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-plangit 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-plan)<a href="https://agentmods.dev/skills/stanshy/agenthub/sop-plan"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/sop-plan.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 | $0.00028 | $0.01043 |
| Opus 5 | $0.00014 | $0.00522 |
| Sonnet 5 | $0.00006 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
sop-plan 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 8d 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
L1 計畫模式 SOP
L1 收到任務分派後,必須依序完成以下所有步驟,不得跳過任何 ⛔ CHECKPOINT。
使用方式
/sop-plan
執行步驟
⛔ STEP 1 — 載入 Sprint 計畫書
讀取當前 Sprint dev-plan:
!ls -t proposal/sprint*-dev-plan.md 2>/dev/null | head -1
確認並記錄:
- Sprint 目標(第 1 節)
- 技術方案(第 4 節)
- 任務清單(第 6 節):任務總數、各任務的指派對象、P0/P1/P2 分布、依賴關係
✋ 確認已閱讀 dev-plan,整理出任務清單後再繼續。
⛔ STEP 2 — 載入踩坑紀錄
讀取:.knowledge/postmortem-log.md
標記出與本次任務相關的地雷,後續在驗收標準中必須加入對應防呆。
✋ 確認已列出相關地雷(或確認無相關項目)後再繼續。
⛔ STEP 3 — 載入架構文件
讀取:.knowledge/architecture.md(若不存在則跳過並說明)
確認:
- 系統層次與模組邊界
- 現有服務與依賴關係
- 本次任務涉及的模組範圍
✋ 確認架構限制已納入考量後再繼續。
⛔ STEP 4 — 複雜度評估 + Plan Mode 建議
根據前三步收集的資訊,產出評估報告:
📊 任務複雜度評估
─────────────────────────────
任務總數:N 個
P0 任務:N 個
跨模組依賴:N 條
最長依賴鏈:T1 → T3 → T5(N 層)
涉及模組:[列出]
postmortem 相關地雷:N 條
建議:[進入 Plan Mode ✅ / 不需要 ⚪]
建議理由:
- [說明原因,例如:有 3 條跨模組依賴、P0 任務涉及核心架構變更...]
─────────────────────────────
建議進入 Plan Mode 的條件(符合任一即建議):
- 任務總數 ≥ 5
- 存在 P0 任務
- 跨模組依賴 ≥ 2
- 最長依賴鏈 ≥ 3 層
- postmortem 有直接相關地雷
詢問老闆:
以上是本次 Sprint 的複雜度評估。是否要進入 Plan Mode 後再開始拆解任務? 進入 Plan Mode 後,我會先提出完整計畫供您審核,確認後再執行。
若老闆確認進入 → 使用 EnterPlanMode 工具進入計畫模式
若老闆選擇跳過 → 直接進入 STEP 5
✋ 等待老闆決策後再繼續。
⛔ STEP 5 — 執行任務拆解
執行 /task-delegation(讀取 .claude/commands/task-delegation.md 並依步驟執行)
✋ 確認所有
.tasks/sprint-{N}/檔案已建立後再繼續。
STEP 6 — 輸出計畫摘要
✅ L1 計畫完成
Sprint:Sprint N
已讀文件:dev-plan ✅ | postmortem ✅ | architecture ✅
Plan Mode:[已進入 / 跳過]
已建立任務:
- T1: {名稱} → {agent} (P0)
- T2: {名稱} → {agent} (P1)
- ...
依賴關係:
T1 → T3 → T5
T2 → T4
地雷提醒:
- {相關 postmortem 條目}
下一步:通知各 L2 執行 /sop-execute {task-id}
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.
- 8d ago First seen · 121 lines · 28 tokens per session scan A 505c690e370a
sop-plan is a skill published in the GitHub repository Stanshy/AgentHub (201 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,043 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
cross-campaign
Discover and reference other camps, projects, and files across camp boundaries. Use when the user mentions another camp or campaign by name, references work done "in another project/camp", or needs to find/copy/compare code across camps.
fest-execution
Execute active festival tasks. Use when finding the next task, marking tasks completed/blocked/reset, committing with festival traceability, advancing workflow steps, and validating sequence progress.
fest-planning
Plan and scaffold festivals. Use when creating festival/phase/sequence/task structure, enforcing naming rules, linking festivals to projects, and promoting lifecycle states.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
camp-workitems
Find, filter, choose, create, or adopt camp work items with camp workitem, camp wi, or camp workitems. Use when a user wants current active work across intents, designs, explore notes, festivals, or tracked workflow directories; when agents need safe camp workitem --json output; or when creating/adopting tracked…
fest-methodology
Use when the user mentions festivals, the fest CLI, phases, sequences, or tasks, or when working inside a festivals/ directory. Provides the core Festival methodology model so Claude understands the planning system.