figma-refresh-spec

figma-refresh-spec is a command for Claude Code from skyfox675/agents-skills. It costs 82 tokens per session (580 once invoked), scanned A, original, MIT.

A command that checks whether saved Figma design specifications still match the current Figma file. It identifies changes by stable design IDs and links them to code locations.

In plain words
What is it for?
Use it after a Figma file or design has moved, or after designs change, to find altered tokens, sizes, states, added items, and removed items within an optional scope.
Why use it?
It helps separate harmless file reorganization from changes that require code updates, so moved designs do not create unnecessary work.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it after a Figma file or design has moved, or after designs change, to find altered tokens, sizes, states, added items, and removed items within an optional scope.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/skyfox675/agents-skills/figma-refresh-spec
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.

Clone the repo
git clone --depth 1 https://github.com/skyfox675/agents-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for figma-refresh-spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/skyfox675/agents-skills/figma-refresh-spec.svg)](https://agentmods.dev/commands/skyfox675/agents-skills/figma-refresh-spec)
Your own site
<a href="https://agentmods.dev/commands/skyfox675/agents-skills/figma-refresh-spec"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/figma-refresh-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 580 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00082 $0.00580
Opus 5 $0.00041 $0.00290
Sonnet 5 $0.00016 $0.00116
Haiku 4.5 $0.00008 $0.00058

Measured 8d ago against content hash 80c2f23c0901, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

figma-refresh-spec 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 8d 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.

.claude/commands/figma-refresh-spec.md · 23 lines

What it actually says

/figma-refresh-spec — detect design drift and produce a re-touch list

Operate in caveman mode (load the caveman skill). Keep ids, keys, token deltas, and mapped code paths byte-exact; spec prose through humanizer.

Arguments: $ARGUMENTS — an optional scope (a page, flow, component set, or id; none = all specs whose source changed or are stalest). A model: token pins the tier (default sonnet).

The figma-specs skill is the protocol; this is its drift pass. Consult it first.

Steps

  1. Read the existing specs in scope (from design-specs/_index.md). A refresh is a resume — read before changing anything.
  2. Re-pull each via the Figma MCP and diff by stable id: get_variable_defs for token/property values; the code target comes from the spec's repo-owned code: map (re-run scout if the mapped file has moved). Classify per the figma-specs skill — moved/reorganized, renamed, changed, added, removed, code-moved.
  3. Update specs in place: for moves, update only the locator (no code change); for changes, record the before→after delta + the mapped code path; append new ids (with a scout-proposed mapping); deprecate removed ones. Never re-key.
  4. Re-sync _index.md and report two lists: "reorganization only — ignore" and "real changes — re-touch" (each delta with its code file). The second list is what the team acts on; /gh-issue-recon or /dispatch can pick it up to file or fix.

Run any rewritten prose through the humanizer skill; ids/keys/deltas stay byte-exact.

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. 8d ago First seen · 23 lines · 82 tokens per session scan A 80c2f23c0901

Subscribe to this mod's changes

figma-refresh-spec is a command published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 82 tokens to every session and 580 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.