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 alphabravo-oss/guild --skill reviewgit clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/alphabravo-oss/guild/review)<a href="https://agentmods.dev/skills/alphabravo-oss/guild/review"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/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/skills/alphabravo-oss/guild/review"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/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 | $0.00076 | $0.01999 |
| Opus 5.5 | $0.00030 | $0.00800 |
| Sonnet 5.5 | $0.00015 | $0.00400 |
| Haiku 4.5 | $0.00008 | $0.00200 |
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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ux-review:review — Experiential UX Review
You are the product's user, not its author. Reading source is a code review; it verifies correctness. It cannot find experience defects — a mode that doesn't do what its label claims, an overlay anchored to the wrong thing, a feature that works on the default screen and silently breaks on another, a table-stakes affordance that is simply absent. Those are only visible when a person uses the running thing.
Non-negotiable: drive the live app. Treat every "huh?" as a bug. Nothing is out of scope until you have actually used it.
The soul in one line: discover the product, then use it like the person it's for — across every state — and treat every "huh?" as a bug.
Phase 0 — Self-configure (this is what makes the review generic)
Derive everything from the app itself. Assume nothing; hardcode no domain knowledge.
- What it is — explore the entry point, onboarding, and navigation. State the product in one sentence.
- Who uses it — infer 2–4 distinct personas grounded in what the UI actually targets (e.g. first-time visitor, power/returning user, admin, someone on a phone in a hurry, an assistive-tech user). Do not invent lore.
- What it promises — collect every claim the product makes about itself: hero/marketing copy, feature names, mode/tab/toggle labels, tooltips, empty-state text, docs. These become your yardstick — the app is judged against its own promises first.
- Category conventions — what do peer products in this space obviously provide on comparable screens? Absence versus peers is a finding.
Write these down. They drive Phases 2–4.
Phase 1 — Enumerate the surface (this is what makes it thorough)
Build a coverage grid and commit to exercising every cell or logging why it was skipped. Silent truncation ("I checked the main flow") is itself a failure.
- Surfaces: every route, screen, panel, modal, drawer, menu.
- Controls: every button, toggle, field, slider, drag handle, gesture, shortcut.
- States: first-run, empty, loading, partial, success, error, offline, slow-network, permission-denied, unauthenticated, returning-with-data, at/over limits & quotas.
- Variants: every mode / theme / tab / filter / layer / sort — not only the default one. Most breakage hides in the non-default variant.
- Viewports: phone, tablet, desktop, and the awkward in-between; portrait and landscape.
- Input modalities: mouse, keyboard-only, touch, screen reader, reduced-motion, high-contrast / zoom 200%.
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.
- 1mo ago First seen · 101 lines · 76 tokens per session scan A b695cb9e8cc7
review is a skill published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 76 tokens to every session and 1,999 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
webui-code
Use this skill when generating or reviewing WebUI code. This skill contains knowledge on WebUI code following Chrome's Lit-element architecture and styling guidelines.
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
figma-design-review
Critique and review Figma designs to ensure alignment with Chromium codebase components, tokens, and structure. Use when the user asks to critique, review, or audit a design, check alignment with code, or compare a Figma node against component specifications or coding standards.
figma-to-webui
Recreate Figma design frames as production-level Chromium WebUI code following Chrome's Lit-element architecture and styling guidelines. Use when asked to create WebUI code from a Figma frame URL.
figma-to-views-json
Recreate Figma design frames as prototype-ready Chromium Views JSON script following Chrome's native Views architecture, component guidelines, and color/shape token mappings. Use when asked to create C++ Views Prototype JSON script from a Figma frame URL.
figma-to-views
Recreate Figma design frames as production-ready Chromium C++ Views code following Chrome's native Views architecture, component guidelines, and color/shape token mappings. Use when asked to create C++ Views code from a Figma frame URL.