Borrowing it
Nothing to install: this file belongs to disler/inkwell-agent-sandboxes-and-software-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/disler/inkwell-agent-sandboxes-and-software-factory/main/.claude/skills/herdr/SKILL.mdgit clone --depth 1 https://github.com/disler/inkwell-agent-sandboxes-and-software-factoryWrote 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.
[](https://agentmods.dev/skills/disler/inkwell-agent-sandboxes-and-software-factory/herdr)<a href="https://agentmods.dev/skills/disler/inkwell-agent-sandboxes-and-software-factory/herdr"><img src="https://agentmods.dev/badge/skills/disler/inkwell-agent-sandboxes-and-software-factory/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.
<a href="https://agentmods.dev/skills/disler/inkwell-agent-sandboxes-and-software-factory/herdr"><img src="https://agentmods.dev/badge/skills/disler/inkwell-agent-sandboxes-and-software-factory/herdr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 184 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Rogue Agent · line 236 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00113 | $0.04647 |
| Opus 5 | $0.00056 | $0.02323 |
| Sonnet 5 | $0.00023 | $0.00929 |
| Haiku 4.5 | $0.00011 | $0.00465 |
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
herdr
Purpose
You are driving herdr, a CLI + NDJSON socket for controlling a persistent
fleet of terminal panes (and the agents running inside them). Every workspace,
tab, and pane is a real, addressable object you can spawn, prompt, read, wait
on, and close from the command line — locally, in named sessions, or over SSH.
Unlike a plain multiplexer, herdr also tracks semantic agent state
(idle · working · blocked · done), so you can block on "the agent finished"
instead of scraping screens.
Instructions
Discover commands first (--help)
Before doing anything, run:
herdr --help
herdr <command> --help # e.g. herdr pane --help, herdr wait --help
herdr evolves fast (validated here against 0.7.1); trust --help over
memory. Never guess flags — confirm them.
When you need the full surface at once — every command's flags, the socket
API's method families, event types, environment variables, or config keys —
read references/command-reference.md
instead of running many --help calls. It's the validated lookup table
(including all reproduced gotchas); still confirm against --help if the
installed version differs from 0.7.1.
Make sure a server is running
The CLI talks to a server over ~/.config/herdr/herdr.sock. Check and start:
herdr status server # "status: running" or "not running"
herdr server & # headless server — no TUI needed to orchestrate
Anyone on the box can drive the socket — you do not need to run inside a
herdr pane to orchestrate (no permission mode to raise). Inside a pane,
HERDR_ENV=1 plus HERDR_PANE_ID / HERDR_TAB_ID / HERDR_WORKSPACE_ID
tell you where you are; use them to avoid touching your own pane.
Understand the hierarchy
Everything nests in one tree. Learn the boxes and the verbs fall out:
- Session → a persistent server (default, or named via
--session <name>). - Workspace → a project-level container. ID:
w1. - Tab → a page of panes inside a workspace. ID:
w1:t1. - Pane → one real PTY (a shell or an agent). ID:
w1:p1.
What ships with it
3 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.
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.
- 11d ago First seen · 356 lines · 113 tokens per session scan A 2cbc42c76622
herdr is a skill published in the GitHub repository disler/inkwell-agent-sandboxes-and-software-factory (154 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 4,647 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…