herdr-orchestra

herdr-orchestra is a skill for Claude Code, Codex from bahayonghang/my-ai-cli-toolkit. It costs 84 tokens per session (896 once invoked), scanned A, original, MIT.

A coordinator for assigning tasks to worker agents in Herdr, a system for running and communicating with multiple agent sessions. It sends work, collects responses, checks their scope and completeness, and returns a record of what happened.

In plain words
What is it for?
Use it for explicit Herdr tasks such as splitting research, collecting worker findings, comparing results, and checking the identity and status of delegated agents.
Why use it?
It provides controlled delegation when several agents need to work in parallel or compare results. It avoids treating an idle worker or matching opinions as proof that a task is complete.

Skill for Claude CodeCodex

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

Good fit Use it for explicit Herdr tasks such as splitting research, collecting worker findings, comparing results, and checking the identity and status of delegated agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bahayonghang/my-ai-cli-toolkit/herdr-orchestra
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 bahayonghang/my-ai-cli-toolkit --skill herdr-orchestra
Clone the repo
git clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkit

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-orchestra

README.md
[![agentmods](https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/herdr-orchestra/github.svg)](https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/herdr-orchestra)
Your own site
<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/herdr-orchestra"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/herdr-orchestra/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-orchestra

Your own site · 80×15
<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/herdr-orchestra"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/herdr-orchestra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 896 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 $0.00084 $0.00896
Opus 5 $0.00042 $0.00448
Sonnet 5 $0.00017 $0.00179
Haiku 4.5 $0.00008 $0.00090

Measured today against content hash 8fa705010fc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

herdr-orchestra 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 today.

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.

skills/developer-tools-integrations/herdr-orchestra/SKILL.md · 37 lines

What it actually says

Herdr Orchestra

在 Herdr 中把明确任务交给 worker,并向调用者交付可核验的结果。默认一项任务、一个 worker;调用者负责权限、分工和最终验收。

Router Rules

  • 只接管显式 Herdr 编排请求,或已获授权的上层 skill 委派。普通 review 走既有审查流程,简单 pane 查询走官方 herdr 指引或 CLI help;研究 Herdr 文档不启动进程。
  • 已被分配为 leaf 的 worker 直接做本职工作,不再次调用此入口。新进程不会自动继承调用者加载的技能:把必要约束放进任务文本。
  • 非 Herdr 环境停止本 skill 的会话操作,并说明限制;缺少能力时不偷偷改用其他传输。

Compact Workflow

  1. 阅读 委派契约,取得目标、cwd、kind/native argv、输入范围、权限/文件 ownership、输出和验收条件。未指定模型就沿用用户配置。未授权的范围变化才需要补问。
  2. 在任何 Herdr 会话控制前检查 HERDR_ENV=1。使用当前 CLI help 确认语法,通过 caller context 取调用 pane;不以 focused pane 代替调用者。
  3. 按契约在创建 sibling 与 agent start 前选择 surface:用户明确要求交互 TUI/Agent 则 agent;否则 kind 原生非交互命令能满足验收则 pane;其余 agent。默认在调用 tab/cwd 创建一个 sibling,按布局选 right/down,保持 --no-focus。解析返回 ID,确认 shell 可用。
  4. pane surface:pane run 与非碰撞 wait,完成证据是命令退出后的输出,不是 agent idle/done。agent surface:agent start 指定 kind,确认 ready identity 后向任务自有且 idle 的 worker 发送一次完整 assignment,使用 agent prompt --wait 和有限 timeout。start 或 identity 失败时按契约检查同一 pane 并 incomplete;不重复提交或自动替换。blocked、unknown、旧输出都不能证明完成。
  5. 按契约收集完整响应,区分 passive read 与可能滚屏的 history read。只读 worker 的截断响应以小段重述恢复;文件 fallback 需要已有写权限。核验实际 scope、证据和缺失项。
  6. 交付下列 receipt,保留 worker pane。需要进一步独立分工或异常恢复时阅读 模式与恢复。提交、发布、修复、trust、更改集成或扩大清理均不因编排而获得授权。

Output Contract

  • 返回解析得到的 worker name/kind/pane identity,以及本任务创建的资源和保留状态。
  • 分开记录已观察的 lifecycle、实际任务/输入范围、收到的响应、覆盖与完整性、错误或待决事项。终端 idle/done 和任务成功是两个判断。
  • 调用者对照输入核验结果;不以多 Agent 一致意见代替证据。响应仍缺失时明确 incomplete,不把它压缩成“无问题”。

Evidence

来源与设计取舍见 调研记录,当前评估和限制见 交付记录。本包提供指令契约,不声称本地检查证明真实 server、模型执行或新会话加载。

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. today Changed 8fa705010fc1
  2. 2d ago First seen · 37 lines · 84 tokens per session scan A eb7b05b7bb04

Subscribe to this mod's changes

herdr-orchestra is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 896 once invoked, about $0.0004 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 2026-09-09.