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.
git clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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.
[](https://agentmods.dev/commands/skyfox675/agents-skills/figma-init-spec)<a href="https://agentmods.dev/commands/skyfox675/agents-skills/figma-init-spec"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/figma-init-spec.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.00617 |
| Opus 5 | $0.00035 | $0.00309 |
| Sonnet 5 | $0.00014 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
figma-init-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.
What it actually says
/figma-init-spec — snapshot the design system into living specs
Operate in caveman mode (load the
cavemanskill). Keep ids, keys, token values, and mapped code paths byte-exact; spec prose through humanizer.
Arguments: $ARGUMENTS — an optional scope (a page, screen flow, or component set; none = the whole file). A model: token pins the tier (default sonnet).
The figma-specs skill is the protocol — stable-identity anchoring, the spec layout, the Figma MCP tools, and the repo-owned design→code map (Code Connect optional). Consult it first. Figma reads go through the Figma MCP — register the Dev Mode MCP under server key figma so the pre-approved mcp__figma__* tools resolve (plugin installs use mcp__plugin_figma_figma__*; allowlist that prefix if so). If it isn't connected, say so and ask the operator to export the variables/screens instead.
Steps
- Discover the domains (component groups, screen flows) from the file via the Figma MCP — not a fixed list.
- Fan out one
design-mapperagent per domain (parallel, per dispatching-subagents). Each pullsget_variable_defs(andget_code_connect_maponly if Code Connect is already set up) and writes its specs anchored to the node id / component key. To map each component to code, it dispatchesscoutto grep the codebase for the matching component and records thefile:line+ confidence; ambiguous matches are confirmed with the operator. - Write
design-specs/_index.md, set each spec'slast_syncedto the current Figma version / commit, and report: the domain map, plus how many components are mapped to code vs unmapped. Unmapped components make later re-touch lists imprecise —scoutproposes a mapping for each and the operator confirms once.
Run spec prose through the humanizer skill; ids/keys/tokens stay byte-exact.
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.
- 8d ago First seen · 22 lines · 70 tokens per session scan A 4c07ae54a06d
figma-init-spec is a command published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 70 tokens to every session and 617 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 commands, from other repositories
seed-create-component
A command for creating a new SEED Design component, including its source specification, recipes, React implementation, documentation, examples, and optional headless layer.
sddesign
Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes .ui-craft/spec.md. Run when starting a net-new surface from scratch.
craft
One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface ("build me a dashboard", "I need a landing page") and expects a shippable result, not component-level help.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
spec-screenshot
Analyze website screenshots and generate detailed implementation specs.