senior-review

senior-review is a skill for Claude Code, Codex from 0fuk/OpenACCP. It costs 178 tokens per session (5,308 once invoked), scanned A, original, MIT.

A pre-merge review process that sends the same code change to two independent reviewers with different focuses, then combines their findings into one decision. One checks maintainability and change discipline; the other checks affected areas, edge cases, and regression risk.

In plain words
What is it for?
Use it before merging or releasing substantial changes, especially when a diff is unexpectedly large or there is concern about hidden side effects.
Why use it?
A single review can overlook problems or become too familiar with the change. Independent reviews provide separate checks before a non-trivial change is accepted or released.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it before merging or releasing substantial changes, especially when a diff is unexpectedly large or there is concern about hidden side effects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/0fuk/openaccp/senior-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 0fuk/OpenACCP --skill senior-review
Clone the repo
git clone --depth 1 https://github.com/0fuk/OpenACCP

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 senior-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/0fuk/openaccp/senior-review/github.svg)](https://agentmods.dev/skills/0fuk/openaccp/senior-review)
Your own site
<a href="https://agentmods.dev/skills/0fuk/openaccp/senior-review"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/senior-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 senior-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/0fuk/openaccp/senior-review"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/senior-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 178 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,308 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.
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 $0.00178 $0.05308
Opus 5.5 $0.00071 $0.02123
Sonnet 5.5 $0.00036 $0.01062
Haiku 4.5 $0.00018 $0.00531

Measured 2d ago against content hash 067b7eb6cdac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

senior-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 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.

field/skills/senior-review/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Review — 双人独立高级复核

派两名独立复核子代理:Reviewer A 判改动纪律与可维护性,Reviewer B 判影响半径、边缘情况与回归安全。主循环综合两份报告,不得削弱任何一方的 verdict。本 skill 与语言/框架/仓库宿主无关;它不替代项目已有的功能、安全、领域或发布门禁。


0 · Claude Code 执行机制(先读这节,否则这个 skill 跑不起来)

  1. 派发方式=Agent 工具,不是让主循环自己扮演两个角色。
  2. 两个 Agent 调用必须写在同一条消息里——同消息内的多个工具调用才会真并发;分两轮发就退化成串行,还平白多一次上下文污染的机会。
  3. 两名 reviewer 一律 model: opus(Opus 5)+ effort: high,这是默认档,不是可选项。
    • 派发时必须显式写出 model 与 effort,禁止省略让子代理静默继承主循环模型。
    • 依据:owner 20260726 裁决——"对抗复核可以用 opus 5(high),但是你永远是最终验收和决策,opus 5 是可以的,4.8 不可以"。Opus 4.8 明令禁用。
    • 降档只有一种合法情形:owner 当场明示。省 token 不构成降档理由——复核是这套流程唯一的质量闸门,降档等于关闸。
    • 终审与最终决策永远在主循环,不随模型下放(见 §0.6)。
  4. 只读靠 prompt 硬约束:Agent 派出的子代理默认拥有写工具。派发时必须在 prompt 里写死:"你是只读复核员,禁止 Edit/Write 任何产品源码或测试;可以跑非破坏性测试、读历史、读消费方、读 schema/配置/产物/运行时证据;findings 直接写在你的最终回复里(或只写到调用方指定的那一个 review 产物文件)。"
  5. 结果走完成通知回来。禁止用 Bash/Read 去读子代理的 output JSONL transcript——那是完整对话流,读一次就可能撑爆主循环上下文。等通知,或用 SendMessage 追问。
  6. 主循环永远是终裁。两份 verdict 是证据,不是合流/部署/发布的授权。项目与 owner 的既有权限规则始终有效。
  7. compact/resume 之后:不要基于摘要续审。从原始复核包和不可变 target 重建;必要时先落一份 checkpoint 再压缩。

1 · 不可协商规则

  1. 派发前先读:用户请求、验收标准、仓库/工单说明、精确 review target、完整变更集、相关测试。
  2. 两名 reviewer 拿到完全相同的原始素材和同一个 target。不得泄露作者的自辩理由、另一名 reviewer 的发现、或你期望的 verdict。
  3. 必须是两个不同的子代理。并发不可用时可排队串行,绝不允许一个 reviewer 扮两个人格。
  4. 两名 reviewer 对产品源码与外部状态只读(见 §0.4)。
  5. 每名 reviewer 在出 verdict 之前必须重读任务与精确变更清单。compact/中断/交接之后,从原始包重建,不从早前摘要重建。
  6. 不接受作者自审、worker 自证、测试全绿、或"没看到明显失败"作为通过依据。
  7. 任何 AMEND/REJECT/INSUFFICIENT_EVIDENCE 都阻断接受。禁止把冲突 verdict 平均成 PASS。
  8. 实验规模匹配真实风险。不得为凑清单制造无关检查;判定某类别"排除"必须给具体证据。
  9. 两份 verdict 都只是复核证据,不构成合流、部署、发布或改动外部系统的授权。
  10. 给复核过程本身设界:每条阻断性发现必须点名"违反了哪条现行不变量"+"最小修正是什么"。不得把一个缺陷变成开放式重设计、不得递归审计无关邻居、不得在没有可测量证据进展的情况下维持 AMEND 循环。
  11. 命令、等待、重试、轮询、压力测试、外部依赖一律要有超时与停止条件。复核员不得为了找产品级 hang 而制造进程级 hang。

2 · 复核包(packet)——两名 reviewer 拿到的是同一份

  • 用户可见的问题与预期行为(说人话一句);
  • 验收标准 + 明确的非目标;
  • 仓库/任务卡约束;
  • 精确 target 身份:Git base/head 与祖先关系;非 Git 时给不可变前后快照、patch 身份、产物哈希,或显式的未提交 diff 边界;
  • 完整变更清单与变更集(能给文件列表与 diff 统计就给);
  • 相关测试、迁移、生成文件、lockfile、配置、API/schema 变更;
  • 可得时给"修复前可复现失败 / 修复后成功"的证据;
  • 已知基线失败、源码树状态、明确排除在复核外的文件或产物。

Read the full file on GitHub · 197 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. 2d ago First seen · 197 lines · 178 tokens per session scan A 067b7eb6cdac

Subscribe to this mod's changes

senior-review is a skill published in the GitHub repository 0fuk/OpenACCP (2 stars, last pushed 2d ago), licensed MIT. It adds 178 tokens to every session and 5,308 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-14.

Related

Other skills, from other repositories

trace

Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…

jeremylongshore/tons-of-skills-marketplace · 84 tokens

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

skeptical-triage

Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.

avelikiy/great_cto · 49 tokens

anti-patterns

Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).

avelikiy/great_cto · 59 tokens

coordinate-recover

Diagnose and safely resume Coordinate Agents Tasks after executable failure, non-zero exit, timeout, stale claim, processing message, or Implementer ERROR. Recovery is explicit and never an automatic retry loop.

hogancv/coordinate-agents · 43 tokens

coordinate-review

Review a Coordinate Agents implementation as the Codex Reviewer. Verify the real commit, diff, tests, validation evidence, and specification without modifying the Implementer's product code.

hogancv/coordinate-agents · 36 tokens