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/punkadillo/figma-code-composerWrote 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/rules/punkadillo/figma-code-composer/config-schema)<a href="https://agentmods.dev/rules/punkadillo/figma-code-composer/config-schema"><img src="https://agentmods.dev/badge/rules/punkadillo/figma-code-composer/config-schema/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/rules/punkadillo/figma-code-composer/config-schema"><img src="https://agentmods.dev/badge/rules/punkadillo/figma-code-composer/config-schema.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 | $0.00000 | $0.00682 |
| Opus 5.5 | $0.00000 | $0.00273 |
| Sonnet 5.5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
config-schema 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supporting — .figma-pipeline/config.json contract
Backs binding rule 1 (write allowlist is derived from this file) and feeds the configSnapshot that the coordinator passes to every specialist.
This file is the runtime configuration every pipeline agent reads. Hand-edits are allowed; the wizard writes it during /init-figma-compose.
Required top-level keys
version, project, framework, language, cssSystem, tokens, components, icons, writeScope.
Optional (commonly present): designSystem, stories, tests, figma, tools, complexity, knowledgeGraph, autonomy.
autonomy (optional; absent → interactive, every gate blocks) controls how mid-run decision gates resolve when the user may be away. level ∈ {interactive, autonomous}; per-gate keys onUnbound, onStackMismatch, onUnsupportedOverride, onLibrarySwap, onRemovedToken, onAmbiguousSelection. See figma-coordinator.md § Autonomy policy.
Hard constraints
version == "1.0". Bumping is a breaking change for every agent.framework.name ∈ {react, vue, angular, svelte}.cssSystem.name ∈ {tailwind-v4, tailwind-v3, unocss, css-modules, css-vars, sass, vanilla-extract, panda, styled-components}.tokens.strategy ∈ {tailwind-css-vars, css-custom-properties, scss-variables, js-tokens, unocss-theme}.components.designMethodology ∈ {atomic, feature-sliced, component-based, flat, custom}.designSystem.name ∈ {none, atomic, antd, chakra, heroui, mantine, mui, radix, shadcn}when present (default:none).writeScope.allowedDirsMUST be non-empty.
Path keys feed the write allowlist
tokens.outputDir, components.atomicLayout.*Dir (or feature-sliced / component-based / flat equivalents), icons.outputDir, stories.outputDir (when not co-located), tests.outputDir (when not co-located) — each appears under writeScope.allowedDirs with a trailing /**.
Edits
Free to hand-edit. After editing, the next Write will trigger check-config-schema.sh (Claude Code) or this rule in Cursor — Cursor users should re-validate manually with npx --yes ajv-cli@5 validate -s .figma-pipeline/config.schema.json -d .figma-pipeline/config.json.
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 · 40 lines · 0 tokens per session scan A 7ba1403b7d89
config-schema is a cursor rule published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 682 tokens. 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 cursor rules, from other repositories
spec-workflow
SDD specification protocol: risk-based specmode classification, required sections per mode, plan approval gate, and artifact directory conventions.
tools
(none|read|write|network|exec) and risk (low|medium|high|critical). These drive the permission classifier — be honest.
testing
Guide for writing pytest unit and integration tests.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.