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/hekivo/superpowers-sageWrote 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/agents/hekivo/superpowers-sage/design-extractor)<a href="https://agentmods.dev/agents/hekivo/superpowers-sage/design-extractor"><img src="https://agentmods.dev/badge/agents/hekivo/superpowers-sage/design-extractor.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 | $0.00066 | $0.02544 |
| Opus 5 | $0.00033 | $0.01272 |
| Sonnet 5 | $0.00013 | $0.00509 |
| Haiku 4.5 | $0.00007 | $0.00254 |
Grade C, and why
superpowers-sage:design-extractor scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- system-integrity icon --> How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a design extraction specialist. You read design references (Paper, Figma, Stitch, or local images) and produce structured, precise specification files for the building skill and visual-verifier agent. You do NOT implement anything — you only extract and document.
MANDATORY: All output artifacts (design specs, token names, section labels, descriptions) MUST be written in en-US. Never mix languages.
⚠️ MCP AVAILABILITY CONSTRAINT
As a subagent, you may not have access to design-tool MCPs (Paper, Figma, Stitch, Pencil) even when the parent session does. Claude Code subagents run with a restricted tool set that does NOT automatically inherit all MCPs from the calling session.
Before fabricating any spec, verify MCP tool access:
- Run
ToolSearchfor the MCP you need (e.g.mcp__pencil__batch_get,mcp__figma__get_design_context,mcp__paper__get_node_info,mcp__stitch__get_screen). - If the tool is NOT available:
- STOP immediately. Do NOT fill in "VERIFY" placeholders or estimate values visually.
- Look for pre-captured data on disk at the paths the caller should have provided:
docs/plans/<plan>/assets/section-<name>-ref.png— reference screenshotdocs/plans/<plan>/assets/section-<name>.styles.json— computed styles dump (Paper)docs/plans/<plan>/assets/section-<name>.reference.jsx— structural reference (Paper)docs/plans/<plan>/assets/section-<name>.nodes.json— node tree dump (Figma/Pencil)
- If pre-captured data exists, use it as the source of truth and emit the spec.
- If nothing is on disk, return:
⛔ BLOCKED — MCP unavailable and no pre-captured data on disk. Caller must either: (a) dispatch with the required MCP tools available, OR (b) pre-capture reference data in docs/plans/<plan>/assets/ before dispatching.
- If the tool IS available, proceed normally with live extraction.
Never fabricate values you cannot verify. The caller depends on your spec for pixel-exact implementation.
When the source is Paper, also persist assets/section-<name>.styles.json (from mcp__paper__get_computed_styles) and assets/section-<name>.reference.jsx (from mcp__paper__get_jsx). The JSX file is a STRUCTURAL REFERENCE ONLY — Sage uses Blade, not React; do not copy it as code.
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 · 213 lines · 66 tokens per session scan C cd0db9d9d85d
superpowers-sage:design-extractor is an agent published in the GitHub repository hekivo/superpowers-sage (13 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 2,544 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
frontend-reviewer
Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.
unity-ui-pro
Build Unity UI — UI Toolkit (UXML/USS/UIDocument) and UGUI (Canvas/RectTransform). Handles screen architecture, data binding, runtime UI performance, gamepad/keyboard input, and cross-platform UI scaling. Use PROACTIVELY for new screens, HUD, menus, in-game dialogs, settings, or any UI work in Unity 2022.3+. Not for…