agentmods.dev

claude-dd: Instructions file for Claude Code

CLAUDE.md

claude-dd CLAUDE.md is an instructions file for Claude Code from kopp0510/claude-dd. It costs 13,041 tokens per session, scanned D, original, MIT.

Instructions for a portable Claude Code automation pipeline that installs and updates shared configuration, skills, and commands. It also defines checks, deployment lists, repository layout, and upgrade procedures.

In plain words
What is it for?
Use it to manage the DD Pipeline installation, run environment checks, update deployed skills and agents, follow the seven-step workflow, or maintain the repository’s promoted component lists.
Why use it?
It provides a repeatable way to install, update, inspect, or remove the pipeline while preserving backups and deploying only components with recorded usage.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is kopp0510/claude-dd's own configuration. It tells Claude Code how to work on claude-dd itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-dd configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 12repo changed 4d ago D scan 13,041 tokens original MIT
View source ↗ kopp0510/claude-dd
Reuse

Borrowing it

Nothing to install: this file belongs to kopp0510/claude-dd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kopp0510/claude-dd/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kopp0510/claude-dd

Made for: Claude Code.

Wrote 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.

agentmods badge for claude-dd CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kopp0510/claude-dd/claude-md/github.svg)](https://agentmods.dev/instructions/kopp0510/claude-dd/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kopp0510/claude-dd/claude-md"><img src="https://agentmods.dev/badge/instructions/kopp0510/claude-dd/claude-md/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.

agentmods 80×15 button for claude-dd CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kopp0510/claude-dd/claude-md"><img src="https://agentmods.dev/badge/instructions/kopp0510/claude-dd/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13,041 This file is loaded in full into every session.
When invoked 13,041 The same file — it is already loaded in full.
Security scan D 4 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.13041 $0.13041
Opus 5.5 $0.05216 $0.05216
Sonnet 5.5 $0.02608 $0.02608
Haiku 4.5 $0.01304 $0.01304

Measured 4d ago against content hash 4f7806f9a87e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

claude-dd CLAUDE.md scanned grade D with 4 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`git grep -n '~/\.claude/' -- scripts/ tests/ commands/` 掃一次；兩個 review agent 都把它

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

find ~/.claude/skills -maxdepth 1 -name '*.zip' # 查 zip 殘留（zsh 下 glob 無匹配會直接報錯，故用 find）

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

確認非 DD pipeline 內容後手動 `rm` / `rm -rf` 清掉。

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

實作+測試 → commit → code-simplifier → code-review → 再測(curl/playwright) → commit
CLAUDE.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DD Pipeline — Claude Code 自動化開發流程

可攜式 Claude Code 設定庫，透過 install-dd-pipeline.sh 安裝到 ~/.claude/ 全域。

安裝 / 更新

./install-dd-pipeline.sh                    # 首次安裝
./install-dd-pipeline.sh --force            # 更新：差異檔覆蓋（內容相同不重寫）；全域 CLAUDE.md 跳過詢問直接覆蓋（先備份）
./install-dd-pipeline.sh --check            # 只檢查環境
./install-dd-pipeline.sh --uninstall --yes  # 免確認解除安裝（自動化；非互動環境的詢問一律採預設值）

從舊版（全量部署 / 分桶時期）升級、既有專案升級到 8 步迴圈：見 UPGRADING.md。

環境檢查（步驟 1 / --check）除必要工具外含可選項 ffmpeg：tech-diagram-gif 的 GIF 匯出用，缺少時警示並附安裝指令（brew / apt），該 skill 退化交付 SVG。 只偵測提示、不代裝系統套件。

部署清單（使用率盤點制）

repo 只保留有實證使用紀錄的元件（2026-08-04 盤點留存 9 skills、4 agents、 dd-init、workflow-review；2026-08-10 新增自製 tech-diagram-gif，實證來源為當次 對話的完整管線驗證；2026-09-30 新增只有 hook 的 gate-guard —— 它是 gate 的防護、不是「用過才收」的 元件，是這條規則唯一的例外；2026-10-23 新增自製 plan-review，實證來源為 docs/designs/2026-10-23-裁決審查-design.md S1 驗收的實跑），全部預設部署；清單定義在 install-dd-pipeline.sh 頂部的 PROMOTED_* 陣列。

  • 歷次盤點刪除（git 歷史可回溯）：deprecated 桶（全歷史 0 次使用的 34 skills / 17 agents / 6 dd 指令 / 13 NS commands）與 misc 桶（SRE 備援性質但零實際調用的 11 skills / 5 NS commands）均於 2026-08-04 刪除；取回方式 git checkout pre-prune-2026-08-04 -- skills/<名字> 後加回陣列

目錄結構

  • skills/ — 12 個 Skills（全數部署；除了 gate-guard，每個子目錄含 SKILL.md 定義檔；writing-great-skills 為 vendored 自 mattpocock/skills 的 skill 撰寫參考、tech-diagram-gif 的風格規範 vendored 自 fireworks-tech-graph；gate-guard 是只有 hook、沒有 skill 的 plugin，擋 Claude 用 --no-verify 繞過 gate，見 skills/gate-guard/hooks/CLAUDE.md）
  • agents/ — 4 個 Agents（code-simplifier、code-reviewer 官方備份 + senior-devops、security-auditor）
  • commands/ — 1 個 dd-* 指令（dd-init，.md 平面檔） + 1 個命名空間 command 目錄（workflow-review）
  • templates/global/ — 全域 CLAUDE.md 模板（經互動比對部署到 ~/.claude/CLAUDE.md）
  • scripts/ — 輔助腳本（部署清單由 install-dd-pipeline.sh 頂部的 DD_SCRIPTS 陣列決定，部署到 ~/.claude/scripts/；含 check-claude-md.sh pre-commit gate 與本 repo 自用的 githooks/，後者不部署）
  • diagrams/ — 兩份 README 嵌的 6 張 GIF（使用流程、8 步迴圈、大工作怎麼跑 × 中英），另有 tech-diagram-gif 各風格的示範 GIF（2026-09-07 加入）；每張的來源與重出方式見 diagrams/src/CLAUDE.md （改來源再重出，勿手改 GIF）。 三層架構圖於 2026-08-31 移除 — 它畫的是目錄清單而非架構，資訊都在 DD_PIPELINE_ARCHITECTURE.md 的文字版裡，還多一份圖要維護
  • docs/ — designs/ 放 task-planner 的段落進度表、measurements/ 放實測原始數字與實驗輸入（例如 reviewer 的派送開銷）；不部署
  • tests/ — CI 在 ubuntu 與 macOS（bash 3.2）都跑的測試：gate 情境 test-gate.sh、安裝端到端 test-install.sh；不部署，也不在 scripts/*.sh 那個 glob 內
  • install-dd-pipeline.sh — 安裝腳本（部署到 ~/.claude/；唯一安裝路線，分享亦同）

Read the full file on GitHub · 395 lines

Changes

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.

  1. 4d ago Changed · -2 lines · -45 tokens per session 4f7806f9a87e
  2. 5d ago Changed · +8 lines · +424 tokens per session 977d196eb499
  3. 11d ago Changed · +14 lines · +540 tokens per session 905fb6e56fb2
  4. 13d ago Changed · +5 lines · +181 tokens per session faf51b6380f2
  5. 20d ago Changed · +3 lines · +85 tokens per session bc6ae1b14d0c
  6. 25d ago Changed · +27 lines · +1,118 tokens per session 689c8b9044a0
  7. 27d ago Changed · +10 lines · +404 tokens per session f57e9bc74b69
  8. 28d ago Changed · +9 lines · +447 tokens per session 68288db851dc
  9. 29d ago Changed · +12 lines · +681 tokens per session f6cf5636db28
  10. 1mo ago First seen · 309 lines · 9,206 tokens per session scan D 87169b27dd12

Subscribe to this mod's changes

claude-dd CLAUDE.md is an instructions file published in the GitHub repository kopp0510/claude-dd (12 stars, last pushed 4d ago), licensed MIT. It adds 13,041 tokens to every session, about $0.0522 per session on Opus 5.5. A static security scan graded it D with 4 findings (reads agent configuration directories, enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeCode reviewagent-skillsai-configclaudedeveloper-tools
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens