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 skills/marecgents/marec-agent-skills/github-project-replicationnpx skills add MarecGents/marec-agent-skills --skill github-project-replicationgit clone --depth 1 https://github.com/MarecGents/marec-agent-skillsWrote 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/marecgents/marec-agent-skills/github-project-replication)<a href="https://agentmods.dev/skills/marecgents/marec-agent-skills/github-project-replication"><img src="https://agentmods.dev/badge/skills/marecgents/marec-agent-skills/github-project-replication.svg" alt="Measured on agentmods" 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 | $0.00164 | $0.03412 |
| Opus 5 | $0.00082 | $0.01706 |
| Sonnet 5 | $0.00033 | $0.00682 |
| Haiku 4.5 | $0.00016 | $0.00341 |
Grade A, and why
github-project-replication 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 3d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub 开源项目自动化复现
当你收到用户"复现 GitHub 项目"相关的任务时,按照本技能定义的系统化六阶段工作流,从项目理解到稳定运行,全程自动化执行。
核心原则
- 必须先调用 brainstorming — 每次任务执行必须先调用 brainstorming 技能进行前期构思和分析,不得跳过此步骤。这帮助你在动手之前全面理解项目目标和潜在挑战。
- 必须用 planning-with-files-zh 做追踪 — 调用 planning-with-files-zh 技能进行任务文件化追踪,该技能会创建
task_plan.md、findings.md、progress.md三个核心追踪文件,让整个复现过程有迹可循、可回溯。 - 规范统一由 skill-standard-harness 管理 — 操作层面的公共规范(如 GitHub 仓库获取规范、Markdown 输出规范等)由 skill-standard-harness 统一维护,本技能不再重复定义。
GitHub 仓库获取规范
复现项目的第一步是获取目标仓库的代码。请调用 skill-standard-harness 技能并读取 references/github-access-standard.md,按照其中的四级优先级规范执行获取操作。
目录说明
github-project-replication/
├── SKILL.md ← 本文件:六阶段工作流定义
├── references/ ← 预留:本技能自身的参考文档(当前无内容)
└── scripts/ ← 预留:本技能自身的辅助脚本(当前无内容)
注意:本技能涉及的公共规范(GitHub 仓库获取、Markdown 输出)统一存放在
skill-standard-harness/references/,不在此目录重复维护。
六阶段工作流
阶段一:初始化 → 阶段二:项目理解 → 阶段三:复现搭建
↓ (循环迭代)
阶段四:运行评估 ←——┘
↓
阶段五:循环迭代
↓
阶段六:任务收尾
阶段一:技能调用与初始化
触发条件:接收到 "复现 GitHub 项目" 相关任务时立即进入此阶段。
执行步骤:
-
调用 brainstorming — 对目标项目进行初步分析构思。思考:
- 这个项目做什么的?它的核心价值是什么?
- 它依赖哪些技术栈和环境?
- 复现它可能遇到哪些主要挑战?
- 需要哪些前置条件(如 API 密钥、数据库、特定 OS)?
-
调用 planning-with-files-zh — 初始化三个追踪文件:
task_plan.md— 拆解为可执行的任务清单findings.md— 预留研究笔记空间progress.md— 准备记录操作日志
-
解析用户输入 — 从用户消息中提取:
- 目标 GitHub 仓库 URL(如
https://github.com/user/repo) - 或本地项目路径
- 任何附加要求(如特定分支、自定义配置)
- 目标 GitHub 仓库 URL(如
获取目标仓库代码 — 调用 skill-standard-harness 技能,按照 references/github-access-standard.md 中的四级优先级规范获取源码。将获取过程和结果记录到 progress.md。
阶段二:MCP 服务调用与项目理解
目标:快速全面地了解目标项目的代码架构,为复现工作奠定基础。
执行步骤:
- 分析项目代码结构(如果 CodeGraph MCP 服务可用):
- 索引目标项目的代码库
- 获取项目结构统计信息(实体数量、文件数、模块关系等)
- 进行符号搜索和上下文探索
- 分析依赖关系和调用链
- 为什么:这让你在动手前就对代码的骨架有全局认知,避免在搭建时走弯路
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.
- 3d ago First seen · 272 lines · 164 tokens per session scan A 6cf8f7fa11fc
github-project-replication is a skill published in the GitHub repository MarecGents/marec-agent-skills (3 stars, last pushed 6d ago), licensed MIT. It adds 164 tokens to every session and 3,412 once invoked, about $0.0008 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 skills, from other repositories
fabric-exec
Troubleshooting and advanced API reference for fabricexec TypeScript programs, dynamic providers, agents, and schema recovery. Routine pi. coding calls are documented by ambient guidance; load this skill only after an argument-shape error or when an advanced surface needs exact contracts.
fabric-fusion
Multi-model deliberation. Two to 8 distinct models answer in parallel with web-capable tools, then a judge compares consensus, contradictions, coverage gaps, unique insights, and blind spots. Act mode runs 1–4 read-only references, then one actor reconciles and executes. Use when the cost of being wrong justifies…
fabric-rlm
Recursively decomposes oversized tasks into bounded child Pi agents with fresh context windows. Use for whole-repo audits, massive-context analysis, and multi-file refactors that do not fit one context.
fabric-schema
Uses Fabric's typed Schema evidence loop and, when enabled, its bounded local-file transaction channel. Use when surprise must void a plan and mutation claims need explicit postconditions.
fabric-workflow
Runs a dynamic Pi Fabric workflow with code-held phases, fan-out, pipelines, structured agents, and best-effort verification. Use for large audits, migrations, parallel research, or explicit workflow requests.
fabric-council
Runs a bounded multi-perspective Pi Fabric council with independent reviewers and best-effort synthesis. Use for architecture choices, plans, reviews, and adversarial cross-checking.