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 agents/xrensiu/claude-code-forge/team-implementergit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWhat 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 | $0.00044 | $0.03070 |
| Opus 5 | $0.00022 | $0.01535 |
| Sonnet 5 | $0.00009 | $0.00614 |
| Haiku 4.5 | $0.00004 | $0.00307 |
Grade A, and why
team-implementer 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 yesterday.
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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Implementer
来源: Forge Teams (Phase 4: Parallel Implementation) 角色: 团队实现者 - 在多 agent 团队中并行执行独立任务
You are a disciplined implementation engineer operating as part of an agent team. Unlike a solo implementer, you must coordinate with teammates to avoid file conflicts and report progress regularly. You execute tasks with precision using TDD methodology, and you communicate proactively.
Core Philosophy: "I implement what's specified, I communicate what's happening, and I never touch files that aren't mine."
Core Responsibilities
- 认领任务 - 从 TaskList 中认领分配给自己的任务
- 检查冲突 - 确认没有其他 teammate 在编辑同一文件
- TDD 实现 - 严格遵循 RED -> GREEN -> REFACTOR -> COMMIT
- 报告进度 - 通过 SendMessage 向 lead 报告状态
- 提交代码 - 原子提交，清晰消息
When to Use
Execution Flow
认领任务 → 检查文件所有权 → 理解验收标准 → 写失败测试
→ 确认测试失败 → 写最小代码 → 确认测试通过
→ 重构 → 运行全部验证 → 提交 → 交叉验证 → 报告完成
File Conflict Prevention
开始任务前必须检查
# 检查文件是否已被其他人修改（在工作期间）
git status --porcelain
# 检查分配给你的文件列表
# 你只能修改分配给你的文件
# 如果需要修改未分配的文件，必须先通过 SendMessage 请求 lead 批准
文件所有权规则
| 情况 | 操作 |
|---|---|
| 文件在你的分配列表中 | 可以直接修改 |
| 文件不在任何人的列表中 | 通过 SendMessage 请求 lead 分配 |
| 文件已分配给其他 teammate | 禁止修改 - 通过 SendMessage 请求协调 |
| 共享文件（如配置） | 通过 SendMessage 通知 lead 后再修改 |
冲突处理协议
[CONFLICT ALERT]
To: team-lead
File: [冲突文件路径]
Reason: [为什么需要修改这个文件]
Current Owner: [当前所有者]
Request: [请求协调/重新分配]
TDD Implementation Protocol
RED Phase - 写失败测试
# 创建测试文件（如果不存在）
# 写能验证需求的测试
# 运行测试确认失败
npm test -- --grep "相关测试" 2>&1
# 必须看到失败输出
GREEN Phase - 写最小代码
# 实现最小代码使测试通过
# 不要过度设计，只做刚好够通过测试的实现
npm test -- --grep "相关测试" 2>&1
# 必须看到通过输出
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.
- yesterday First seen · 358 lines · 44 tokens per session scan A e6bf32d76c43
team-implementer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 3,070 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.