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 rules/punkadillo/figma-code-composer/frozen-pathsgit clone --depth 1 https://github.com/punkadillo/figma-code-composerWhat 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 | $0.00435 | $0.00435 |
| Opus 5 | $0.00217 | $0.00217 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
frozen-paths 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 yesterday.
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
Rule 1 — Write-access allowlist
Cursor in agent mode may create / edit / delete files only inside the directories listed in .figma-pipeline/config.json → writeScope.allowedDirs. Everything else in the project is read-only.
Before /init-figma-compose runs (bootstrap)
Until .figma-pipeline/config.json exists, only these roots are writable:
.figma-pipeline/**.mcp.json/tmp/**
After /init-figma-compose
The wizard composes writeScope.allowedDirs from the configured paths (token output, component dirs, icon output, story / test output when not co-located). Plus always: .figma-pipeline/**, .mcp.json, /tmp/**.
Always-blocked
Regardless of the allowlist:
node_modules/**,dist/**,build/**,.next/**,.turbo/**,coverage/**package-lock.json,yarn.lock,pnpm-lock.yaml.env,.env.*(except.env.example— seeenv-access.mdc)tailwind.config.{js,ts,cjs,mjs}whencssSystem.name == "tailwind-v4"(v4 is CSS-only)
Escape
The escape hatch FP_ALLOW_RESTRICTED_WRITE=1 (legacy HK_ALLOW_RESTRICTED_WRITE=1 still accepted) lives in the shell env, which Cursor cannot read. The user must explicitly tell Cursor to override; otherwise refuse the write and report.
If you find yourself wanting to write outside the allowlist
Stop. Either (a) ask the user to extend config.writeScope.allowedDirs and re-validate, or (b) ask the user to override explicitly. Do not silently bypass.
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.
- yesterday First seen · 39 lines · 435 tokens per session scan A 0588d4482292
frozen-paths is a cursor rule published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 13d ago), licensed MIT. It adds 435 tokens to every session, about $0.0022 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 2026-08-31.
Other cursor rules, from other repositories
pi-en
PI Cognitive AI. Trigger: $pi/coding/dev/code/architecture/API/refactor/debug/bug/error/exception/crash/timeout/performance/optimization/test/compile/git/release/verify/review/CR/product/requirements/ops/growth/design/team/support, or deep/2+ failures/looping/stuck/giving-up/retry/nevermind.
pi
你与用户是伙伴🤝战友🔥亲人❤️利益共同体🎯——目标一致：高质量解决问题。百务皆适，融贯古今中西的通才。.
testing
Guide for writing pytest unit and integration tests.
ai-actions-schemas
Cursor rule "ai-actions-schemas" from freshworks-developers/fw-dev-tools, covering ai actions schemas (actions.json), structure, parameters schema, preferred: flat structure and string constraints (enum, pattern, format).
tools
(none|read|write|network|exec) and risk (low|medium|high|critical). These drive the permission classifier — be honest.
git-commits
description: "Reference and apply the git commits skill for Conventional Commit formatting and pre-push checks." alwaysApply: true.