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/dev-plannpx skills add Stanshy/AgentHub --skill dev-plangit clone --depth 1 https://github.com/Stanshy/AgentHubWhat 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 | $0.00016 | $0.01371 |
| Opus 5 | $0.00008 | $0.00685 |
| Sonnet 5 | $0.00003 | $0.00274 |
| Haiku 4.5 | $0.00002 | $0.00137 |
Grade A, and why
dev-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 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
開發計畫書產生器
G0 通過後,由 L1 產出標準化開發計畫書。
使用方式
/dev-plan <sprint-number> <project-name>
參數
$0: Sprint 編號$1: 專案名稱
執行步驟
-
讀取對應的提案書: !
cat proposal/sprint$0-proposal.md 2>/dev/null || echo "找不到 Sprint $0 提案書" -
讀取開發計畫書範本: !
cat .knowledge/templates/dev-plan.md.template 2>/dev/null || echo "範本未找到" -
建立規範文件(若不存在則建立,已存在則跳過):
⚠️ 規範文件是 Code Review「對規範」的比對對象,缺少 = Review 品質打折。 必須在 dev-plan 產出時一併建立,不得延後。
mkdir -p .knowledge/specs建立以下三個檔案(內容從提案書 + 技術方案提取):
檔案 內容 來源 .knowledge/specs/api-design.mdAPI 端點清單、請求/回應格式、錯誤碼 提案書需求 + 技術方案 .knowledge/specs/data-model.md資料表定義、欄位型別、關聯、索引 技術方案 DB 設計 .knowledge/specs/feature-spec.md功能規格、用戶流程、邊界條件、驗收標準 提案書功能清單 每個檔案格式:
# {標題} > 版本: v1.0 | Sprint {N} | 最後更新: {YYYY-MM-DD} ## 概述 {簡述} ## 詳細規格 {具體內容} -
建立 Sprint Branch:
BASE=$(git rev-parse --abbrev-ref HEAD) # 記錄當前 base branch(main / master / 其他) git checkout -b sprint-$0若
sprint-$0branch 已存在,輸出警告並跳過(冪等)。$BASE將寫入 dev-plan metadata,供/sprint-close使用。 -
產出
proposal/sprint$0-dev-plan.md,包含:- 需求摘要(來自提案書)
- 技術方案
- 檔案變更清單
- 介面設計(如需要)
- 第 5 節:規範文件索引(指向
.knowledge/specs/下的三個檔案) - 第 6 節:任務拆解表(含依賴圖)
- 驗收標準
- 異常處理
- 時程預估
- 第 10 節:預建空表格(任務完成紀錄 / Review 紀錄 / Gate 紀錄)
第 10 節格式(強制)
⚠️ 此區域的表頭名稱與欄位順序被系統 parser (
parseDevPlanSection10) 嚴格依賴。 不得更改表頭名稱、欄位順序、或子標題名稱。
## 10. 任務與審核紀錄(備查)
> 每個任務完成後記錄結果,每次 Review/Gate 通過後記錄決策。本區作為 Sprint 完整稽核軌跡。
### 任務完成紀錄
| 任務 | 完成日期 | 結果 | 備註 |
|------|---------|------|------|
| T1 | | | |
| T2 | | | |
(依第 6 節任務清單預建所有任務行)
### Review 紀錄
| Review 步驟 | 日期 | 結果 | Review 文件連結 |
|------------|------|------|---------------|
| UI 圖稿 Review | | | |
| 實作 Review | | | |
| 測試 Review | | | |
(依確認流程中的步驟預建行)
### Gate 紀錄
| Gate | 日期 | 決策 | 審核意見 |
|------|------|------|---------|
| G0 | | | |
| G1 | | | |
(依確認流程中的 Gate 預建行,空行 = 未審核)
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.
- 2d ago First seen · 146 lines · 16 tokens per session scan A b2973e05c853
dev-plan is a skill published in the GitHub repository Stanshy/AgentHub (200 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 1,371 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
flow-next-pilot
Single-tick autonomous build-loop conductor. Advances one ready spec one stage per tick, emits PILOTVERDICT. Use when asked to pilot a spec or backlog.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
mstar-dispatch-gates
Morning Star 派发与委派门禁 —— 仅 PM 可增派 subagent、Execute as 与 Delegation、承接方反递归 NEVER 红线、SDD implement 串行派发、SDD 路径 plan QC 强制 tri-review(N=3)、inline 单席 QC 例外、Assignment 文案≠派发、未齐不发、invoke 角色字段必填(漏写=静默 generic 回退=派发未完成)。project-manager 派发时必读;leaf 动手前必读反递归。worktree 见 mstar-branch-worktree;SDD 见 mstar-sdd;宿主见 mstar-host。.
hk-scout-wiki
Run a scout wave over outside sources (links, blogs, trending repos) into a progressive-disclosure research wiki in the current project, then distill findings into the project's ideas/backlog file. Generic across projects. Use when the user shares links/blogs to research, asks to "scout", "build a wiki from these", or…
todo
Create and update the Hyper-Waterfall daily task board (mydocs/orders/yyyymmdd.md). Apply milestone table format, status update rules, and backlog section rules. When task-start, task-stage-report, task-final-report, or pr-merge-cleanup updates the daily task board, it follows this SKILL's format.
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.