (both skills)
- Tokens/variables are the source of truth. Never measure from a screenshot.
- Fidelity means the right token, not the literal pixel. So resolve every measured value back to its named token before labelling a row — a bare hex/px delta is not a finding. Verdicts:
PASS·DRIFT(name both tokens) ·HARDCODED(resolves to none) ·VARIANT(wrong state — re-pick the node) ·MISSING(selector matched nothing; an error, never a pass). - Tag each drift
theme-level(one upstream, cross-app fix) orcomponent-level(fix here). Never patch a theme default locally. - Reuse existing components before scaffolding new ones.
- Prove a match by measuring rendered values, not glancing; cap the fix loop at ~3 iterations and report residuals honestly.
- Compare box/position values with a ±1px tolerance — rendered rects are fractional.
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 · 33 lines · 786 tokens per session scan A c14d45f2ecc0
figma-design-skills AGENTS.md is an instructions file published in the GitHub repository jeltehomminga/figma-design-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 786 tokens to every session, about $0.0031 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.