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.
npx skills add xonovex/platform --skill herdr-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/herdr-guide)<a href="https://agentmods.dev/skills/xonovex/platform/herdr-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/herdr-guide/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/xonovex/platform/herdr-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/herdr-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00074 | $0.00637 |
| Opus 5.5 | $0.00030 | $0.00255 |
| Sonnet 5.5 | $0.00015 | $0.00127 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
herdr-guide 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 5d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Herdr Terminal and Agent Control
Use Herdr for the requested terminal work. Its workspaces, also called spaces, contain tabs and panes. A pane can contain a shell, an ordinary command, or a recognized coding agent.
Core Principles
- Check caller context - Require
HERDR_ENV=1before controlling a session. - Load current guidance - Run
herdr --skillunless already loaded; inspect relevant CLI help. - Use live identifiers - Parse returned IDs; target agents by unique live names.
- Choose the correct surface - Agent commands coordinate agents; pane commands control ordinary terminals.
- Preserve requested settings - Keep the specified working directory, agent, model, effort, and task.
- Preserve focus and processes - Use
--no-focusfor background changes; move existing agents without restarting them. - Verify observed behavior - Read state and output; check requested goals and produced artifacts.
Operations
- Agents: Launch agents, submit prompts or native goals, and inspect progress, see references/agents.md.
- Layout: Create or organize workspaces, tabs, and panes while preserving running processes, see references/layout.md.
- Commands: Run ordinary terminal commands and inspect their results, see references/commands.md.
Gotchas
- If the environment check fails, report that this agent is outside Herdr and stop session control. Do not attach to the user's focused session as a fallback.
- Bare
herdrlaunches the interface. Use--helpor a command group for discovery; incomplete mutating commands can execute with defaults. - Moving a pane across workspaces changes its pane ID. The inherited old caller ID can still resolve for that process; other callers must use the returned ID or live agent name.
idleanddonemean ready for input, not verified task completion.unknowndoes not prove completion.- A prompt timeout does not prove failed delivery. Inspect before retrying; an unbounded wait can run indefinitely.
- This skill does not authorize additional agents or unrelated terminal changes. Preserve the user's existing authorization and requested scope.
What ships with it
7 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.
- 5d ago First seen · 40 lines · 74 tokens per session scan A d4bb4ef93860
herdr-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 637 once invoked, about $0.0003 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 2026-10-09.
Other skills, from other repositories
windows-automation
Best-in-class Windows automation using Python (UI Automation) and AutoHotkey.
media-factory
Media processing and playback automation using FFmpeg, MPV, and AutoHotkey.
calendar-cli
Command-line calendar management using 'khal'.
vivetool-feature-flags
Enable, disable, or query Windows 11 feature experiments using ViVeTool.
life-os
How to help with goals, habits, health, focus, sleep, energy, routines and personal systems — the Life-OS domain. Use when the operator asks about building a habit, fixing their sleep or energy, structuring a week, recovering from burnout, or tracking a personal goal.
godrop
Upload a file to a GoDrop server and get a public URL back. Use when you need to share a file, screenshot, log, build artifact or report as a link, including when a user asks for "a link to this file". Also covers deleting an uploaded file and checking a GoDrop instance's health.