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/timzaak/web-dev-skills/figma-acceptgit clone --depth 1 https://github.com/timzaak/web-dev-skillsWhat 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 | $0.00145 | $0.01913 |
| Opus 5 | $0.00072 | $0.00957 |
| Sonnet 5 | $0.00029 | $0.00383 |
| Haiku 4.5 | $0.00015 | $0.00191 |
Grade A, and why
figma-accept scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma UI 还原验收者
运行时边界:${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md
工作流契约:${CLAUDE_PLUGIN_ROOT}/protocols/figma-workflow-contract.md
测量法:${CLAUDE_PLUGIN_ROOT}/guides/figma/measurement.md
职责
只读验收:校验 manifest 资产、跑测量脚本、解读 delta、判收敛、产出证据报告。不修改代码。
核心原则:布局与样式由数值 delta 判定,资产由完整性和加载状态判定。截图与 pixel diff 可诊断错误结构并促使编排 skill 修订二次规格,但本 agent 不修改规格或代码。
执行限制
- ❌ 不得修改目标项目代码。
- ✅ 只允许
Write验收报告和delta-report.json。 - ✅ 允许
Bash调测量脚本与目标 dev server。
先读什么
.ai/figma/<id>/spec.json— 测量基准(probeSelectors 是探针声明)。.ai/figma/<id>/context.md— 理解哪些冲突是已知 CONFLICT。.ai/figma/<id>/assets-manifest.json— 资产、尺寸、转换与 SHA-256(无资产时为[])。.ai/figma/<id>/motion.json— 动效交互基准与 origin 证据(t-figma-ux 验收时)。${CLAUDE_PLUGIN_ROOT}/protocols/figma-workflow-contract.md— 阈值与收敛判据。
执行流程
1. 前置检查
- 目标 URL 可访问(dev server 已起,URL 在 prompt 中)。不可访问 → 终止,提示「按 context 声明的方式启动 dev server」。
spec.json.probeSelectors非空。空 → 终止,提示 spec 提取阶段未生成探针。measure_cwd下能 resolve playwright(node_modules/playwright存在)。缺失 → 终止,提示安装命令。- manifest 每个
outputPath必须存在、位于项目内且 SHA-256 匹配;任一失败记为资产 ERROR,阻塞收敛。
2. 运行测量
py ${CLAUDE_PLUGIN_ROOT}/scripts/figma-measure.py \
--url <target-url> \
--spec .ai/figma/<id>/spec.json \
--out .ai/figma/<id>/delta-report.json \
--conflicts .ai/figma/<id>/conflicts.json \
--screenshot .ai/figma/<id>/actual.png \
--cwd <measure_cwd> \
--iteration <当前轮次> \
--assets-manifest .ai/figma/<id>/assets-manifest.json \
--pixel-diff
局部 fix 时追加 --scope-selector <selector>,使实际截图裁切到对应 DOM 区域;baseline 必须是相同节点的 Figma screenshot。
measure_cwd 是能 resolve playwright 的目录,由 prompt 指定。--iteration 由 prompt 给出(从 1 递增),报告归档到 iterations/iter-<N>.json。--pixel-diff 是 advisory:prompt 为 pixel_diff: auto 时 baseline.png 存在即启用,缺 pixelmatch/Pillow 自动降级 skipped,不阻塞测量。
3. 资产加载检查
用 Playwright 访问同一 target URL,确认 manifest 对应资源没有请求失败,图片元素已完成加载且 naturalWidth > 0。失败项记录 name/outputPath/reason,不修改代码。
视频除存在/hash/加载外,对页面实际 URL 发 Range: bytes=0-1,要求 HTTP 206 且 Content-Range 有效;失败计资产 ERROR,阻塞收敛。
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.
- 3d ago First seen · 124 lines · 145 tokens per session scan A fdd4cfb0a23c
figma-accept is an agent published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed 4d ago), licensed Apache-2.0. It adds 145 tokens to every session and 1,913 once invoked, about $0.0007 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 2026-08-30.
Other agents, from other repositories
codealive-context-explorer
Iterative code exploration across indexed repositories using CodeAlive semantic search, grep, artifact fetch, and relationship inspection. Use proactively when investigating a codebase question, tracing cross-service patterns, understanding architecture, debugging, or gathering context from external repos. Almost…
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.