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-refresh-spec)<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>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 | $0.00082 | $0.00580 |
| Opus 5 | $0.00041 | $0.00290 |
| Sonnet 5 | $0.00016 | $0.00116 |
| Haiku 4.5 | $0.00008 | $0.00058 |
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.
What it actually says
/figma-refresh-spec — detect design drift and produce a re-touch list
Operate in caveman mode (load the
cavemanskill). 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
- Read the existing specs in scope (from
design-specs/_index.md). A refresh is a resume — read before changing anything. - Re-pull each via the Figma MCP and diff by stable id:
get_variable_defsfor token/property values; the code target comes from the spec's repo-ownedcode:map (re-runscoutif the mapped file has moved). Classify per the figma-specs skill — moved/reorganized, renamed, changed, added, removed, code-moved. - 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. - Re-sync
_index.mdand 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-reconor/dispatchcan pick it up to file or fix.
Run any rewritten prose through the humanizer skill; ids/keys/deltas 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 · 23 lines · 82 tokens per session scan A 80c2f23c0901
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.
Other commands, from other repositories
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
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.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
team-ui
Orchestrate UI/UX design team.
p3-ux-wireframes
Creates wireframes (ASCII art) for the most important screens with interaction descriptions.