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-changenpx skills add davidomil/cloudx --skill review-changegit clone --depth 1 https://github.com/davidomil/cloudxWrote 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/davidomil/cloudx/review-change)<a href="https://agentmods.dev/skills/davidomil/cloudx/review-change"><img src="https://agentmods.dev/badge/skills/davidomil/cloudx/review-change.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 | $0.00022 | $0.00360 |
| Opus 5 | $0.00011 | $0.00180 |
| Sonnet 5 | $0.00004 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
review-change 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 4d 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 Change
Responsibility
Produce the aggregate implementation verdict from current source evidence and fresh policy-selected reviews. Do not edit code, fix findings, rerun verification, or mutate GitHub.
Inputs
- Original task and trusted instructions.
- Accepted plan and implementation artifacts.
- Passed verification artifact for the same head.
- Current base-to-head diff.
- One fresh review artifact from every skill selected by policy.
Do not receive the implementation conversation. Confirm each area reviewer was selected by the current path classification and that every artifact matches the same policy digest, subject and head.
Gate
- Trace every behavioral claim from production entry to changed seam and test.
- Reconcile findings by stable ID and evidence, not by prose similarity.
- Preserve the highest supported severity when reviewers disagree.
- Preserve the union of every area-review tag. Add
manual-reviewwhen the actual path classification is human-required or this exact head needs a maintainer decision despite having no blocking finding. - Treat missing, stale, malformed or contradictory review evidence as a process finding.
- A model assertion cannot override deterministic verification or an unresolved area finding.
Output
Produce JSON matching .agents/schemas/review.schema.json with
subject: "implementation" and reviewer_role: "review-change". A clean
verdict requires zero findings across the aggregate.
Always emit tags; use [] only when no durable disposition applies.
Findings return to a fresh implementer. The resulting head must be reverified and reviewed by all selected reviewers. An iteration ceiling blocks the change.
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.
- 4d ago First seen · 48 lines · 22 tokens per session scan A 1db985b2228f
review-change is a skill published in the GitHub repository davidomil/cloudx (1 stars, last pushed 11d ago), licensed MIT. It adds 22 tokens to every session and 360 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
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.
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.
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…
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.