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 commands/hmj1026/dhpk/indexgit clone --depth 1 https://github.com/hmj1026/dhpkWrote 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/commands/hmj1026/dhpk/index)<a href="https://agentmods.dev/commands/hmj1026/dhpk/index"><img src="https://agentmods.dev/badge/commands/hmj1026/dhpk/index.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 | $0.00017 | $0.01163 |
| Opus 5 | $0.00009 | $0.00581 |
| Sonnet 5 | $0.00003 | $0.00233 |
| Haiku 4.5 | $0.00002 | $0.00116 |
Grade A, and why
INDEX 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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commands Index (dhpk plugin)
Navigation for slash commands shipped by the dhpk plugin. dhpk commands are invoked as
/dhpk:<name>. External OpenSpec commands, when that separate plugin is installed, use/opsx:<name>.
工作入口與交付
| Command | 用途 |
|---|---|
/dhpk:do |
Smart Router：把自然語言任務路由到適用的 dhpk-* workflow；--route-only 只輸出 Route only: /...（底層 MATCH／NO_MATCH／NO_QUERY），不執行 downstream。 |
/dhpk:create-dev |
舊版相容性 alias；新工作請使用 /dhpk:do。 |
/dhpk:deep-analyze |
深入分析提案並產出 roadmap。 |
/dhpk:spec-mine |
從既有程式碼萃取 behavioral specification。 |
/dhpk:opsx-apply-resume |
長時間 opsx:apply 的 context handoff。 |
Review、測試與驗證
| Command | 用途 |
|---|---|
/dhpk:codex-review |
整合式 Codex second opinion（--scope diff|branch|doc|security|tests）。 |
/dhpk:codex-review-branch / /dhpk:codex-review-fast |
Branch 或快速 diff review。 |
/dhpk:codex-review-doc / /dhpk:codex-security |
文件或安全性專門 review。 |
/dhpk:codex-test-gen / /dhpk:codex-test-review / /dhpk:check-coverage |
產生、審查與檢查測試覆蓋。 |
/dhpk:review-spec |
審查既有技術規格。 |
/dhpk:precommit / /dhpk:precommit-fast / /dhpk:verify |
提交前或完整驗證。 |
/dhpk:dep-audit |
依賴安全風險稽核。 |
/dhpk:review-pending |
完成 pending-review sentinel 對應的 review。 |
Git、發布與工作區
| Command | 用途 |
|---|---|
/dhpk:smart-commit / /dhpk:create-pr |
分組提交與建立 PR。 |
/dhpk:create-release |
版本、changelog、PR、tag 與 CI 的 release 流程。 |
/dhpk:git-worktree |
管理平行 worktree。 |
/dhpk:merge-prep / /dhpk:pr-summary |
合併前分析與 open PR 摘要。 |
Harness、文件與設定
| Command | 用途 |
|---|---|
/dhpk:harness-audit / /dhpk:harness-govern |
Harness 的單次評估與 measure→conform→fix→verify 迴圈。 |
/dhpk:check-skill |
結構化 skill 健康檢查。 |
/dhpk:update-docs / /dhpk:update-codemaps / /dhpk:doc-refactor |
更新、產生或精簡文件；update-docs 以實作證據與 writing-for-agents 契約為準。 |
/dhpk:project-brief |
將技術內容整理為 PM/CTO 摘要。 |
/dhpk:setup |
設定 plugin；用 --install hooks|rules|scripts|all 安裝資產。 |
/dhpk:install-hooks / /dhpk:install-rules / /dhpk:install-scripts |
已棄用的一個 minor-release forwarding alias；新文件與新流程不得使用。 |
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.
- 4d ago First seen · 73 lines · 17 tokens per session scan A a1fc931eaa0c
INDEX is a command published in the GitHub repository hmj1026/dhpk (2 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 1,163 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 2026-08-31.
Other commands, from other repositories
init
在既有專案初始化 Octopus——摸專案、檢查 OpenSpec CLI 與結構（缺則引導安裝）、盤點 change 狀態、建 Arena、出交接報告。每個專案跑一次。.
harness-lint
이 프로젝트의 생성된 하네스를 계약에 대고 검사한다. 결정적 검사 9종.
harness-evolve
하네스를 쓴 결과를 회고하고 에이전트·스킬·오케스트레이터에 되먹인다.
build
SDD 後半段（全自主）：驗 Locked → Builder 逐 task 實作（每條 task 隨行回報）→ 審查 → P1 自動退修（≤3 輪）→ 帶驗收報告回來，你只剩 merge 與 archive。中途不停下來等人。.
spec
SDD 前半段：需求釐清（反問+挑戰）→ OpenSpec change 一次落檔（proposal＋delta＋tasks，Draft）→ TPM 拍板鎖定（回一個 OK 即可）。鎖定後 build 全自主執行。.
debug
用 Agent 工具啟動 debugger agent，把錯誤資訊原文（含截圖/log）完整轉給它。.