herdr

herdr is a skill for Claude Code from happyhappy-jun/writing-driven-autoresearch. It costs 208 tokens per session (4,309 once invoked), scanned A, original, Apache-2.0.

A tool for coordinating multiple AI coding agents in terminal panes, either on one computer or across computers connected by SSH. It tracks their sessions, restores layouts, and can mirror remote agents locally.

In plain words
What is it for?
Use it to discover and restore agent workspaces, monitor local agents, review their prompts, and connect to persistent agents on remote servers.
Why use it?
It removes the need to manage many terminal windows and remote connections by hand. It also helps recover stalled agents and apply consistent permission and idle rules.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Part of the alin plugin — 2 skills, 2 hooks shipped together

Good fit Use it to discover and restore agent workspaces, monitor local agents, review their prompts, and connect to persistent agents on remote servers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/happyhappy-jun/writing-driven-autoresearch/herdr
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 happyhappy-jun/writing-driven-autoresearch --skill herdr
Clone the repo
git clone --depth 1 https://github.com/happyhappy-jun/writing-driven-autoresearch

Made for: Claude Code.

Or install alin, the plugin that ships this one along with the rest of its 2 skills, 2 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/herdr/github.svg)](https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/herdr)
Your own site
<a href="https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/herdr"><img src="https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/herdr/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/herdr"><img src="https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/herdr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 208 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,309 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 $0.00208 $0.04309
Opus 5 $0.00104 $0.02155
Sonnet 5 $0.00042 $0.00862
Haiku 4.5 $0.00021 $0.00431

Measured 10d ago against content hash 0be0e3db6773, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

herdr 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 10d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/attach-herdr-agent.sh, scripts/herdr_sync.py, scripts/herdr-act.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

alin-skills/skills/herdr/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

herdr — multi-agent terminal orchestration

herdr is an open-source terminal workspace manager for AI coding agents (panes, tabs, named persistent sessions, agent detection, --remote ssh attach). This skill adds the orchestration layer herdr does not ship natively. It supports two topology shapes, which can coexist:

  • Local-only — several agents in panes on one herdr server, no ssh. The skill can watch them, read their prompts, auto-judge (approve/deny/dismiss), and nudge a wedged agent — all without ssh.
  • Remote-bridge — agents that run persistently on a remote host (over ssh) mirrored into your local agents tab; herdr has no cross-machine federation, so the skill bridges it with status mirroring + clean per-agent attach views.

On top of either shape: topology discovery, idempotent revival, and policy-driven permission and idle handling.

Everything is driven by a bundled tool: python3 ${CLAUDE_SKILL_DIR}/scripts/herdr_sync.py <cmd>. It is config-driven, not hardcoded — the topology lives in ~/.config/herdr-mgr/topology.json (override the dir with $HERDR_MGR_HOME). Run herdr_sync.py schema to see the format.

Core abilities

  1. Bootstrap — ensure herdr is installed and the agent integration is active.
  2. Topology discovery & memory — detect the live topology and persist it (to the config file and your memory) so later sessions don't re-derive it.
  3. Pane / layout management — build and idempotently revive the workspace, panes, labels, and splits after a restart.
  4. Cross-server wiring (the non-native core, remote only) — mirror remote agents' status into local panes and keep clean per-agent attach views alive over ssh.
  5. Inter-agent communication — relay text/commands between agents and panes.
  6. Liveness & permission monitoring — surface agents that newly block or stall (local and remote alike), scoped to configured agents.
  7. Policy-driven auto-judgment & nudging — approve/deny/dismiss blocked agents' permission prompts against a user policy; prod idle/wedged agents; escalate the rest.
  8. Lifecycle — start/resume agents; provision allowlistable scripts; install/remove the self-healing mirror daemon (remote only).

Read the full file on GitHub · 267 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 267 lines · 208 tokens per session scan A 0be0e3db6773

Subscribe to this mod's changes

herdr is a skill published in the GitHub repository happyhappy-jun/writing-driven-autoresearch (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 208 tokens to every session and 4,309 once invoked, about $0.0010 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens