D
Drix10/agent-flow
Guardrails for AI coding agents: run Claude Code, Codex, Gemini CLI, Cursor or Copilot unattended and come…
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"drix10-agent-flow": {
"command": "npx",
"args": ["@drix10/agent-flow"]
}
}
}解析自我们于 2026-11-09 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"drix10-agent-flow": {
"command": "npx",
"args": ["@drix10/agent-flow"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio drix10-agent-flow -- npx @drix10/agent-flow
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- ★ 数取值
- 12 ★ · Drix10/agent-flow · 取自 GitHub 搜索 API · （2026-11-13 20:00:50 核对）
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型：开源项目
- 收录与活跃
- 收录于 2026-11-10 · 最近见到 2026-11-14 · 共见到 5 次 · 被 1 个来源列出
- 评分构成
- 综合分 103 · 12 ★ · 1 个来源 · repo
- 安装
npx @drix10/agent-flow
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx @drix10/agent-flow。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: Agent 技能。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
Drix10/agent-flow；我们收录于 2026-11-10；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。Leave your coding agent alone with your repo. Come back to a reviewed pull reque
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
One agent builds. A second reviews. A third tests. A guard keeps all three out of what they must never touch.
Install · What you come back to · How it works · Harnesses · FAQ
## Install
bash
npx @drix10/agent-flow install --harness claude
Then tell your agent "use the agent-flow-bootstrap skill": it reads the repo and asks what must never be touched. After that, hand it a task:
bash
npx @drix10/agent-flow run "Add a --json flag so CI can parse the output"
That's all of it. It runs in its own git worktree and stops with checked work and a draft pull request waiting for you. Works with Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Pi and anything that reads AGENTS.md: swap claude for codex, gemini, cursor, copilot, windsurf or agents. Node.js 20+, no runtime dependencies, no package.json needed in your repo.
The guard blocks tool calls directly on Claude Code and Pi. On the other hosts the skills guide the agent and a pre-commit hook and CI catch the slips: what each host enforces.
## What you come back to
Real output from a run on a real repository (trimmed):
text
$ agent-flow status
Protection
✓ Claude Code guard hook is active
✓ 11 protected paths, 7 critical areas
✓ 1 review-only path: agents may add lines (a new CI test), a person reviews the pull request
Work
· #100000 is ready: reviewed, checked, not pushed
→ agent-flow run 100000 --pr to open the pull request
## Without it, and with it
| | ❌ Without Agent Flow | ✅ With Agent Flow |
| Who checks the work | The agent that wrote it | A second agent reviews, a third runs the checks |
| The new test isn't in the CI list | It edits the workflow or loosens the check to get green | It adds one line; every other CI change is refused |
| Push to main, force-push, --no-verify | Nothing stops it | Refused by the guard (Claude Code, Pi) or caught by the pre-commit hook |
| A check fails | You find out when you're back | It goes back to the Implementer, up to a round cap |
| When you're back | A whole diff to read | A draft pull request and a short list of what needs you |
| Docs and context | AGENTS.md describes the old behaviour | agent-flow doctor flags it |
| What happened | Ask the agent | A hash-chained audit log |
## From one real repo
Agent Flow ran for five days on a real C++ and Python research repository (294 role runs, about $83). The audit log recorded:
150 tool calls blocked, among them 20 reads of secret files, 2 pushes to main and 1 --no-verify. Not every block was right: 16 were false alarms from a Windows path bug, fixed in 1.2.6.
15 lines added to the CI workflow, none changed or deleted.
A median finished issue cost $0.90 and took 17 minutes, over 63 issues.
One repository, one maintainer: an example, not a benchmark.
More ways to install and run
Try it first, nothing installed and nothing written:
bash
npx @drix10/agent-flow scan
A read-only X-ray of any repository: languages, test and lint commands, CI, secret suspects. Or take just the skills, with any agent, via skills.sh (they call the CLI through npx, so there is still nothing to set up):
bash
npx skills add Drix10/agent-flow
Install the harness files, then ask your coding agent to bootstrap the repository:
Install · What you come back to · How it works · Harnesses · FAQ
## Install
bash
npx @drix10/agent-flow install --harness claude
Then tell your agent "use the agent-flow-bootstrap skill": it reads the repo and asks what must never be touched. After that, hand it a task:
bash
npx @drix10/agent-flow run "Add a --json flag so CI can parse the output"
That's all of it. It runs in its own git worktree and stops with checked work and a draft pull request waiting for you. Works with Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Pi and anything that reads AGENTS.md: swap claude for codex, gemini, cursor, copilot, windsurf or agents. Node.js 20+, no runtime dependencies, no package.json needed in your repo.
The guard blocks tool calls directly on Claude Code and Pi. On the other hosts the skills guide the agent and a pre-commit hook and CI catch the slips: what each host enforces.
## What you come back to
Real output from a run on a real repository (trimmed):
text
$ agent-flow status
Protection
✓ Claude Code guard hook is active
✓ 11 protected paths, 7 critical areas
✓ 1 review-only path: agents may add lines (a new CI test), a person reviews the pull request
Work
· #100000 is ready: reviewed, checked, not pushed
→ agent-flow run 100000 --pr to open the pull request
## Without it, and with it
| | ❌ Without Agent Flow | ✅ With Agent Flow |
| Who checks the work | The agent that wrote it | A second agent reviews, a third runs the checks |
| The new test isn't in the CI list | It edits the workflow or loosens the check to get green | It adds one line; every other CI change is refused |
| Push to main, force-push, --no-verify | Nothing stops it | Refused by the guard (Claude Code, Pi) or caught by the pre-commit hook |
| A check fails | You find out when you're back | It goes back to the Implementer, up to a round cap |
| When you're back | A whole diff to read | A draft pull request and a short list of what needs you |
| Docs and context | AGENTS.md describes the old behaviour | agent-flow doctor flags it |
| What happened | Ask the agent | A hash-chained audit log |
## From one real repo
Agent Flow ran for five days on a real C++ and Python research repository (294 role runs, about $83). The audit log recorded:
150 tool calls blocked, among them 20 reads of secret files, 2 pushes to main and 1 --no-verify. Not every block was right: 16 were false alarms from a Windows path bug, fixed in 1.2.6.
15 lines added to the CI workflow, none changed or deleted.
A median finished issue cost $0.90 and took 17 minutes, over 63 issues.
One repository, one maintainer: an example, not a benchmark.
More ways to install and run
Try it first, nothing installed and nothing written:
bash
npx @drix10/agent-flow scan
A read-only X-ray of any repository: languages, test and lint commands, CI, secret suspects. Or take just the skills, with any agent, via skills.sh (they call the CLI through npx, so there is still nothing to set up):
bash
npx skills add Drix10/agent-flow
Install the harness files, then ask your coding agent to bootstrap the repository:
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/drix10-agent-flow/)
- 来源
- github · https://github.com/Drix10/agent-flow
- 按领域浏览
- Agent 技能
- Traction
- 12 ★
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。