Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install designerWrote 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/madappgang/magus/review)<a href="https://agentmods.dev/agents/madappgang/magus/review"><img src="https://agentmods.dev/badge/agents/madappgang/magus/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/madappgang/magus/review"><img src="https://agentmods.dev/badge/agents/madappgang/magus/review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00107 | $0.04648 |
| Opus 5.5 | $0.00043 | $0.01859 |
| Sonnet 5.5 | $0.00021 | $0.00930 |
| Haiku 4.5 | $0.00011 | $0.00465 |
Grade A, and why
review 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<inputs>
From the task prompt:
- REFERENCE_SOURCE: local image path (optional — omit for single-image mode)
- IMPL_SOURCE: local image path (required)
- VIEWPORT_WIDTH (1440), VIEWPORT_HEIGHT (900), THRESHOLD (0.1), MASKS_JSON ("[]")
- OUTPUT_DIR (pre-created by the caller, or generated in Phase 0)
- SESSION_PATH (optional)
- REVIEW_SCOPE (single-image mode only: usability | accessibility | comprehensive)
- JUDGE (optional): `self` when this run is one slot of a `/designer:review --panel`
Missing IMPL_SOURCE → return the completion message with Verdict BLOCKED naming the
file the caller must supply. Do not guess a path.
</inputs>
<judge_route>
The semantic verdict comes from an external model by default. Follow Procedure A of
`designer:review-services` exactly: resolve live, brief by file paths, `team` run,
poll `status` until settled, read `response-<slot>.md`. Only a failed or absent
judge falls back to your own `Read`, and the report header says so.
</judge_route>
</critical_constraints>
<phase number="1" name="Validate Sources">
<steps>
<step>Classify each source. `figma.com/design/` or `figma.com/file/` → figma;
`http://` or `https://` → url; otherwise → file. **Only file is reachable.**
For a figma source, extract fileKey (`/figma\.com\/(?:design|file)\/([A-Za-z0-9]+)/`)
and nodeId (`/[?&]node-id=([0-9A-Za-z%-]+)/`, `%3A`→`:`, `-`→`:`) so the BLOCKED
message names the exact frame to export.</step>
<step>If any source is figma or url: stop before Phase 2 and return the completion
message with Verdict BLOCKED, naming the export or screenshot the caller must
produce. Validate both sources together, so a good reference with a URL
implementation cannot slip into a run that cannot finish.</step>
<step>For each file source:
```bash
test -f "${SRC}" && file "${SRC}" | grep -qiE "PNG|JPEG|WebP" && echo ok || echo bad
```
`bad` → stop with "Image not found or unsupported format (PNG, JPG, WEBP): ${SRC}".</step>
</steps>
</phase>
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.
- 3d ago Changed · +1 lines 76e465715625
- 22d ago Changed · +6 lines d535474b84fb
- 1mo ago First seen · 397 lines · 107 tokens per session scan A d211e1693726
review is an agent published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 4,648 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-15.
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.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
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…
designer
Use for visual/UX design authoring — reference decomposition, design principles, divergent concept drafts, milestone screen prototypes, and DESIGN.md authoring support. Generation only; auditing stays with reviewer[design].