Borrowing it
Nothing to install: this file belongs to espennilsen/pi. 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/espennilsen/pi/main/.pi/skills/herdr-operations/SKILL.mdgit clone --depth 1 https://github.com/espennilsen/piWrote 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/espennilsen/pi/herdr-operations)<a href="https://agentmods.dev/skills/espennilsen/pi/herdr-operations"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/herdr-operations.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00492 |
| Opus 5 | $0.00016 | $0.00246 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
herdr-operations 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 7d 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.
What it actually says
Herdr Operations
Inspect state before acting. Use the installed CLI help as the authority for the current version.
Safe discovery
herdr status
herdr session list --json
herdr workspace list
herdr pane list
herdr agent list
If one command fails, do not try invented alternatives. Run herdr --help, then the relevant command group's --help; if needed, use the upstream docs fallback.
Choose the right target
| Need | Use |
|---|---|
| Coding-agent state, output, or message | herdr agent … |
| Server, test, shell, or low-level terminal control | herdr pane … |
| Submit a shell command atomically | herdr pane run <pane_id> <command> |
| Read logs without soft wrapping | --source recent-unwrapped |
Common workflows
Inspect an agent, then use the installed agent-message command:
herdr agent list
herdr agent get <target>
herdr agent read <target> --source recent-unwrapped --lines 120
herdr agent --help
herdr agent <installed-message-command> <target> "<message>"
For example, documented releases have used agent send; newer releases may expose another message command. Use the spelling and argument order from local help.
Create an unfocused workspace or split pane so current work remains visible:
herdr workspace create --cwd <path> --label <label> --no-focus
herdr pane split <pane_id> --direction right --no-focus
Wait rather than polling:
herdr agent wait <target> --until idle --timeout 300000
herdr pane wait-output <pane_id> --match "<text>" --timeout 300000
Safety
- Read output before sending input to an agent.
- Use
pane runinstead of separate text and Enter events for shell commands. - Ask before stopping/deleting sessions or closing workspaces, tabs, or panes.
- Treat agent messages as literal terminal input; do not send destructive instructions without explicit user approval.
What ships with it
1 file 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.
- 7d ago First seen · 65 lines · 32 tokens per session scan A 75262478528f
herdr-operations is a skill published in the GitHub repository espennilsen/pi (117 stars, last pushed 14d ago), licensed MIT. It adds 32 tokens to every session and 492 once invoked, about $0.0002 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.