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 skills add yugasun/aiops --skill reviewgit clone --depth 1 https://github.com/yugasun/aiopsWrote 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/yugasun/aiops/review)<a href="https://agentmods.dev/skills/yugasun/aiops/review"><img src="https://agentmods.dev/badge/skills/yugasun/aiops/review.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 5.1 | $0.00050 | $0.01513 |
| Opus 5 | $0.00025 | $0.00757 |
| Sonnet 5 | $0.00010 | $0.00303 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
review 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
Three modes. Each mode has its own inputs, axes, and output artifact. Do not mix modes in one file.
Mode selection
| Mode | Trigger | Agent | Output |
|---|---|---|---|
| code | delivery sub-phase, user asks to review diff/PR |
code-reviewer | .scratch/<slug>/REVIEW.md |
| design | design_review phase, user asks to review design |
design-reviewer | .scratch/<slug>/DESIGN_REVIEW.md |
| drift | drift_check phase (after delivery, before ship) |
design-reviewer | .scratch/<slug>/DRIFT_REPORT.md |
When unsure: Flow Conductor phase name wins. Direct invocation defaults to code unless the user names design or drift.
Code mode
Review git diff <fixed-point>...HEAD:
- Standards — matches repo coding standards?
- Spec — matches originating issue/PRD?
- Constitution (optional) — when
CONSTITUTION.mdexists at repo root, violates any non-negotiable principle?
Run /aiops-setup if docs/agents/issue-tracker.md is missing.
Process
- Pin fixed point — commit, branch, tag, or
main. Confirm ref resolves and diff is non-empty. - Find spec — issue refs in commits (
docs/agents/issue-tracker.md), user path, ordocs//.scratch/PRD. No spec → Spec axis skips. - Find standards —
CODING_STANDARDS.md,CONTRIBUTING.md, etc. - Find constitution —
CONSTITUTION.mdat repo root. Missing → Constitution axis skips. - Parallel sub-agents — one per active axis. Each under 400 words, cite sources.
- Aggregate — one section per axis verbatim. One-line summary per axis; don't merge axes.
A change can pass one axis and fail another — keep axes separate.
Output: REVIEW.md
# Code Review: <feature-slug>
## Summary
<overall assessment>
## Design Alignment
- [ ] 实现符合 NOTES.md 设计决策
- [ ] 接口符合 tech-spec.md 规格
- [ ] 无超出 scope 的变更
## Findings
### Blocking (必须修复)
#### B1: <file:line> — <title>
- **问题**: …
- **建议**: …
### Non-blocking (建议改进)
#### N1: <file:line> — <title>
- **问题**: …
- **建议**: …
## Verdict
**APPROVE** | **REQUEST_CHANGES**
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.
- 8d ago First seen · 190 lines · 50 tokens per session scan A 4a22985296e1
review is a skill published in the GitHub repository yugasun/aiops (4 stars, last pushed 19d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,513 once invoked, about $0.0003 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
hashiiiii-pull-request
Use this skill to create or edit a GitHub pull request with the repository template or the default structure.
pr-review
Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…
review
Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence (file:line or source); unverifiable ones are flagged.…
review
Uses a fresh agent to review an implementation change without editing it. Checks behavior, security, regressions, complexity, tests, docs, and missing proof. Use for code, PR, diff, security, second-opinion, or pre-merge reviews.
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.
winui-code-review
Code quality review for WinUI 3 apps — MVVM compliance, x:Bind correctness, accessibility, theming, security, and performance. Use before committing to catch issues that the compiler and UI tests won't find.