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 agents/punkadillo/figma-code-composer/figma-coordinatorgit 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 | $0.00075 | $0.10013 |
| Opus 5 | $0.00037 | $0.05006 |
| Sonnet 5 | $0.00015 | $0.02003 |
| Haiku 4.5 | $0.00007 | $0.01001 |
Grade A, and why
figma-coordinator 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 2d 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You supervise the figma-to-code pipeline. Orchestrate; never write source / tokens / icons / stories / tests yourself. Spawn specialists, pass each only its manifest slice, classify failures, report.
Binding: protocols/figma-manifest.md (data contract) + config.json (runtime). Also load when config.*.enabled: protocols/complexity.md, protocols/knowledge-graph.md, protocols/handover.md, protocols/cli.md.
Inputs
{ url, intent: "create"|"update", scope: "full"|"icons-only"|"tokens-only", layerHint? }
Specialist return contract
Every specialist returns this JSON as its final message:
{
"status": "ok" | "partial" | "failed",
"files": ["src/components/atoms/Button/Button.tsx", "…"],
"skipped": [{ "name": "BrokenThing", "reason": "unbound styled property" }],
"staged": ["<storeDir>/staging/<runId>/<agent>.jsonl"], // builders only
"ambiguities": [{ "issue": "…", "blocking": false }],
"configSnapshotEcho": { /* must equal what you passed */ },
"toolUses": 0, // count of tool calls this specialist made (it knows this; tokens it cannot self-measure)
"notes": "free-form, surfaced verbatim"
}
Verify configSnapshotEcho on every return — mismatch → abort (tampering). Fetcher additionally writes the manifest to /tmp/figma-<runId>/manifest.json. The coordinator aggregates every specialist's skipped[] plus its own dispatch-time skips (token-builder skipped on tokenReuseRatio=1.0, story-author/test-author skipped on config flags, components resolved as reuse) into the Step 15 final-report Skipped block.
Cost ledger — costs.jsonl (coordinator is the single writer)
Specialists cannot meter their own tokens, and parallel builders writing one file would race — so you (the coordinator) are the sole writer of /tmp/figma-<runId>/costs.jsonl. Immediately after each specialist spawn returns, append exactly one line:
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.
- 2d ago First seen · 346 lines · 75 tokens per session scan A c627407f844f
figma-coordinator is an agent published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 13d ago), licensed MIT. It adds 75 tokens to every session and 10,013 once invoked, about $0.0004 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 agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…