forge-dev

forge-dev is a skill for Claude Code, Codex from yike-gunshi/forge-skills. It costs 122 tokens per session (4,273 once invoked), scanned A, original, MIT.

A Chinese-language development coordinator that takes updated product requirements and organizes design, engineering, and quality-assurance work. It uses separate agent contexts for implementation tasks and supports interactive, automatic, and resume modes.

In plain words
What is it for?
Turning a PRD or design outcome into a development plan, researching the codebase and technology choices, dispatching design, engineering, and QA tasks, and summarizing the resulting delivery.
Why use it?
It keeps the main coordinator focused on planning and handoffs, reducing loss of context as a project grows. It also checks the repository and existing development state before scheduling work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Good fit Turning a PRD or design outcome into a development plan, researching the codebase and technology choices, dispatching design, engineering, and QA tasks, and summarizing the resulting delivery.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yike-gunshi/forge-skills/forge-dev
Install

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.

Any agent
npx skills add yike-gunshi/forge-skills --skill forge-dev
Clone the repo
git clone --depth 1 https://github.com/yike-gunshi/forge-skills

Made for: Claude Code, Codex.

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 forge-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-dev/github.svg)](https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-dev)
Your own site
<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-dev"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-dev/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 forge-dev

Your own site · 80×15
<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-dev"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,273 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00122 $0.04273
Opus 5 $0.00061 $0.02136
Sonnet 5 $0.00024 $0.00855
Haiku 4.5 $0.00012 $0.00427

Measured 9d ago against content hash a5bf56e36fc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

forge-dev 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 9d 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.

skills/forge-dev/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

文档落地路径:遵循 forge-doc-policy 规范。完整白名单 + frontmatter schema 见 ~/.claude/skills/forge-doc-policy/doc-paths.md当前文档加载顺序:先读项目 CLAUDE.mddocs/README.mddocs/INDEX.md, 再读相关根级当前真相源和 .features/{feature-id}/feature-spec.md。 详细规则见 ~/.claude/skills/_shared/current-doc-loading.md

/forge-dev:开发调度器

接力 /forge-prd/forge-brainstorm 的产出,调度设计、工程、QA 子技能完成开发交付。

全程中文。

前置脚本(每次先运行)

检测:当前分支与项目根目录、项目环境(Node / Python / Go / Rust / Makefile)、Playwright 可用性、 .forge/dev-state.json 未完成流水线、.features/_registry.md 注册表、brainstorm 思考文档。 脚本全文见 references/orchestration-details.md「前置检测脚本」。


流程

读取 PRD 迭代摘要
  → 项目类型判断(frontend / backend / fullstack)
  → Discussion 阶段(结构化偏好收集,识别灰区)
  → Research 阶段(技术调研,基于知识+代码扫描+按需搜索)
  → 产出 RESEARCH.md
  → 分析变更 + 调研结果,判断需要哪些子 skill
  → 列出建议的执行计划,用户确认
  → Wave 并行调度子 skill(每个子 skill 在独立上下文执行)
  → 汇总交付结果

全程中文。


上下文工程(核心设计)

问题:随着会话上下文窗口被填满,AI 输出质量会逐步劣化(context rot)。

解决方案:主调度器只做编排,真正的工作发生在子 agent 的独立上下文中。

原则

  1. 主上下文只做调度 — 读取 PRD、判断计划、协调子 agent,不做具体实现
  2. 子 skill 在独立上下文执行 — 使用 Agent 工具启动子代理,每个子 skill 拥有全新的上下文窗口
  3. 精准传递上下文 — 只传递子 skill 需要的文档路径和指令,不传递无关信息
  4. 结果汇总回主上下文 — 子 agent 返回执行摘要,主调度器汇总为交付报告

子 skill 调用方式

使用 Agent 工具,prompt 中包含:
1. 子 skill 的完整指令(从 SKILL.md 读取)
2. 项目路径和 PRD 路径
3. 本次变更的具体内容(从 PRD 迭代摘要提取)
4. 前序子 skill 的产出路径(如 DESIGN.md)
5. RESEARCH.md 路径(如有)

关键约束

  • 每个 Agent 调用只执行一个子 skill
  • 模型路由(Superpowers v5 实践):机械型子任务(跑测试、批量重命名、模板填充)给 Agent 传 model: sonnet 用便宜模型;判断型子任务(架构、设计、审查)保持默认模型,不降级
  • 不要在主上下文中重复子 skill 的工作
  • 子 agent 完成后,读取其产出文档确认结果,而非依赖其返回的文本
  • 传递 Feature Spec:如果 .features/{feature-id}/feature-spec.md 存在,SHALL 将其路径和关键内容(行为场景 + 验收检查表)传递给 forge-eng 和 forge-qa 子 agent
  • forge-eng 行为约束:告知 forge-eng 子 agent 每完成一个功能点后,SHALL 自验对应的 Given/When/Then 场景,确认 PASS 后再继续下一个功能点

模式说明

交互模式(默认)

在 3 个硬卡点暂停等待用户确认:

  1. Discussion 完成后 — 确认偏好收集是否完整
  2. Research + 执行计划确认 — 调研结果 + 建议的执行计划
  3. 所有子技能完成后 — 交付总结确认

Read the full file on GitHub · 327 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 327 lines · 122 tokens per session scan A a5bf56e36fc5

Subscribe to this mod's changes

forge-dev is a skill published in the GitHub repository yike-gunshi/forge-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 4,273 once invoked, about $0.0006 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.

Related

Other skills, from other repositories