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/agentlas-ai/agentlas-desktop/auditnpx skills add agentlas-ai/agentlas-desktop --skill auditgit clone --depth 1 https://github.com/agentlas-ai/agentlas-desktopWrote 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/agentlas-ai/agentlas-desktop/audit)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/audit"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/audit.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 | $0.00032 | $0.00513 |
| Opus 5 | $0.00016 | $0.00257 |
| Sonnet 5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Purpose
Evaluates existing product interfaces and flows through direct step-by-step browser capture, producing an evidence-grounded UX, design, and accessibility audit report.
Preconditions
- The target product URL or interface and the specific user journey (e.g., onboarding, checkout, signup, settings) must be identified.
- Browser capture capability (such as
@agentlas-browseror@playwright) must be available. - Adhere to
$critical-overridesand$design-audit-framework. - Judge what the captures show against
$hig-checklist; when a finding needs a citation, route to the backing guideline with$hig-lookup. For a full guideline-graded review of a surface rather than a journey, hand off to$hig-review.
Steps
- Initialize & Navigate: Open the target flow and wait until the initial screen is fully loaded and visually stable.
- Step-by-Step Capture & Inspection:
- Advance through the user journey one action at a time.
- Capture a clean screenshot at each state and save it sequentially (e.g.,
01-start.png,02-form-filled.png). - Observe visual hierarchy, validation behaviors, loading states, empty states, keyboard focus, and contrast.
- Analyze Findings: For each step, note observed strengths, UX friction points, accessibility risks, and limits of screenshot-only inspection. Grade findings by consequence using the severity scale in
$hig-review-protocol, and state the guideline behind any rule-shaped claim. - Compose Inline Report:
- Assemble an inline markdown report pairing numbered steps directly with their corresponding screenshots.
- Include an executive summary, step-by-step breakdown, top-priority recommendations, and clear evidence limits.
- Optional Figma Board: If explicitly requested by the user, plot the accepted screenshots and notes onto a Figma canvas.
Outputs
- Sequentially saved flow screenshot files.
- Evidence-grounded inline UX and accessibility audit report.
Verification
- Ensure every reported issue and strength is tied 1:1 to an actual captured screenshot.
- Verify that no speculative claims or ungrounded opinions are presented as audit facts.
- Confirm that accessibility assessments clearly state what was visually observed versus what requires automated/screen-reader testing.
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 Changed · +3 lines 5572cc10a1f0
- 5d ago First seen · 34 lines · 32 tokens per session scan A ad30b628c787
audit is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 513 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
create-workspace
Creates a .clave workspace file that defines groups, sessions, terminals, toolbar actions, and icons for the Clave desktop app. Use when the user wants to create, edit, or understand .clave workspace files.
electron-expert
Expert in Electron framework, desktop app development, IPC, and cross-platform packaging. Use when the user mentions desktop, Node.js, cross platform, Windows, macOS, or Linux, or when the task involves Electron Architecture, Process Types, IPC Communication, or App Lifecycle.
recover-sessions
Rebuilds a lost Clave workspace by finding the user's past Claude Code sessions on disk, mapping them to projects, and reopening them as grouped tabs with their full history. Use when the user has lost their tabs or groups (crash, restart, accidental close) and wants their working sessions back, or when they ask what…
ensemblr
How Ensemblr works from inside it — the workspace/git-worktree model, the ensemblr control tools and what their answers mean, the committed .ensemblr/settings.toml (setup and run scripts, [git], [prompts], [infisical], environment variables), /.config/ensemblr/config.json, the Changes panel and diff comments, the…
skills-cli-sync
Sync skills-desktop's AGENTDEFINITIONS and UNIVERSALAGENTIDS with the upstream vercel-labs/skills CLI, then update docs and validate. Use when bumping SKILLSCLIVERSION, mirroring a new upstream skills-CLI release, or when the agent list / universal set drifts from upstream agents.ts.
react-doctor
Use when finishing a feature, fixing a bug, before committing React code, or when the user types /doctor, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.