herdr-dispatch

herdr-dispatch is a skill for Claude Code, Codex from pivoshenko/pivoshenko.ai. It costs 123 tokens per session (1,475 once invoked), scanned A, original, MIT.

A workflow for splitting a task list across several parallel agent panes, collecting their results, checking them, and cleaning up. A pane is a separate terminal area where one worker can operate.

In plain words
What is it for?
Use it when several tasks can be worked on at the same time, such as independent coding or investigation tasks. It is designed for the Herdr environment and falls back to an Agent tool outside it.
Why use it?
It provides a controlled way to divide independent work without overcrowding the main working area. It also handles workspace limits, blocked workers, result collection, and verification.

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 when several tasks can be worked on at the same time, such as independent coding or investigation tasks. It is designed for the Herdr environment and falls back to an Agent tool outside it.

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

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-dispatch

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/herdr-dispatch"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/herdr-dispatch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,475 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 $0.00123 $0.01475
Opus 5 $0.00062 $0.00737
Sonnet 5 $0.00025 $0.00295
Haiku 4.5 $0.00012 $0.00147

Measured yesterday against content hash 43e57f755557, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

herdr-dispatch 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 yesterday.

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/herdr-dispatch/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Herdr Dispatch

Budget -> split -> start -> brief -> collect -> verify -> clean up.

The Herdr instruction decides that subagents become panes. This decides how. Policy lives there; do not restate it here.

Preconditions

test "${HERDR_ENV:-}" = 1                                  # else: not inside Herdr, stop
printf '%s\n' "$HERDR_WORKSPACE_ID" "$HERDR_TAB_ID" "$HERDR_PANE_ID"

Not inside Herdr -> say so and fall back to the Agent tool. Never control a Herdr session from outside it.

Pane Budget

Claude Code's TUI is unusable below ~60 columns; budget at 68 so a worker can render a diff rather than merely survive. Splitting a tab N ways divides its width by N.

Workers belong in their own tab — the user's driving pane stays uncluttered and their focus stays where they put it. Create that tab first, then measure it:

herdr tab create --label "workers" --cwd "$PWD" --no-focus   # -> .result.tab, .result.root_pane
herdr pane layout --pane "<root-pane-id>"                    # -> .result.layout.area.width

Measure the worker tab's root pane, never $HERDR_PANE_ID. Your own pane is whatever width the user's current split happened to leave it; a fresh tab spans the terminal. Budgeting off your pane under-counts and you spawn fewer workers than actually fit.

Tab width 2 panes 3 panes 4 panes
136 68 — ok 45 — too narrow 34 — unusable

Budget = floor(width / 68), minimum 1. More workers than that -> a second tab, never thinner splits.

Tasks beyond the budget wait for a free pane. Reuse a finished worker's pane — an idle agent takes a new prompt — or close it and split fresh. Never queue two tasks into one live agent; it serializes them and you lose the point.

Split

Wide pane -> right. Narrow or tall -> down. Avoid repeated same-direction splits that produce unusable slivers.

herdr pane split --current --direction right --cwd "$PWD" --no-focus
# -> .result.pane.pane_id

Read the full file on GitHub · 132 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. yesterday First seen · 132 lines · 123 tokens per session scan A 43e57f755557

Subscribe to this mod's changes

herdr-dispatch is a skill published in the GitHub repository pivoshenko/pivoshenko.ai (4 stars, last pushed 2d ago), licensed MIT. It adds 123 tokens to every session and 1,475 once invoked, about $0.0006 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 2026-09-11.

Related

Other skills, from other repositories

80-livekit-agents-majiayu000-claude-skill-registr

Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.

majiayu000/claude-skill-registry · 18 tokens

agent-creation-skill

Procedural guide for creating new agents from templates when project complexity requires delegation.

majiayu000/claude-skill-registry · 0 tokens

agent-creator

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use…

majiayu000/claude-skill-registry · 84 tokens

nx-monorepo

Provides comprehensive Nx monorepo management guidance for TypeScript/JavaScript projects. Use when creating Nx workspaces, generating apps/libraries/components, running affected commands, setting up CI/CD, configuring Module Federation, or implementing NestJS backends within Nx.

giuseppe-trisciuoglio/developer-kit · 55 tokens

turborepo-monorepo

Provides comprehensive Turborepo monorepo management guidance for TypeScript/JavaScript projects. Use when creating Turborepo workspaces, configuring turbo.json tasks, setting up Next.js/NestJS apps, managing test pipelines (Vitest/Jest), configuring CI/CD, implementing remote caching, or optimizing build performance…

giuseppe-trisciuoglio/developer-kit · 76 tokens

loom-usage

Meta-orchestration skill for Claude driving loom itself.

cosmix/loom · 15 tokens