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 atman-33/workhub --skill setup-herdrgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/setup-herdr)<a href="https://agentmods.dev/skills/atman-33/workhub/setup-herdr"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/setup-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/atman-33/workhub/setup-herdr"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/setup-herdr.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 | $0.00059 | $0.02017 |
| Opus 5.5 | $0.00024 | $0.00807 |
| Sonnet 5.5 | $0.00012 | $0.00403 |
| Haiku 4.5 | $0.00006 | $0.00202 |
Grade D, and why
setup-herdr scanned grade D with 3 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://herdr.dev/install.sh | sh Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Claude Code integration** (Windows and WSL): read `~/.claude/settings.json` directly Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://herdr.dev/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Install herdr (https://herdr.dev), a terminal-native agent multiplexer, wire up its
Claude Code / OpenCode integrations, and configure shell profiles so herdr launches
automatically on startup — replacing any existing Zellij autostart installed by
setup-zellij.
Environment note: this session can be hosted on either side
This skill touches both a Windows environment and a WSL environment, and the agent session driving it can be hosted on either — the interop direction flips accordingly:
- Hosted in WSL: reach Windows via
powershell.exe/pwsh.exe, and read/edit Windows profile files directly at their/mnt/c/...path rather than shelling a multi-line edit throughpowershell.exe -Command— quoting an edit through a nested shell is fragile; a direct file edit is not (the same class of problem step 4's here-string warning describes). - Hosted on Windows: reach WSL via
wsl -- <command>, as this skill's snippets show by default.
Determine which applies once, then use the matching direction for every step below.
The same preference — direct file access over a shell-quoted command — also applies to
the idempotency checks in steps 1, 3, and 4: read a file's content and inspect it
rather than piping it through grep/Select-String across the interop boundary.
Steps
1. Check herdr installation (per environment)
A PATH-only check false-negatives: herdr's own installer doesn't add itself to PATH
(see step 2), so the binary can be present — even running — without Get-Command/
which finding it. Check, in order, until one hits:
Windows: Get-Command herdr -ErrorAction SilentlyContinue → known install dirs
(e.g. Test-Path "$env:LOCALAPPDATA\Programs\Herdr\bin\herdr.exe") → a running process
(Get-Process herdr -ErrorAction SilentlyContinue).
WSL: which herdr → $HOME/.local/bin/herdr (the installer's default target).
Record whichever path resolved it — step 4 needs it to invoke herdr if it never lands on PATH. If found by any check, mark the environment "already installed" and skip to step 3 for it. Only when every check is empty, continue to step 2 for that environment.
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.
- 1mo ago First seen · 184 lines · 59 tokens per session scan D 7008e6f10f45
setup-herdr is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 2,017 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.
wiki-orchestrate
A coordinator for organizing an Obsidian vault, which is a folder of linked Markdown notes, by first checking its structure and then arranging the notes.
kb-preferences
Use when user wants to view, update, reset, or audit report preferences stored in vault kb.yaml. Triggers on '/kb-preferences', 'update report prefs', 'change report style', 'my preferences', or when a passive reflection step in another skill needs to propose preference updates.
aetox-teach
สอนคนใช้ Aetox — ทำอะไรได้บ้างในคำที่คนเข้าใจ ห้องไหนไว้ทำอะไร ห้าอย่างที่คนใหม่ต้องรู้ และวิธีสอนด้วยการลงมือทำงานจริงของเขาแทนการบรรยาย · อ่านเมื่อผู้ใช้ถามว่าแอปนี้ทำอะไรได้ ถามวิธีใช้ หรือเพิ่งเปิดครั้งแรก.
aetox-orient
ตอนเข้าโปรเจกต์ที่ยังไม่ได้อ่านในบทสนทนานี้ หรือกลับมาสานต่อหลังเว้นไป — ก่อนแตะไฟล์แรก.