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/davidomil/cloudx/review-webnpx skills add davidomil/cloudx --skill review-webgit clone --depth 1 https://github.com/davidomil/cloudxWhat 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 | $0.00026 | $0.00297 |
| Opus 5 | $0.00013 | $0.00148 |
| Sonnet 5 | $0.00005 | $0.00059 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
review-web 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 2d 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.
What it actually says
Review Web
Responsibility
Review React/Vite behavior and its browser/server boundary. Findings only; no edits or GitHub mutation.
Run in a fresh context with root and web instructions, shared/API contracts, accepted plan, exact diff, component tests and browser evidence.
Lenses
- Components render/project server state and send explicit commands; they do not duplicate server authorization, path, automation-safety or lifecycle logic.
- Root composition stays readable; reusable transitions move to focused pure modules or controllers.
- Async effects handle stale responses, target stable IDs and clean up timers, sockets, subscriptions, object URLs, terminal views and audio streams.
- Loading, empty, error, reconnect and offline states are coherent.
- Keyboard, pointer and touch workflows remain accessible and equivalent.
- Text fits controls; panes, dialogs, toolbars and fixed-format elements remain stable at desktop and mobile viewports without overlap.
- Existing workbench conventions and Lucide icons are preserved.
- Tests reach user-visible behavior; visible changes include browser validation and desktop/mobile screenshots. A successful build alone is not UX proof.
Output
Produce .agents/schemas/review.schema.json with
subject: "implementation" and reviewer_role: "review-web".
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.
- 2d ago First seen · 36 lines · 26 tokens per session scan A b6dfd45b4f02
review-web is a skill published in the GitHub repository davidomil/cloudx (1 stars, last pushed 9d ago), licensed MIT. It adds 26 tokens to every session and 297 once invoked, about $0.0001 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
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
qwen-code-claw
Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks.
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
new-app
Workflow for creating new applications from scratch. Covers requirements gathering, tech stack selection, scaffolding, implementation, and delivery of a functional prototype.
extension-creator
Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…