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/pipeline-rolesgit 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/pipeline-roles)<a href="https://agentmods.dev/rules/punkadillo/figma-code-composer/pipeline-roles"><img src="https://agentmods.dev/badge/rules/punkadillo/figma-code-composer/pipeline-roles.svg" alt="Measured on agentmods" 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 | $0.00504 | $0.00504 |
| Opus 5 | $0.00252 | $0.00252 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
pipeline-roles 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 4d 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.
What it actually says
Supporting — Per-agent write scope
Cursor doesn't natively spawn sub-agents — you run them sequentially in one chat thread. Never attempt to launch a specialist (or the coordinator) as a separate model-pinned agent — that path doesn't exist in Cursor and, on the Free plan, aborts the whole run with Named models unavailable — Free plans can only use Auto (see model-preference.mdc). Play every role inline on the current model. To prevent role bleed, respect each agent's declared write scope:
| Agent | May write inside |
|---|---|
wizard |
.figma-pipeline/config.json, .mcp.json, /tmp/figma-wizard-*/* |
project-detector |
nothing — read-only |
figma-coordinator |
/tmp/figma-<runId>/* only (scratch, including the per-run lessons.md) |
figma-fetcher |
/tmp/figma-<runId>/manifest.json + shot-*.png + scratch/* |
token-builder |
config.tokens.outputDir/** |
component-builder |
configured component target dirs (atomicLayout.*Dir / featureSlicedLayout.*Dir / flatLayout.componentsDir) |
icon-generator |
config.icons.outputDir/** (component files + barrel) |
story-author |
stories colocated with components (or config.stories.outputDir) |
test-author |
unit tests colocated with components (or config.tests.unit.outputDir) + E2E specs under config.tests.e2e.outputDir |
If you find yourself wanting to write outside your current role's scope, STOP. Either switch roles explicitly ("now acting as token-builder") or escalate to the user.
The .cursor/rules/frozen-paths.mdc allowlist enforces the union of these scopes globally; this rule helps you stay tidy within that envelope.
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.
- 4d ago First seen · 26 lines · 504 tokens per session scan A 5bbf55cfbc6e
pipeline-roles is a cursor rule published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 15d ago), licensed MIT. It adds 504 tokens to every session, about $0.0025 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.
testing
Guide for writing pytest unit and integration tests.
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.
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.