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 petekp/claude-code-setup --skill herdr-namesgit clone --depth 1 https://github.com/petekp/claude-code-setupWrote 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/petekp/claude-code-setup/herdr-names)<a href="https://agentmods.dev/skills/petekp/claude-code-setup/herdr-names"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/herdr-names/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/petekp/claude-code-setup/herdr-names"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/herdr-names.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 | $0.00167 | $0.01482 |
| Opus 5.5 | $0.00067 | $0.00593 |
| Sonnet 5.5 | $0.00033 | $0.00296 |
| Haiku 4.5 | $0.00017 | $0.00148 |
Grade A, and why
herdr-names scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Herdr names
Why names go stale
Herdr's sidebar is only useful when each entry says what that session is for. Three things break that:
- A new tab is labeled with a number ("1") unless someone names it.
- Claude Code rewrites the terminal title on every prompt from the latest user message. A real session showed "Address findings" after the user typed "address the findings". Out of context it says nothing.
- Workspace names already carry the project, so a tab that repeats it ("zui" under zui) adds nothing.
This skill reads what each agent is actually doing and gives the tab, its pane, and the agent one short task name each. Run it end to end without asking for confirmation. Every rename is reversible, and the user invoked it to avoid doing this by hand.
Steps
SKILL_DIR below is the base directory printed when this skill loaded.
-
Confirm you are inside Herdr with
test "${HERDR_ENV:-}" = 1. If that fails, say you are not running inside Herdr and stop. The CLI can only see the session it runs in. -
Take the snapshot:
python3 "$SKILL_DIR/scripts/herdr_names.py" snapshotIt prints every workspace, tab, and pane with current labels, the agent's name and state, cwd, git branch, terminal title, and the tail of each agent's recent output. For Claude Code panes the recap line comes first; it is the best one-line statement of what the session is for. The first lines also say whether the Agents panel is configured to show tab or pane names at all.
-
Choose names with the rules below. For your own pane, marked "[this session]", use the conversation, not the output tail.
-
Write the plan as JSON in the scratchpad and apply it:
python3 "$SKILL_DIR/scripts/herdr_names.py" apply plan.jsonAdd
--dry-runfirst when a choice feels uncertain. The script validates the whole plan before touching anything, skips names that are already in place, and prints before and after for each rename. -
Report a before → after table, one line for each tab left alone and why, and the sidebar warning if the snapshot raised one.
What ships with it
2 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.
- 23d ago First seen · 87 lines · 167 tokens per session scan A 1c15ceb3ba7e
herdr-names is a skill published in the GitHub repository petekp/claude-code-setup (48 stars, last pushed 10d ago), licensed MIT. It adds 167 tokens to every session and 1,482 once invoked, about $0.0007 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 2026-09-23.
Other skills, from other repositories
opus-rail
Session control for the FULL opus-rail system (hook-enforced variant). "/opus-rail disable" (or off) pauses every rails injection for this session; "/opus-rail enable" (or on) resumes; "/opus-rail status" reports hook telemetry and mode. Use when the user runs /opus-rail with one of those arguments. This is NOT the…
first-task
Run the first task chat that setup hands off.
initiate-setup
Run the first-run setup chat in the Hermes desktop app.
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
apple-reminders
Apple Reminders via remindctl: add, list, complete.