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 Stanshy/AgentHub --skill sop-executegit clone --depth 1 https://github.com/Stanshy/AgentHubWrote 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/stanshy/agenthub/sop-execute)<a href="https://agentmods.dev/skills/stanshy/agenthub/sop-execute"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/sop-execute/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.
<a href="https://agentmods.dev/skills/stanshy/agenthub/sop-execute"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/sop-execute.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.00960 |
| Opus 5.5 | $0.00013 | $0.00384 |
| Sonnet 5.5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
sop-execute 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 1mo 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
L2 任務執行 SOP
L2 執行任務時，必須依序完成以下所有步驟，不得跳過任何 ⛔ CHECKPOINT。
使用方式
/sop-execute <task-id>
參數
$0: 任務 ID（如T3）
執行步驟
STEP 1 — 標記任務開始
執行 /task-start $0（讀取 .claude/commands/task-start.md 並依步驟執行）
⛔ STEP 2 — 載入任務規格
找到任務檔案：
!find .tasks -name "$0-*" -o -name "$0.*" 2>/dev/null | head -1
確認並記錄：
- 任務描述
- 指派對象確認（確認是本 Agent 的任務）
- 依賴任務（確認依賴項目均已
done，否則回報 blocked） - 驗收標準（逐項列出
- [ ]清單）
✋ 確認任務規格清楚、依賴已解除後再繼續。若依賴未完成，執行
/task-status $0 blocked 等待 {依賴任務} 完成並停止。
⛔ STEP 3 — 載入對應規範
讀取 .knowledge/company-rules.md
依任務類型讀取對應規範：
| 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 |
| 不確定 | 全部讀取 |
讀取 .knowledge/postmortem-log.md，找出與本次任務相關的地雷條目。
輸出：
📋 規範載入完成
- company-rules ✅
- [對應規範] ✅
- postmortem 相關地雷：[列出，或「無」]
本次任務需特別注意：
- [從規範中提取與任務直接相關的限制條目]
✋ 確認規範已讀、相關限制已列出後再繼續。
STEP 4 — 實作
依規範實作。過程中：
-
遇到阻塞（技術問題、依賴未就緒、需求不明）： 執行
/task-status $0 blocked {具體原因}，回報 L1 後停止等待 -
需要變更規範範圍外的內容： 先回報 L1，不得擅自修改規範文件或驗收標準
⛔ STEP 5 — 自我驗收
逐項確認任務檔案中 ## 驗收標準 的每個 - [ ]：
- 已完成 → 標記為
- [x] - 無法確認 → 在備註中說明，不可跳過
✋ 所有驗收標準必須打勾或有說明後才可繼續。 若有未完成項目，返回 STEP 4 繼續實作。
STEP 6 — 提交審查
執行 /task-done $0 {完成備註}（讀取 .claude/commands/task-done.md 並依步驟執行）
STEP 7 — 輸出摘要
✅ $0 執行完成，已提交 L1 審查
驗收標準：全部通過 ✅
規範對照：完成 ✅
地雷防呆：[已處理 / 無相關]
等待 L1 執行 /sop-review $0
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.
- 1mo ago First seen · 109 lines · 32 tokens per session scan A dec099e59c7b
sop-execute is a skill published in the GitHub repository Stanshy/AgentHub (204 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 960 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp: publish the Windows head first, then point packaging at the resolved resizetizer manifest. Use for a MAUI MSIX or signed unpackaged build, MAUI packaging in CI, or 'manifest contains unresolved placeholders' errors from winapp package.