herdr-coordinator

herdr-coordinator is a skill for Claude Code, Codex from magic3007/dotfiles. It costs 153 tokens per session (1,909 once invoked), scanned A, original, MIT.

A coordinator workflow for sending substantial coding work to background `omp` workers through `hc`. The main conversation handles understanding, planning, task splitting, integration, and final review, while workers implement, debug, or repair tests in separate Git worktrees.

In plain words
What is it for?
Use it for multi-file changes, parallel implementation, substantial debugging, test repairs, or an independent review. Small single-file edits and simple questions are explicitly meant to stay in the main conversation.
Why use it?
It avoids making the main agent do every part of a large change and reduces collisions when several workers edit code. It also sets rules for choosing when delegation is worth its setup cost and for checking the actual models used.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Good fit Use it for multi-file changes, parallel implementation, substantial debugging, test repairs, or an independent review. Small single-file edits and simple questions are explicitly meant to stay in the main conversation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/magic3007/dotfiles/herdr-coordinator
Install

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.

Any agent
npx skills add magic3007/dotfiles --skill herdr-coordinator
Clone the repo
git clone --depth 1 https://github.com/magic3007/dotfiles

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for herdr-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/skills/magic3007/dotfiles/herdr-coordinator/github.svg)](https://agentmods.dev/skills/magic3007/dotfiles/herdr-coordinator)
Your own site
<a href="https://agentmods.dev/skills/magic3007/dotfiles/herdr-coordinator"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/herdr-coordinator/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.

agentmods 80×15 button for herdr-coordinator

Your own site · 80×15
<a href="https://agentmods.dev/skills/magic3007/dotfiles/herdr-coordinator"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/herdr-coordinator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,909 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00153 $0.01909
Opus 5.5 $0.00061 $0.00764
Sonnet 5.5 $0.00031 $0.00382
Haiku 4.5 $0.00015 $0.00191

Measured 3d ago against content hash 0c4c778047c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

herdr-coordinator 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.

omp/skills/herdr-coordinator/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

herdr-coordinator:协调者 + hc 后台 worker 工作流

本会话是协调者。你负责项目理解、规划、任务拆分、集成和终审。实现、调试、修测试、多文件改动交给后台 omp worker。

hc 的具体命令(启动、就绪判断、发送、等待、读回、核实模型、清理)全部以 herdr-desktop skill 为准,先读它。本 skill 只写流程和规则,不重复那些命令。

方案选择原则

每次选能同时改善用户体验(UX)、开发者体验(DX)和代理体验(AX)的方案,且不破坏现有功能。三者冲突时,先保证不破坏现有功能,再说明取舍。

worker 模型

模型不写死在命令里,取 ~/.omp/agent/config.yml 的 modelRoles 角色:

角色 命令 用途
worker omp --model worker 实现、调试、修测试
reviewer omp --model reviewer 独立审查、第二意见
  • 只用 omp。不安装、不启动 Claude Code CLI 或 Codex CLI。
  • 角色指向哪个 provider/model、档位是什么,由用户在 config 里定;启动前按 herdr-desktop 第 0 步读出实际值并冒烟确认。角色缺失或模型不可用时停下告诉用户,不要换模型、换 provider 或降档位。

1. 先判断要不要委托

  • 委托:大量实现、调试、修测试、多文件改动、需要独立审查。
  • 自己做:单文件小改、只读问答、一两条命令能完成的事。为小事开 worker,启动和上下文交接的成本比活本身大。

2. 拆分并说明分工

先用一两段话告诉用户分工:几个 worker、各做什么、哪些并行、谁审查。然后在同一轮里把独立任务全部启动,不要启动一个等一个。

并发数按三项定,最多 10 个,不必用满:

uptime; nproc     # load average 接近或超过 nproc 时少开
  • 任务量:只有真正独立的切片才各开一个 worker。
  • 配额:上一轮 worker 的 jsonl 里出现 429 或 errorMessage,就减少并发。

3. 隔离写入

  • 并行改代码时,每个 worker 一个 worktree、一个分支。共享 checkout 中不允许两个 worker 写同一路径。
  • worktree 从已提交的 HEAD 创建,协调者未提交的改动不会带过去。需要的话先提交,或在任务里写明。
  • 本机没有全局 git 身份。委托前确认仓库有本地身份,worktree 会继承它:
git -C <repo> config user.email          # 为空则 worker 无法提交,先告诉用户
git -C <repo> worktree add -b hc/<task> ../<repo名>-wt/<task> HEAD

worker 的 --cwd 就是这个 worktree 路径。

4. 任务合同

worker 看不到本会话,合同必须自足。每个任务都写全下面六项,并把第一条任务放进 hc send(就绪后发送):

目标:<要解决什么,为什么>
工作目录:<worktree 绝对路径>,分支 hc/<task>;只改 <路径范围>
上下文:<相关文件、接口约定、已知坑、运行/测试命令>
交付物:<在分支上提交的改动 + 简短说明>
完成标准:<可验证的条件,例如某测试通过、某命令输出>
回报:完成或卡住时执行 hc send <协调者地址> '<NONCE> <结果摘要 + 提交 sha>';长内容写文件,发路径
规则:
- 不要为没人要求的罕见情况或未来情况做设计。
- 不要改合同范围外的路径。
  • <协调者地址> 写字面值(echo $HC_TERMINAL_ID 的结果)。worker 自己的 $HC_TERMINAL_ID 指向它自己。
  • 每个 worker 用不同的 NONCE,后面靠它核对回报来源并找到会话 jsonl。
  • 前端任务额外写:优化布局、视觉细节和实际交互,并在浏览器里自测。
  • 不限制 worker 自己起 subagent 或 task。它需要并行探查、跑多个独立切片时,让它自己决定怎么分; 协调者只管合同范围和最终验收,多一层编排不需要额外授权。

5. 等待与反馈

  • 用 hc wait --children all(或 hc wait <name>)等待,不要 sleep 轮询。
  • 返工意见用 hc send <原 worker> 发回去,让它在原对话里接着改。重开 worker 会丢掉它已有的上下文。

Read the full file on GitHub · 128 lines

Changes

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.

  1. 3d ago First seen · 128 lines · 153 tokens per session scan A 0c4c778047c7

Subscribe to this mod's changes

herdr-coordinator is a skill published in the GitHub repository magic3007/dotfiles (11 stars, last pushed 2d ago), licensed MIT. It adds 153 tokens to every session and 1,909 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-11-03.

Related

herdr-coordinator compared with skills from other repositories

herdr-coordinator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
herdr-coordinatormagic3007/dotfilesSkill112d agoMITA153Claude Code, Codex
merge-readyurmzd/dotfilesSkill63d agoApache-2.0A208Claude Code
sync-releaseurmzd/dotfilesSkill63d agoApache-2.0A136Claude Code
prurmzd/dotfilesSkill63d agoApache-2.0A161Claude Code
repo-statusurmzd/dotfilesSkill63d agoApache-2.0A140Claude Code
setup-ciurmzd/dotfilesSkill63d agoApache-2.0A119Claude Code
release-auditurmzd/dotfilesSkill63d agoApache-2.0A126Claude Code