Borrowing it
Nothing to install: this file belongs to cloud-Xolt/local-repo-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cloud-Xolt/local-repo-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/cloud-Xolt/local-repo-mcpWrote 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/instructions/cloud-xolt/local-repo-mcp/agents-md)<a href="https://agentmods.dev/instructions/cloud-xolt/local-repo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cloud-xolt/local-repo-mcp/agents-md.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 5.1 | $0.00734 | $0.00734 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
local-repo-mcp AGENTS.md 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 8d 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.
What it actually says
Local Repo MCP — AI 开发约束
本项目是轻量、单一用途的本地 Git 仓库 MCP Server,不是企业 Agent Runtime。
第一约束:工具定位
本项目只提供单仓库的受控远程开发、测试/构建执行和结果回传能力。设计必须保持轻量、固定工具面、受控执行和结果可核验;禁止演进为 Agent、任务编排平台或通用远程 Shell。
产品边界
- 只服务一个配置的本地 Git 仓库
- 默认
MCP_MODE=read - 仅支持
read/write/test三档模式 - 写入主要通过
repo_apply_patch(统一文本 Patch) - 可选
repo_git_commit(默认关闭;GUI/ALLOW_GIT_COMMIT显式开启后,write/test 可创建本地 commit) - 可选
repo_run_test(仅 test 模式,白名单 test/build/lint/check;兼容单命令与有界顺序批量) - 可选 OpenAI Secure MCP Tunnel(用户自行安装 tunnel-client)
禁止新增
- Session / RBAC / Risk Scorer / Policy YAML
- 自动分支 checkout / push / amend / reset / rebase
- 三阶段 Patch 审批
- Docker Sandbox / 任意 Shell
- Tunnel 自动下载
- API Key 落盘
每次修改必须
- 路径使用
relative_to(),拒绝绝对路径、..、symlink - 敏感路径使用
src/security/guard.pydenylist - Git status/diff 过滤敏感路径
- 搜索使用
rg --fixed-strings -e query -- - 同步更新
tests/与 README - 保持 MCP Tool 数量为 8 个,不随意新增
- 所有 MCP Tool 必须发布稳定的
inputSchema与outputSchema;可选参数通过 default/required 表达,避免不必要的 nullable union - 协议契约统一定义在
src/tools/contracts.py,并由真实tools/list回归测试验证,禁止为单个客户端写 Tool 特判
MCP Tools(仅这 8 个)
repo_list_files
repo_read_file
repo_search_code
repo_git_status
repo_git_diff
repo_apply_patch
repo_git_commit
repo_run_test
核心模块
src/security/guard.py — 路径 denylist
src/security/scanner.py — Patch 新增行凭证 regex
src/repo/filesystem.py — 读取与列表
src/repo/git.py — 过滤后的 Git 操作
src/tools/contracts.py — 统一 MCP Tool 协议契约与 tools/list schema 自检
src/tools/patches.py — 原子统一 Patch 适配层(支持一次修改多个文件)
src/commands/models.py — CommandSpec / CommandResult / BatchResult
src/commands/registry.py — 固定白名单命令注册
src/commands/runner.py — 统一受控命令执行核心
src/tools/test_runner.py — 旧 Python 入口兼容层,不承载生产执行逻辑
launch_mcp.py — Tunnel 固定 launcher
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.
- 8d ago First seen · 67 lines · 734 tokens per session scan A 16fceb930820
local-repo-mcp AGENTS.md is an instructions file published in the GitHub repository cloud-Xolt/local-repo-mcp (5 stars, last pushed 14d ago), licensed MIT. It adds 734 tokens to every session, about $0.0037 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.