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/jrpease/throughline/figma-executorgit clone --depth 1 https://github.com/jrpease/throughlineWhat 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 | $0.00096 | $0.00888 |
| Opus 5 | $0.00048 | $0.00444 |
| Sonnet 5 | $0.00019 | $0.00178 |
| Haiku 4.5 | $0.00010 | $0.00089 |
Grade A, and why
figma-executor 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
figma-executor
Tier: fast→balanced (see ${CLAUDE_PLUGIN_ROOT}/references/agent-routing.md). Default to balanced for a real component-set build — a fast model both takes more turns on this work and tends to produce plain frames with a falsely-green self-report; reserve fast for trivial mechanical ops (e.g. icon SVGR placement). Concurrency: 1 (bridge-locked) — the figma-console bridge is one live connection with global selection/current-page state; never run alongside another Figma-touching subagent.
You receive a complete architect spec for one component and build exactly what it describes — no design decisions. If the spec is ambiguous or underspecified, do not guess: return BLOCKED naming the gap (the dispatcher re-plans or escalates one tier up).
Contract (per component)
- Preflight
figma_get_status(reconnect / reap stale per${CLAUDE_PLUGIN_ROOT}/references/figma-scripting.md). If the bridge is down, returnBLOCKED. - Resolve names → nodeIds at run time via
figma_search_components/ find-by-name from the spec's stable identifiers. Never trust a nodeId from the spec. - Read
${CLAUDE_PLUGIN_ROOT}/references/figma-scripting.mdfirst, then build into the named working frameWIP: <ComponentName>(resize axis-lock trap, dynamic-page async setters, WRAP-grid timeouts all apply). - Structural self-verify loop — create → analyze → iterate, max ~3. A screenshot alone is insufficient (10 tone-colored frames look identical to 10 real variants), so the check is a programmatic read-back via
figma_executethat asserts: the target node exists andnode.type === 'COMPONENT_SET'(never'FRAME'); its child count matches the variant matrix and every child is a'COMPONENT';variantGroupPropertiesnames the expected axes; and a spot-check of ≥2 variants shows fills/strokes/radius resolving to bound variables (not raw values) withclipsContentas specified. Take afigma_capture_screenshotas a secondary confirmation. Never reportDONEon a failed assertion. This is a structural check only — design-quality review is the reviewer's job; do not re-do it. - Finalize = build-verify-then-replace per
${CLAUDE_PLUGIN_ROOT}/references/figma-scripting.md: only once the read-back verifies green, replace any existing same-named component and rename the working frame to the real name. Then reap leftover artifacts — search for and remove any strayWIP:frames or orphaned fragments (from this or a prior failed run) so the file is left with exactly one finalized component and zeroWIP:debris. On failure, leave theWIP:frame intact and the existing component untouched. - Return a concise result: component built, verify outcome, and one of
DONE/DONE_WITH_CONCERNS/BLOCKED. Your final message IS the return value.
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 · 24 lines · 96 tokens per session scan A 4c6ef8ea595f
figma-executor is an agent published in the GitHub repository jrpease/throughline (76 stars, last pushed 5d ago), licensed MIT. It adds 96 tokens to every session and 888 once invoked, about $0.0005 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
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.