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.
npx skills add arcasilesgroup/ai-engineering --skill ai-review-uigit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/skills/arcasilesgroup/ai-engineering/ai-review-ui)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-review-ui"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-review-ui/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/skills/arcasilesgroup/ai-engineering/ai-review-ui"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-review-ui.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 | $0.00103 | $0.02156 |
| Opus 5.5 | $0.00041 | $0.00862 |
| Sonnet 5.5 | $0.00021 | $0.00431 |
| Haiku 4.5 | $0.00010 | $0.00216 |
Grade A, and why
ai-review-ui scanned grade A 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 19d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Run `curl -s -o /dev/null -w '%{http_code}' <web URL>` (Project config → *Web URL*). If nothing answers, run the *Dev server* command from the repo root in the background and wait until it responds. How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review UI against prototype
This skill runs in one of two modes. Work out which one you're in first.
- Standalone (a human ran
/ai-review-ui): run steps 1–5. The output is a findings report. Don't fix anything; step 5 ends by offering fixes, and fixing happens only if the user accepts. - Gate (
/ai-orchestratorGate 2): run steps 2–4 only, with the checkpoint'sui.scope. Before capturing, check thatroutein.ai-engineering/workflow/prototypes/<name>.states.jsonequals the checkpoint'sui.route; if not, fix the scenario file to useui.route, since the capture script only reads the scenario. ReturnPASSorFAILand the merged findings to the orchestrator. Never offer or apply fixes; failures go through the orchestrator's failure path. The gate passes when every in-scope, live-reproducible state ismatchand there are nohighormedfindings, other than ones tagged[intentional?].
1. Resolve the pair
- Prototype:
.ai-engineering/workflow/prototypes/<name>.html. Match it from the request; if more than one could fit, ask. - Live route: the page that implements it (see
FILEMAP.md, and Project config → Pages inAGENTS.md, which says where signed-in and public pages live). Public pages don't need the saved sign-in session. - Source files: that route's page file, plus any components it uses (Project config → Components).
If the route isn't obvious from the prototype name, send an Explore subagent to find the page that implements it and its component files. Have it return only the paths.
2. Make sure the app is reachable
- Run
curl -s -o /dev/null -w '%{http_code}' <web URL>(Project config → Web URL). If nothing answers, run the Dev server command from the repo root in the background and wait until it responds. - Signed-in pages need a saved session. If
.ai-engineering/workflow/playwright/auth.jsonis missing, stop and ask the user to run the command below, sign in, and close the window:! npx -y playwright codegen --save-storage=.ai-engineering/workflow/playwright/auth.json <web URL><sign-in path>.ai-engineering/workflow/playwright/is gitignored. If the screenshots come back showing the login page, the session has expired; ask the user to run the same command again.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 19d ago First seen · 111 lines · 103 tokens per session scan A d27fa0e0c58f
ai-review-ui is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 103 tokens to every session and 2,156 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.
Other skills, from other repositories
skill-pages
AL page design patterns for Business Central. Use when creating Card, List, ListPart, Document pages, implementing page extensions, or designing UX layouts.
apex-python-diagrams
UTILITY SKILL — Python diagram generation for Azure architectures, WAF/cost/compliance charts, ERDs, swimlanes, timelines, and wireframes. WHEN: 'architecture diagram', 'WAF bar chart', 'cost chart', 'ERD', 'swimlane', 'timeline', 'wireframe'. DO NOT USE FOR: inline Mermaid diagrams (apex-mermaid).
figma-code-connect-components
Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma designs and code implementations. For…
figma-create-design-system-rules
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server…
design-assessment
WHAT - Evidence-based design-unit assessment orchestrated by project-assessment. Evaluates visual hierarchy, UX friction, interaction, a11y, responsiveness, design-system compliance, and distinctiveness with severity/confidence evidence citations. Reuses project-assessment-evidence semantics — no second framework.
design-improvement
WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.