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 agentmods add skills/rustfs/console/ui-auditnpx skills add rustfs/console --skill ui-auditgit clone --depth 1 https://github.com/rustfs/consoleWhat 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 | $0.00097 | $0.02661 |
| Opus 5 | $0.00048 | $0.01331 |
| Sonnet 5 | $0.00019 | $0.00532 |
| Haiku 4.5 | $0.00010 | $0.00266 |
Grade A, and why
ui-audit 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 yesterday.
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Audit
Operating Mode
Treat the request as implementation work unless the user asks for analysis only. Read local instructions first, preserve unrelated changes, and keep edits surgical. Do not create project summary documents or reports unless explicitly requested.
In this repository, read skills/rustfs-console-design-guide/SKILL.md before auditing or changing Console UI. Use that guide as the source of design decisions; use this skill for audit execution, browser validation, evidence capture, and verification.
If the user asks to pull latest, do it before editing after checking git status. If local unrelated work is present, preserve it and avoid destructive git commands.
Classify The Surface
Before scanning, identify the primary UI type and adjust emphasis:
- Operational apps: prioritize density, tables, forms, keyboard flow, data states, batch actions, and predictable navigation.
- Landing/product sites: prioritize first viewport, real visual assets, responsive hero composition, contrast, content hierarchy, and scroll rhythm.
- Developer/docs sites: prioritize reading flow, code block overflow, navigation state, search, anchors, and dark theme.
- Interactive tools/games: prioritize canvas/scene nonblank state, controls, motion, hit targets, and viewport fit.
- Component libraries/migrations: prioritize primitive usage, wrapper boundaries, design tokens, API consistency, and regression patterns.
Baseline
- Read project guidance: local instructions, package scripts, existing component patterns, theme config, and design-system conventions.
- Prefer existing wrappers and utilities. Do not edit base UI primitives directly unless explicitly required; fix usage sites or create wrappers.
- Start or reuse the local dev server. Use Docker Compose only when the app needs it.
- Fetch current UI guidance when available, especially:
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md
- Define target flows: first screen, navigation shell, forms, dialogs, tables/lists, media, upload flows, theme switch, and one mobile breakpoint.
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.
- yesterday First seen · 144 lines · 97 tokens per session scan A f33639e6f9f3
ui-audit is a skill published in the GitHub repository rustfs/console (169 stars, last pushed 3d ago), licensed Apache-2.0. It adds 97 tokens to every session and 2,661 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
rustfs-release-publish
Run the end-to-end RustFS console gate, version bump, preview validation, human confirmation, and final-tag publication pipeline. Use only when the user explicitly asks to release or publish a RustFS version (发版/发布).
rust-code-quality
Run a focused Rust quality review when the user requests one, when reviewing a Rust PR/commit, or when another selected review workflow delegates Rust-specific checks. Do not auto-load for every implementation edit.
pr-review
Review a GitHub PR end-to-end from a URL or number — fetch metadata, inspect the diff, run multi-role adversarial review, check CI status, and post the review comment. Use when the user provides a PR link and asks to review it.
issue-triage
Triage a GitHub issue — determine if it is already fixed, needs implementation, or should be closed. Searches related commits and PRs, verifies implementation status, and posts a triage comment or closes the issue. Use when the user provides an issue URL and asks whether it can be closed or needs work.
security-advisory-lessons
Perform a dedicated RustFS security/advisory review for authn/authz, IAM, RPC trust, paths, secrets, browser isolation, encryption, Object Lock, or other security boundaries. Use only when the user requests a security/advisory review or an adversarial review explicitly escalates to the full advisory map; do not…
tier-debug
Debug ILM tiering / lifecycle transition issues — NoSuchVersion on tier GET, restore failures, xl.meta inspection, remote-tier versionId tracing. Use when investigating tiered/transitioned objects, warm backends, or transition metadata.