forge-teams

forge-teams is a skill for Claude Code from XRenSiu/claude-code-forge. It costs 184 tokens per session (12,073 once invoked), scanned A, original, MIT.

A seven-stage development coordinator for Agent Teams that routes a request to feature development, bug investigation, or red-team review. It combines debate, parallel implementation, debugging, and review.

In plain words
What is it for?
Use it for a new project, a complex feature, a code-review request, or a known bug. It can run the full process, start at a chosen stage, or optionally fix and recheck review findings.
Why use it?
It provides one entry point for different engineering situations and brings together the planning, coding, testing, and review work they require.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

Part of the forge-teams plugin — 7 skills, 20 agents shipped together

Good fit Use it for a new project, a complex feature, a code-review request, or a known bug. It can run the full process, start at a chosen stage, or optionally fix and recheck review findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xrensiu/claude-code-forge/forge-pipeline
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 XRenSiu/claude-code-forge --skill forge-pipeline
Clone the repo
git clone --depth 1 https://github.com/XRenSiu/claude-code-forge

Made for: Claude Code.

Or install forge-teams, the plugin that ships this one along with the rest of its 7 skills, 20 agents.

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-teams

README.md
[![agentmods](https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/forge-pipeline.svg)](https://agentmods.dev/skills/xrensiu/claude-code-forge/forge-pipeline)
Your own site
<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/forge-pipeline"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/forge-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,073 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 $0.00184 $0.12073
Opus 5 $0.00092 $0.06037
Sonnet 5 $0.00037 $0.02415
Haiku 4.5 $0.00018 $0.01207

Measured 7d ago against content hash 0f27b13a7f9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

forge-teams 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 7d 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.

plugins/forge-teams/skills/forge-pipeline/SKILL.md · 1,010 lines

How it starts

The opening of the file, as written. The whole thing — 1,010 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge Teams - Agent Teams 7 阶段对抗协作流水线

/forge-teams 是 Agent Teams 驱动的产品开发主协调器。支持意图自动识别——根据需求内容自动选择最佳入口:bug 描述直接进对抗调试(P6),审查请求直接进红队审查(P5),新功能走完整 7 阶段流水线。每个关键决策点由多个 agent 并行竞争、辩论和交叉验证,通过结构化对抗消除单 agent 的认知偏差。

Announce at start: "I'm using the forge-teams skill to orchestrate a 7-phase adversarial development pipeline with Agent Teams."

前置条件: 需要启用 Agent Teams 实验性功能。 在 settings.json 中添加: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }


用法

/forge-teams <requirement> [options]

参数说明

参数 说明 默认值
<requirement> 需求描述 / bug 描述 / 审查上下文(文本或文件路径) 必填(完整流水线);--skip-to 时可选但建议提供
--phase <1-7> 仅运行指定阶段 运行全部
--skip-to <phase> 从指定阶段开始。有前序产物则恢复,无前序产物则自动 bootstrap 从阶段 1 开始
--team-size <size> 团队规模配置 medium
--no-red-team 跳过红队审查(阶段 5) 启用红队
--fix 审查/调试发现问题后自动修复 不自动修复
--loop [N] 修复后重新验证(最多 N 轮) 3
--feature <name> 指定恢复的 feature 目录(配合 --skip-to 自动检测最近未完成的 run

示例

自动路由(推荐用法,无需记参数)

# 自动识别 → bug 描述 → 对抗调试(P6)
/forge-teams "支付回调间歇性超时,大约每10次失败2次"
/forge-teams "用户登录后 session 偶尔丢失"

# 自动识别 → 审查请求 → 红队审查(P5)
/forge-teams "帮我审查下 src/payment/ 的安全性"
/forge-teams "上线前帮我做个代码体检"

# 自动识别 → 新功能 → 完整流水线(P1→P7)
/forge-teams "用户认证功能,支持 OAuth2 和 JWT"
/forge-teams "支付系统重构" --team-size large --fix --loop 5

意图自动识别: Lead 分析 <requirement> 内容,自动判定走 P5(审查)、P6(调试) 还是完整流水线。用户不需要记任何参数,直接说要做什么就行。

显式指定入口(覆盖自动判定)

# 强制走红队审查
/forge-teams --skip-to 5 "支付回调间歇性超时"

# 断点续跑
/forge-teams --skip-to 3 --feature "用户认证功能-20260324"

# 审查 + 发现问题自动修复
/forge-teams --skip-to 5 --fix --loop 3

--skip-to 始终优先于自动路由。有前序产物则恢复断点,无前序产物则自动 bootstrap(仅支持 P5/P6)。

独立入口(不走完整流水线)

# 独立 bug 修复(复用 P6 引擎,支持快速路径和三层迭代控制)
/forge-fix "支付回调间歇性超时" --loop 5
/forge-fix "CSS 错位" --quick

# 独立需求验证(检查代码是否实现了指定需求)
/forge-verify "用户可以通过邮箱注册,密码至少8位"
/forge-verify "支持 OAuth2 登录" --fix --loop 3   # 验证 + 自动补齐

团队规模配置

规模 每阶段团队 适用场景 Token 消耗
small 2-3 agents 小功能、快速验证
medium 3-5 agents 标准功能开发
large 5-7 agents 复杂功能、高质量要求 很高

Read the full file on GitHub · 1,010 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. 7d ago First seen · 1,010 lines · 184 tokens per session scan A 0f27b13a7f9c

Subscribe to this mod's changes

forge-teams is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed today), licensed MIT. It adds 184 tokens to every session and 12,073 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens