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-plugin-apinpx skills add davidomil/cloudx --skill review-plugin-apigit 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 | $0.00024 | $0.00289 |
| Opus 5 | $0.00012 | $0.00144 |
| Sonnet 5 | $0.00005 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
review-plugin-api 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.
What it actually says
Review Plugin API
Responsibility
Review the in-process plugin contract and its server consumers. Findings only; no edits or GitHub mutation.
Run in a fresh context with root instructions, packages/plugin-api, shared
contracts, server registry/hook/trigger consumers, plan, diff and verification.
Lenses
- Contract responsibility belongs in plugin API rather than concrete plugins or shared domain types.
- IDs, descriptors, configuration, actions, hooks, triggers, rules, skills and UI contribution shapes are typed, serializable and runtime-validated at external boundaries.
- Exposure and ownership cannot be widened accidentally or bypassed through a generic call path.
- Additions compose with existing extension points rather than create parallel registration or descriptor shapes.
- Every constructor/converter/consumer is updated; server registry and contribution tests cover the new contract.
- Compatibility impact is explicit. Do not accept a compatibility shim unless the user approved it.
- Do not imply installed GitHub plugin metadata executes third-party code; that install path is metadata-only today.
Output
Produce .agents/schemas/review.schema.json with
subject: "implementation" and reviewer_role: "review-plugin-api".
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 · 38 lines · 24 tokens per session scan A 8367f61f0f6a
review-plugin-api is a skill published in the GitHub repository davidomil/cloudx (1 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 289 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
verify-pr
This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.
coordinate
Coordinate a small team of Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invoke explicitly with /coordinate.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…