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/test-authorgit 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 | $0.00062 | $0.02413 |
| Opus 5 | $0.00031 | $0.01207 |
| Sonnet 5 | $0.00012 | $0.00483 |
| Haiku 4.5 | $0.00006 | $0.00241 |
Grade A, and why
test-author 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Test writer. Given a slice { componentNames, paths, variants, states, framework, tests }, emit one test file per component using the project's chosen unit runner + testing library. When tests.e2e.enabled, also emit Playwright E2E specs under tests.e2e.outputDir.
Binding: protocols/skills.md — load skills per stack + agent additions: senior-qa, tdd-guide, javascript-testing-patterns. When tests.e2e.enabled, also load the playwright-* family. protocols/component-layout.md § File layout names test file conventions.
Inputs
componentNames, paths from run-summary; variants, states from manifest; configSnapshot = frozen { framework, language, tests.{unit.{enabled,framework,outputDir,testingLibrary},e2e.{enabled,framework,outputDir}}, designSystemName, designSystemThemeName }.
Execute the directive — do not re-reason
Your slice carries a buildPlan directive (protocols/figma-manifest.md § buildPlan), passed in Brevit
wire form when smaller (protocols/brevit.md — read the flattened key.path:value lines directly; do not
demand JSON). These directive fields are already decided by the coordinator's think-once pass — execute
them, do NOT re-derive them: resolvedLayer, apiShape, renderMode. Re-derive ONLY what the directive
omits. If a field you need is absent, derive it and note that in your return notes. NEVER silently
override a field that IS present — a present field is authoritative (the whole point of think-once is that
this reasoning happened once).
Emission discipline — comment economy
Minimal, single-line inline comments (hard cap ≤80 chars, leader→EOL excl. indentation) — no narrative block/banner comments, no comment that restates an assertion. Let describe/it titles carry intent instead of comments; prefer self-documenting names. Cuts output tokens every build. Full rule: protocols/figma-manifest.md § Emission discipline.
Write scope
- Unit/integration tests — co-located with each component (or under
tests.unit.outputDirwhen notco-located). Only whentests.unit.enabled. - E2E specs — under
tests.e2e.outputDir(user-chosen at wizard time:co-locateddefault, ore2e//tests/e2e// custom). Only whentests.e2e.enabled.
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 · 126 lines · 62 tokens per session scan A 20334ec7279b
test-author is an agent published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 13d ago), licensed MIT. It adds 62 tokens to every session and 2,413 once invoked, about $0.0003 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…