Agent skill

Sop Review

by Stanshy in Stanshy/AgentHub

L1 Code Review SOP — 強制規範對照 + 審核決策,不得跳過任何 checkpoint. An agent skill from Stanshy/AgentHub.

MITAuto-check: notesBusiness, Finance & HR

Install Sop Review

skills CLI
$ npx skills add Stanshy/AgentHub --skill sop-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Stanshy/AgentHub sop-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Stanshy/AgentHub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.knowledge/company/skill-templates/sop-review .claude/skills/sop-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sop-review
GitHub stars
202
Token cost
~522 tokens
SKILL.md length
135 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

L1 Code Review SOP — 強制規範對照 + 審核決策,不得跳過任何 checkpoint. An agent skill from Stanshy/AgentHub.

  • Works in 2 steps: 先同步最新 sprint → 取得 diff
  • Tasks that involve Operations and SOPs
  • SKILL.md covers 使用方式, 參數 and 執行步驟
  • Calls git

What it does

Sop Review is an agent skill from Stanshy/AgentHub. L1 Code Review SOP — 強制規範對照 + 審核決策,不得跳過任何 checkpoint

Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Operations and SOPs. The repository describes itself as: One person, one software company. Manage 47 AI agents from a single Electron app — with Harness Engineering (Skills + Hooks + FileWatchers) for disciplined, traceable AI workflows. The licence is MIT.

When your agent uses it

  • Tasks that involve Operations and SOPs

Example prompts

  • “/sop-review”

Requirements

  • Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. 先同步最新 sprint
  2. 取得 diff

What it can do on your machine

Read from SKILL.md and the folder at commit 5300820. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sop Review loads about 522 tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 135 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~16
When it runs · the whole SKILL.md, loaded when a task matches
~522

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Glob, Grep, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Stanshy/AgentHub at commit 5300820, republished under its MIT licence (© Stanshy). 135 words, ~522 tokens.

Download SKILL.mdSave it as .claude/skills/sop-review/SKILL.md (or your agent's skills folder).
name
sop-review
description
L1 Code Review SOP — 強制規範對照 + 審核決策,不得跳過任何 checkpoint
allowed-tools
Read, Glob, Grep, Bash

L1 Code Review SOP

L1 審核任務時,必須依序完成以下所有步驟,不得跳過任何 ⛔ CHECKPOINT。

使用方式

/sop-review <task-id>

參數

  • $0: 任務 ID(如 T3)

執行步驟

⛔ STEP 1 — 載入任務

找到任務檔案:使用 Glob tool 搜尋 .tasks/**/$0-*.md,若無結果再搜尋 .tasks/**/$0.md,用 Read tool 讀取。

確認並記錄:

  • 任務描述與目標
  • 驗收標準清單(逐項列出)
  • 指派對象(確認是正確的 L2)
  • 完工時間(確認事件紀錄有記錄)

✋ 確認任務內容清楚後再繼續。


⛔ STEP 2 — 載入審查規範

必讀:

  • .knowledge/coding-standards.md(或 .knowledge/company/standards/coding-standards.md)

依任務類型額外讀取:

任務類型必讀規範
後端 / API.knowledge/specs/api-design.md + .knowledge/specs/data-model.md
前端 / UI.knowledge/specs/feature-spec.md
全端以上全部

輸出:

📋 審查規範載入完成
- coding-standards ✅
- [對應規範] ✅

審查重點(從規範中提取):
- [與本任務相關的規範條目]

✋ 確認規範已讀、審查重點已列出後再繼續。


⛔ STEP 2.5 — 取得變更範圍(Git Diff)

讀取任務檔的 | 並行組 | 欄位:

若並行任務(並行組 = A/B/C...):

  1. 先同步最新 sprint:
    bash
    git checkout task/s{N}-$0-{slug}
    git merge sprint-{N}
    若有衝突 → 停止,通知 L2 解決衝突後重新提交
  2. 取得 diff:
    bash
    git diff sprint-{N}...task/s{N}-$0-{slug}
    輸出:
    📂 本次變更範圍(並行任務)
    異動檔案:[列出]
    新增行數:N | 刪除行數:N

若循序任務(並行組 = —):

bash
git show HEAD

輸出:

📂 本次變更範圍(循序任務,最新 commit)
Commit:{hash} {message}
異動檔案:[列出]

以此 diff / show 結果作為 STEP 3 Review 的主要審查依據。

✋ 確認已取得變更範圍後再繼續。


⛔ STEP 3 — 執行 Code Review

執行 /review(讀取 .claude/commands/review.md 並依步驟執行)

Review 必須逐項對照:

  1. 驗收標準 — 每個 - [x] 是否確實完成
  2. 規範條目 — 程式碼是否符合已載入的規範
  3. postmortem 地雷 — 是否有重蹈覆轍

✋ Review 報告完成後再繼續。


⛔ STEP 4 — 審核決策

通過 — 所有驗收標準與規範均符合: → 執行 /task-approve $0 {備註}(讀取 .claude/commands/task-approve.md)

退回 — 有不符合項目: → 執行 /task-status $0 rejected {具體說明哪些項目不通過、需要修改什麼} → 通知 L2 重新執行 /sop-execute $0

✋ 決策必須明確,不得含糊帶過。


STEP 5 — 輸出審核結果
[✅ 通過 / ❌ 退回] $0 審核完成

審核結果:[通過 / 退回]
驗收標準對照:[全部通過 / {列出未通過項目}]
規範對照:[符合 / {列出違規項目}]
備註:{說明}

[若通過] 下一步:PM 執行 /pm-review
[若退回] 下一步:L2 修正後重新執行 /sop-execute $0

© Stanshy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .knowledge/company/skill-templates/sop-review of Stanshy/AgentHub.

Open the folder on GitHubat commit 5300820

Compare with similar skills

Sop Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sop Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sop Review this skillStanshy/AgentHub202—~522Automated safety check: NotesMIT
Alcoa Guards0912758806p/agentic-sop-to-work209—~363Automated safety check: PassMIT
Cc Sdd New Agentgotalab/cc-sdd3.7k—~1.1kAutomated safety check: PassMIT
DBS Business Toolkit Entrydontbesilent2025/dbskill11k—~2kAutomated safety check: PassCustom licence
Agent Sop Authorstrands-agents/agent-sop1.2k—~3.5kAutomated safety check: PassApache-2.0
Diffusion Narrative Denouncingcanwhite/Krebs1k—~831Automated safety check: PassMIT

Similar skills

  • Alcoa Guard

    s0912758806p/agentic-sop-to-work

    A skill your agent uses when checking a record / dataset / GMP document for ALCOA+ data integrity — attribution, contemporaneity (backdating), completeness, accuracy (recompute / in-spec)…

    209 GitHub stars~363 tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Cc Sdd New Agent

    gotalab/cc-sdd

    Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end.

    3.7k GitHub stars~1.1k tokensUpdated 18 days ago
    Business, Finance & HRAuto-check passed
  • DBS Business Toolkit Entry

    dontbesilent2025/dbskill

    Chinese-language entry skill for the dontbesilent business toolkit: onboards new users, orchestrates tasks across sub-skills, runs numbered prompts and lists hidden ones.

    11k GitHub stars~2k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Agent Sop Author

    strands-agents/agent-sop

    Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.

    1.2k GitHub stars~3.5k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed
  • 基于"扩散模型叙事去噪流"的小说写作 SOP。将 AI 视为去杂质机器,通过锁定全局信号、预测叙事噪声、精准去噪、随机修正四个步骤,解决 AI 翻译腔、逻辑断层和故事平淡的问题。

    1k GitHub stars~831 tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Company Research

    simonlin1212/Vibe-Research

    A 股 / 港股 / 美股个股研究六阶段 SOP(profile → financials → estimates → valuation → risk → report),Phase 0 范围 = 财务估值闭环。当任务是研究 / 分析 / 评估一只或多只已指定代码的个股时使用(港股 / 美股的口径差异见 §7);规定每阶段取哪些数据、调哪些 calc 函数、必须落盘什么产物、过什么…

    2.7k GitHub stars~3.2k tokensUpdated today
    Business, Finance & HRAuto-check passed

More from Stanshy/AgentHub

All 23 skills in this repo
  • Dev Plan

    Stanshy/AgentHub

    Generate a development plan with task breakdown and section 10 tracking tables

    202 GitHub stars~686 tokensUpdated 6 mo ago
    Auto-check: notes
  • Knowledge Feedback

    Stanshy/AgentHub

    Scan child projects for pitfalls and propose company standard updates

    202 GitHub stars~549 tokensUpdated 6 mo ago
    Auto-check: notes
  • Product Diagnosis

    Stanshy/AgentHub

    Six-question diagnostic framework for G0 pre-check — validate product direction before development starts

    202 GitHub stars~690 tokensUpdated 6 mo ago
    Auto-check passed
  • Project Kickoff

    Stanshy/AgentHub

    Initialize new project with CLAUDE.md, .knowledge/ structure, company rules, and git

    202 GitHub stars~528 tokensUpdated 6 mo ago
    Auto-check: notes
  • Review

    Stanshy/AgentHub

    L1 internal review with auto-detection, design comparison, and Gate escalation path

    202 GitHub stars~854 tokensUpdated 6 mo ago
    Auto-check: notes
  • Sop Plan

    Stanshy/AgentHub

    L1 計畫模式 SOP — 強制上下文載入 + Plan Mode 評估 + 任務拆解. An agent skill from Stanshy/AgentHub.

    202 GitHub stars~437 tokensUpdated 6 mo ago
    Auto-check: notes

Questions about Sop Review

What does Sop Review do?

L1 Code Review SOP — 強制規範對照 + 審核決策,不得跳過任何 checkpoint. An agent skill from Stanshy/AgentHub. Sop Review is an agent skill from Stanshy/AgentHub.

When should I use Sop Review?

Sop Review fits situations like: tasks that involve Operations and SOPs.

How do I install Sop Review in Claude Code?

Run `npx skills add Stanshy/AgentHub --skill sop-review -a claude-code`. Or copy the skill folder (.knowledge/company/skill-templates/sop-review in Stanshy/AgentHub) into .claude/skills/sop-review in your project. Claude Code loads it when a task matches its description.

How do I install Sop Review in Codex?

Run `npx skills add Stanshy/AgentHub --skill sop-review -a codex`. Or copy the skill folder (.knowledge/company/skill-templates/sop-review in Stanshy/AgentHub) into .agents/skills/sop-review in your project. Codex loads it when a task matches its description.

Can I use Sop Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Stanshy/AgentHub --skill sop-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sop-review, .gemini/skills/sop-review, .github/skills/sop-review and .opencode/skills/sop-review in your project.

What does Sop Review need to run?

Going by SKILL.md and its folder, Sop Review needs the command-line tools its instructions call (git). Its frontmatter pre-approves these tools: Read, Glob, Grep, Bash.

Does Sop Review access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Sop Review safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Sop Review use?

Sop Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sop Review use?

About 522 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sop Review?

Skills that share tags, products or a category with Sop Review: Alcoa Guard (s0912758806p/agentic-sop-to-work, 209 stars), Cc Sdd New Agent (gotalab/cc-sdd, 3.7k stars), DBS Business Toolkit Entry (dontbesilent2025/dbskill, 11k stars) and Agent Sop Author (strands-agents/agent-sop, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sop Review?

Stanshy (a GitHub user) maintains it in Stanshy/AgentHub, which has 202 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on April 9, 2026.

Source: Stanshy/AgentHub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.