A tool for running several coding agents at the same time in separate herdr panes. Each agent can use a different account or model, while a clausona profile selects that account or model.

Use it to split coding work across multiple agents in herdr, compare their results, and retire finished workers.

It avoids waiting for one coding agent to finish before starting another. Separate panes make it possible to watch, review, and stop the workers individually.

herdr-fleet — Skill for Claude Code by larcane97/clausona

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 larcane97/clausona --skill herdr-fleet

Clone the repo

git clone --depth 1 https://github.com/larcane97/clausona

Made for: Claude Code.

Or install herdr-fleet, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/larcane97/clausona/herdr-fleet/github.svg)](https://agentmods.dev/skills/larcane97/clausona/herdr-fleet)

Your own site

<a href="https://agentmods.dev/skills/larcane97/clausona/herdr-fleet"><img src="https://agentmods.dev/badge/skills/larcane97/clausona/herdr-fleet/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/larcane97/clausona/herdr-fleet"><img src="https://agentmods.dev/badge/skills/larcane97/clausona/herdr-fleet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,156 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.

Model	Per session	Once invoked
Fable 5.1	$0.00105	$0.02156
Opus 5.5	$0.00042	$0.00862
Sonnet 5.5	$0.00021	$0.00431
Haiku 4.5	$0.00011	$0.00216

Measured 9d ago against content hash c88e3b71f321, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

herdr-fleet 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 9d 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.

plugins/herdr-fleet/skills/herdr-fleet/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

herdr fleet on clausona profiles

herdr runs agents in panes and shows their state in its sidebar. clausona puts each pane's agent on the profile you choose.

0. Load the shared rules

Load the fleet-core skill first and follow it; this skill only adds the herdr steps. In Claude Code, invoke it with the Skill tool. If that fails, or you run in Codex, read the first of these files that exists, where <base> is this skill's base directory:

<base>/../../../fleet-core/skills/fleet-core/SKILL.md
<base>/../../../../fleet-core/*/skills/fleet-core/SKILL.md (if several versions match, read the highest)

If none exists, stop and tell the user to install it: claude plugin install fleet-core@clausona in Claude Code, or codex plugin add fleet-core@clausona in Codex.

1. Before anything

Stop and tell the user what is missing if any of these fails.

You run inside a herdr pane: HERDR_ENV is 1 (test "${HERDR_ENV:-}" = 1; in PowerShell, $env:HERDR_ENV -eq '1'). herdr's CLI talks to the session of the pane it runs in. Do not control herdr from outside it. In Codex, HERDR_ENV is also unset when Codex hides the environment (fleet-core, Shells). If it does, do not tell the user they are outside herdr: tell them to start Codex again in this pane with -c shell_environment_policy.inherit=all.
herdr status shows a running server. Before a command group's first use, run the group alone (herdr worktree, herdr workspace, herdr agent, herdr pane) to see its current syntax. Never run bare herdr: it starts the interface.
The repo has a remote: workers push their branches.

herdr commands print JSON. Read ids and paths from it; never guess them. herdr runs on macOS, Linux and Windows, and the commands below are the same on each.

2. Starting a worker

For each task, after fleet-core picked its profile:

Worktree. herdr worktree create --cwd <repo> --branch fleet/<task> --label "<task> · <profile>" --no-focus. Keep the label to 20 characters or fewer, with a short task word such as docs · ds-flash: herdr's agents list cuts longer labels, and the profile at the end is what shows which account runs where. Record .result.workspace.workspace_id, .result.root_pane.pane_id and .result.worktree.path. The worktree lands under ~/.herdr/worktrees/.
Start. herdr pane run <pane> "clausona run <profile> -- <args>", with the arguments from fleet-core section 4. Codex workers keep --disable hooks.
Check it started. Within 20 seconds, herdr agent list shows the pane with agent claude or codex. If not, read the pane (herdr pane read <pane> --source recent-unwrapped --lines 60). If the launch line never ran, for example because the shell was still starting, run it once more. Otherwise tell the user what the screen shows.
Name it. herdr agent rename <pane> <name>, with a name such as w1-docs: lowercase letters, digits, - or _, starting with a letter, up to 32 characters. Use the name from now on.
Folder trust. The first worker of a profile in a repo that profile never trusted asks whether to trust the folder, and herdr shows it as blocked. Read the screen (herdr agent read <name> --source visible) and answer only that question, and only about this repository:
- Claude Code ("Is this a project you created or one you trust?"): the highlighted answer is "No, exit". Send herdr agent send-keys <name> down enter.
- Codex ("Trust this folder?"): the highlighted answer is "1. Trust and continue". Send herdr agent send-keys <name> enter.

Read the full file on GitHub · 131 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.

9d ago Changed · +7 lines c88e3b71f321
16d ago First seen · 124 lines · 105 tokens per session scan A 326193c4aa2e

Subscribe to this mod's changes

herdr-fleet is a skill published in the GitHub repository larcane97/clausona (57 stars, last pushed 5d ago), licensed MIT. It adds 105 tokens to every session and 2,156 once invoked, about $0.0004 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 2026-10-10.

Building agents Claude Code account-manager account-switcher ai-coding claude cli

repo-hygiene

Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.

QwenLM/qwen-code · 48 tokens

test-failure-explorer

Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.

QwenLM/qwen-code · 32 tokens

requirements-writer

Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.

mvschwarz/openrig · 28 tokens

refocusing

Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.

mvschwarz/openrig · 59 tokens

orchestration-team

Use when coordinating assignments, selected review boundaries, or blocked work across a rig.

mvschwarz/openrig · 21 tokens

oversight-team

Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…

mvschwarz/openrig · 117 tokens