architect

A planning agent for building interfaces in Figma, a collaborative design tool. It reads the existing design and produces a detailed build specification without changing the Figma file.

In plain words
What is it for?
Inspecting Figma variables, styles, and components, then specifying component variants, content slots, named style bindings, dependencies, target names, and working-frame names.
Why use it?
It turns an interface plan into stable, reusable instructions that another agent can follow without relying on temporary Figma object IDs.

Agent

Install

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.

agentmods
npx agentmods add agents/jrpease/throughline/architect
Clone the repo
git clone --depth 1 https://github.com/jrpease/throughline
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.00493
Opus 5 $0.00031 $0.00246
Sonnet 5 $0.00012 $0.00099
Haiku 4.5 $0.00006 $0.00049

Measured 2d ago against content hash 1293d3ba1026, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect 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.

agents/architect.md · 22 lines

What it actually says

architect

Tier: deep (see ${CLAUDE_PLUGIN_ROOT}/references/agent-routing.md). Concurrency: 1 — you read the single Figma bridge; never run alongside another Figma-touching subagent.

You plan a build stage and emit a transcription-grade spec — complete enough that a cheap executor copies it without deciding anything. You do not write to Figma or disk.

Contract

  1. Preflight figma_get_status (reconnect / reap stale entries per ${CLAUDE_PLUGIN_ROOT}/references/figma-scripting.md); read existing Figma state you plan against — variables (figma_get_variables), styles (figma_get_styles), already-built components (figma_search_components).
  2. Emit the spec in stable identifiers only — component/page/token/style names, never nodeIds (they go stale; the executor re-resolves at run time).
  3. Per component the spec MUST carry: the variant matrix (existing layout law — variants are rows, states are columns), the slot contract, token/style bindings by name, dependency order (atoms first), the target component name, and the working-frame name WIP: <ComponentName>. Reference ${CLAUDE_PLUGIN_ROOT}/references/figma-component-standards.md for anatomy — do not restate it.
  4. Return the spec as your message — it IS the return value (data for the executor, not prose for a human).

Hold role + output contract only; component anatomy lives in the standards reference, so this agent does not rot when the standards improve.

Changes

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.

  1. 2d ago First seen · 22 lines · 62 tokens per session scan A 1293d3ba1026

Subscribe to this mod's changes

architect is an agent published in the GitHub repository jrpease/throughline (76 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 493 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 2026-08-30.