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 skills add zsutxz/ClaudeLearning --skill multi-agent-programmergit clone --depth 1 https://github.com/zsutxz/ClaudeLearningWrote 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/skills/zsutxz/claudelearning/multi-agent-programmer)<a href="https://agentmods.dev/skills/zsutxz/claudelearning/multi-agent-programmer"><img src="https://agentmods.dev/badge/skills/zsutxz/claudelearning/multi-agent-programmer/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.
<a href="https://agentmods.dev/skills/zsutxz/claudelearning/multi-agent-programmer"><img src="https://agentmods.dev/badge/skills/zsutxz/claudelearning/multi-agent-programmer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.02560 |
| Opus 5 | $0.00028 | $0.01280 |
| Sonnet 5 | $0.00011 | $0.00512 |
| Haiku 4.5 | $0.00006 | $0.00256 |
Grade A, and why
multi-agent-programmer 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.
How it starts
The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Programmer
协调多代理协作完成复杂编程任务的专业技能。通过主控LLM（Master）协调需求分析、代码实现和代码审查三个专业代理，实现结构化、高质量的软件开发流程。
使用时机
在以下场景使用此技能：
- 复杂功能开发：需要多步骤分析、设计和实现的功能
- 代码重构：涉及多个文件和架构调整的重构任务
- 系统集成：需要理解现有代码库并添加新功能
- 质量要求高：需要经过严格审查的代码实现
- 需求不明确：需要深入分析才能实现的模糊需求
不适合的场景：
- 简单的单文件修改
- 明确的Bug修复（单行或少量代码变更）
- 文档生成或简单配置修改
系统架构
┌─────────────────────────────────────────────────────────┐
│ Master LLM (主控) │
│ 职责：流程协调、任务分发、决策 │
└─────────────┬───────────┬───────────────┬───────────────┘
│ │ │
▼ ▼ ▼
┌─────────────────┐ ┌─────────────┐ ┌─────────────────┐
│ Requirements │ │ Code │ │ Review │
│ Agent │ │ Agent │ │ Agent │
│ (需求分析) │ │ (代码实现) │ │ (代码审查) │
└─────────────────┘ └─────────────┘ └─────────────────┘
代理角色定义
Master LLM (主控代理)
职责：
- 整体流程控制和协调
- 任务分解和分发
- 代理间通信桥接
- 最终决策和质量把关
能力要求：
- 全局视野和决策能力
- 任务优先级判断
- 冲突解决和协调
- 上下文管理
Requirements Agent (需求代理)
职责：
- 分析和理解用户需求
- 识别技术细节和约束条件
- 明确功能边界和验收标准
- 输出详细的技术规格说明
输入：用户原始需求
输出：结构化需求文档（参考 references/requirement_template.md）
能力配置：
- 高度分析性和细致性
- 强调技术细节
- 关注边界情况
- 输出结构化文档
Code Agent (代码代理)
职责：
- 根据需求规格实现代码
- 遵循项目代码规范
- 实现核心功能和边界情况处理
- 编写必要的注释和文档
输入：需求规格文档 输出：实现代码和修改说明
能力配置：
- 代码生成和实现导向
- 遵循最佳实践
- 注重可维护性
- 完整性思维
Review Agent (审查代理)
职责：
- 审查代码质量和正确性
- 检查安全漏洞和潜在问题
- 验证需求覆盖度
- 提出改进建议
输入：实现代码 + 需求规格 输出：审查报告和改进建议
能力配置：
- 批判性和审查性思维
- 安全和质量意识
- 细节观察力
- 建设性反馈
执行流程
阶段 1：需求分析 (Requirements Agent)
-
加载需求模板
使用 Read 工具加载：references/requirement_template.md -
执行需求分析
- 理解用户意图和目标
- 识别功能需求和非功能需求
- 分析技术约束和依赖
- 定义验收标准
-
输出需求文档
- 使用模板生成结构化文档
- 包含：功能描述、技术规格、验收标准、边界情况
阶段 2：代码实现 (Code Agent)
-
分析现有代码库（如需要）
- 使用 Glob 查找相关文件
- 使用 Read 理解现有结构
- 识别需要修改的部分
-
生成实现代码
- 遵循需求规格文档
- 应用项目代码规范
- 处理错误和边界情况
What ships with it
2 files 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.
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.
- 9d ago First seen · 351 lines · 56 tokens per session scan A 82fd30e14bdc
multi-agent-programmer is a skill published in the GitHub repository zsutxz/ClaudeLearning (5 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,560 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…