omd-review

omd-review is a skill for Claude Code, Codex from AbyssCN/oh-my-dag. It costs 101 tokens per session (1,517 once invoked), scanned A, original, MIT.

A structured review of code changes that looks for correctness, security, missing requirements, and edge cases. It can review everything changed in the current branch or a selected part of the codebase.

In plain words
What is it for?
Use it for routine code reviews, large changes, sensitive changes, and deeper reviews that read the whole codebase and test claims about libraries or runtime behavior.
Why use it?
It helps find problems before release, especially in changes that affect data structures, authentication, security boundaries, or actions that cannot easily be undone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for routine code reviews, large changes, sensitive changes, and deeper reviews that read the whole codebase and test claims about libraries or runtime behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abysscn/oh-my-dag/omd-review
Install

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.

Any agent
npx skills add AbyssCN/oh-my-dag --skill omd-review
Clone the repo
git clone --depth 1 https://github.com/AbyssCN/oh-my-dag

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for omd-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-review/github.svg)](https://agentmods.dev/skills/abysscn/oh-my-dag/omd-review)
Your own site
<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-review"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for omd-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-review"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,517 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00101 $0.01517
Opus 5 $0.00051 $0.00758
Sonnet 5 $0.00020 $0.00303
Haiku 4.5 $0.00010 $0.00152

Measured 11d ago against content hash f51ba98022f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

omd-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 11d 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.

client-skills/omd-review/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/omd-review — 对抗式改动审查

经 omd MCP dag_review(可能带 mcp__omd__ 前缀;未加载先 ToolSearch "dag_review")对一批改动做对抗审查:默认多维并行 find(召回)+ 确定性跨模型 verify(证伪);deep 档单 agent 读全仓 + 实测(实测最优,见档位选择)。

用法(异步三段式)

  • gate:按 blast radius 选,不按行数(真源 harness/docs/GATES.md,与引擎 scripts/dag-review.ts 逐档一致)。不给 = G2。

    gate 什么改动 实际跑什么
    G0 文档 / 机械(注释、配置、纯改名、格式) 免审短路——不取 diff、不发模型、直接 exit 0。它不是"便宜的浅扫",是"不审";要便宜的召回选 G1
    G1 骨架(新模块脚手架、签名、接线) contract + boundary 两维
    G2 常规逻辑(普通业务码、带行为测试的重构) correctness + security + boundary 三维
    G3 敏感:schema · 认证 · 安全边界 · 不可逆 G2 三维 + contract + spec 轴强制(对照 SDD,--no-spec 在 G3 直接报错)+ owner 终审

    轮数硬上限:G1/G2 各 1 轮,G3 = 1 轮 + 至多 1 个修复 cycle。

  • scope:收窄审查范围(路径/模块);不给 = 当前 branch diff 全量。

  • deep:深审档(true)。一个 pi agent 读全仓 + 实测(库/runtime API 主张必跑 bun -e 复现,治外部 API 幻觉)→ 确定性跨模型 verify。比默认贵,但精度更高、自然去重

  1. dag_review(gate?, scope?, deep?)runId;
  2. dag_status(runId) 轮询(跑几分钟,别重复发起);
  3. dag_result(runId)报告落盘路径,自己 Read 再转述(按严重度先讲 top 项)。

档位选择:默认 vs 深审(deep)

  • 默认(多维并行 find + 确定性 verify):廉价召回档,diff-可见的 bug 够抓,适合日常/大 diff。
  • 深审 deep:true(单 agent):实测最干净(3 方召回测:满召回 + 0 假阳性 + 推理最好 + 自然去重)。用于敏感接缝(会计/authz/迁移/状态机)、需读 diff 外真身、或默认档出噪音时。贵在一个 agent 全仓读+跑,别对大批量机械 diff 滥用。
  • 模型(review 自成体系,不碰引擎 verifier 角色):find = review 角色(OMD_REVIEW_MODEL);verify = OMD_REVIEW_VERIFY_MODEL 覆盖,否则回落 find 模型(跨模型 verify 靠显式配 OMD_REVIEW_VERIFY_MODEL)。无需任何配置也能跑,fallback 优雅降级、不假设 key。

误报裁决程序(承终裁手册:finding ≠ ground truth)

车队产出是候选,你终裁。每条 finding:

  1. 定位代码事实——必须看 diff 视野外(审查器只看 diff,这是误报主源)。
  2. oracle 证伪:typecheck / 测试 / 活库实测 / 既有测试钉。
  3. 证伪成立 → 驳,记驳的依据;证伪不了 → 修;拿不准 → ? 升级 owner。

已知误报模式(直接警惕):

  • 「X 未导出/未定义」而 X 是 diff 外既有代码(ugrep 确认真身,build 绿即证伪)。
  • 「缺权限守卫」而守卫以 JOIN/EXISTS 已在查询里(空集测试即证伪)。
  • 用「可能/如果内部没校验」推测行为——去读那个函数,不接受推测性 P0。

gate 分档:插在 ROI 高处,别铺满(承终裁手册)

审核 ROI = P(缺陷) × 逃逸代价 ÷ 成本。

  • P(缺陷)高 = 机械铺量 / 敏感接缝(会计写·状态机·迁移)/ 大 diff。
  • 逃逸代价高 = 账面污染 / 绕审计——错了是灾难,再贵也审(上 G3)。
  • ROI 决定的是审不审、审多深;分档轴仍是 blast radius——骨架接线 + typecheck/test 全绿 → G1 够,别 G3。 但别拿 G0 当"小改的便宜档":G0 = 不审,只对文档/机械改动成立。
  • 0 P0/P1 ≠ 白审,可能是"插错位置"信号:过程审(写码前判定)> 结果审(post-code gate)。

Read the full file on GitHub · 58 lines

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.

  1. 11d ago First seen · 58 lines · 101 tokens per session scan A f51ba98022f9

Subscribe to this mod's changes

omd-review is a skill published in the GitHub repository AbyssCN/oh-my-dag (39 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 1,517 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

control-center-review

Review one captured Control Center build before runtime activation.

openonion/connectonion · 14 tokens

review-pr

Review GitHub pull requests. Use when user says "review PR", "review pull request", or "/review-pr".

openonion/connectonion · 27 tokens

codex

Delegate coding work to the OpenAI Codex CLI for repository changes, reviews, and focused fixes.

Open-Curiosity/gini-agent · 23 tokens

spawn-reviewers

Spawn and collect the reviewer fleet at stage20spawnreviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves CODEINTELALLOWED, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified Auditor, Domain Critics, Impact…

closedloop-ai/claude-plugins · 184 tokens

singleton-dispatch

PLN-725 single-agent dispatch for stage11extractsignals and stage15coveragecritic. After each prepare stage writes its manifest, this skill reads the status field (cachehit / skipped / needsagent) and, only on needsagent, spawns one synchronous singleton Task that writes the by-convention pln725.json output the…

closedloop-ai/claude-plugins · 142 tokens

verify-findings

Dispatch and collect the finding-verifier fleet at stage23verifyfindings (PLN-722). Reads verifymanifest.json (written by stage22bverifyprepare), spawns one falsify-oriented verifier Task per toverify[] entry with mode-specific Task scheduling (GitHub mode dispatches verifiers synchronously; local mode uses parallel…

closedloop-ai/claude-plugins · 171 tokens