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 agentmods add skills/stanshy/agenthub/sop-deploynpx skills add Stanshy/AgentHub --skill sop-deploygit 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-deploy)<a href="https://agentmods.dev/skills/stanshy/agenthub/sop-deploy"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/sop-deploy.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 | $0.00026 | $0.00592 |
| Opus 5 | $0.00013 | $0.00296 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
sop-deploy 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 5d 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
部署 SOP
部署前，必須依序完成以下所有步驟，不得跳過任何 ⛔ CHECKPOINT。
使用方式
/sop-deploy
執行步驟
⛔ STEP 1 — 載入品質 Checklist
讀取（依序嘗試）：
.knowledge/quality-checklist.md.knowledge/company/standards/quality-checklist.md
逐項列出所有檢查項目，確認每項的當前狀態。
✋ 確認 checklist 已讀、項目已列出後再繼續。
⛔ STEP 2 — 確認所有任務狀態
!find .tasks -name "*.md" | xargs grep -l "| 狀態 |" 2>/dev/null | xargs grep "| 狀態 |" 2>/dev/null
確認：
- 本 Sprint 所有任務均為
done - 無
in_progress、in_review、blocked的未結任務
✋ 若有未結任務，禁止繼續部署，回報 L1 處理。
⛔ STEP 3 — 執行 Pre-deploy 檢查
執行 /pre-deploy（讀取 .claude/commands/pre-deploy.md 並依步驟執行）
對照 STEP 1 載入的 checklist，逐項勾選：
- 已完成 →
- [x] - 未完成 → 停止，回報原因
✋ 所有 checklist 項目通過後才可繼續。若有未通過項目，記錄原因並停止。
STEP 4 — 執行部署
依專案部署方式執行（參考 CLAUDE.md 或 dev-plan 的部署指令）。
⛔ STEP 5 — 記錄 Gate G5
執行 /gate-record G5 通過 {備註}（讀取 .claude/commands/gate-record.md 並依步驟執行）
STEP 6 — 輸出部署結果
✅ 部署完成
Sprint：Sprint N
品質 Checklist：全部通過 ✅
未結任務：無 ✅
Gate G5：已記錄 ✅
部署時間：{timestamp}
下一步：PM 執行 /sprint-retro
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.
- 5d ago First seen · 76 lines · 26 tokens per session scan A 20e2ea02e48a
sop-deploy is a skill published in the GitHub repository Stanshy/AgentHub (201 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 592 once invoked, about $0.0001 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.
Other skills, from other repositories
fix-ci
Fix the failed CI checks for the current session. Use when the user requests a CI fix via the Fix Checks button in the Changes toolbar.
comet-github-ci-triage
使用 PR 当前准确 head、失败 job 日志、本地复现边界和可合并状态，诊断 Comet PR 的 GitHub Actions 与覆盖率检查。PR 出现 CI 报错、Codecov 问题、过期检查或无法解释的红色 job 时使用。.
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
watch-ci
Monitor GitHub Actions CI runs until completion. Use when: watching CI after push, checking build status, monitoring PR checks, waiting for CI completion, user says 'watch CI', 'check CI', 'CI status', 'monitor build', or /watch-ci. Not for: pushing code (use push-ci), creating PRs (use create-pr). Output: per-run…
squid-implement-night
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan.
squid-review-ci
Drive CI green on a pushed, review-clean feature PR — On-Call diagnoses failures and hands fix tasks to the SWE. Output: a CI-validated feature PR. Trigger after /squid-review passes.