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 domanski-ai/headroom --skill rotatorgit clone --depth 1 https://github.com/domanski-ai/headroomWrote 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/domanski-ai/headroom/rotator)<a href="https://agentmods.dev/skills/domanski-ai/headroom/rotator"><img src="https://agentmods.dev/badge/skills/domanski-ai/headroom/rotator.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.00469 |
| Opus 5 | $0.00042 | $0.00234 |
| Sonnet 5 | $0.00017 | $0.00094 |
| Haiku 4.5 | $0.00008 | $0.00047 |
Grade A, and why
rotator 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 8d 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
rotator
Rotate BETWEEN connected logins for the same provider when one hits a usage
limit. Powered by the headroom CLI (https://github.com/domanski-ai/headroom).
When to fire
- The user types
/rotator(optionally/rotator <model>, defaultclaude). - A command or session fails with a session/weekly/usage-limit or 429 error.
- The user asks which account has capacity, or says they are out of usage.
What to do
- Run
headroom rotate <model>(default model family:claude). It cools the current account down until its window resets, picks the next login with PROVEN headroom, and prints the export line for the new account. - Relay the one-line result to the user exactly:
rotated <old> -> <new> (<family>); <old> cools until <reset>. - If it exits 2, every account is limited. Report the earliest reset time it printed — never silently fail, never downgrade the model.
- For a status view first, run
headroom status <model>and show the table.
Guardrails
- Never edit
~/.headroom/config.jsonby hand from this skill; account changes go throughheadroom connect/headroom setup. - Cooldowns are fail-closed: if headroom says nobody has proven capacity, believe it. Do not retry the limited account "just in case".
- The new account takes effect for NEW sessions/processes that inherit
CLAUDE_CONFIG_DIR(orCODEX_HOME). The current interactive session keeps its own login; tell the user to restart the session if they want it moved.
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.
- 8d ago First seen · 37 lines · 84 tokens per session scan A 1231022b59ef
rotator is a skill published in the GitHub repository domanski-ai/headroom (100 stars, last pushed 13d ago), licensed MIT. It adds 84 tokens to every session and 469 once invoked, about $0.0004 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
session-recap
Use when the user asks to recap, summarize, or review a Claude Code session — e.g. 'recap my last session', 'what happened in that session', 'session summary'.
standup
Use when the user asks for a standup update, work log, or activity summary — e.g. 'standup update', 'what did I work on today', 'work log', 'daily summary'.
live
Use when the user asks about running sessions, agent status, what needs attention — e.g. 'what's running', 'live status', 'which sessions need me', 'agent status', 'check on my agents', 'are my sessions done', 'anything stuck'.
workflow-creator
Turn a repeatable multi-step task into a runnable, reusable saved workflow through guided conversation, in either of two shapes — chaining existing skills/recordings (wiring each one's output into the next's input), or composing the workflow script's own primitives (agent/parallel/pipeline) directly when the task…
cron-task-creator
A scheduler for recurring octo agent tasks. Each task contains a schedule and a prompt, so octo can run an agent turn automatically at the specified times.
coaching
Use when the user asks about improving their Claude Code usage, coaching rules, or best practices — e.g. 'how can I improve', 'coaching tips', 'my coaching rules', 'add a coaching rule'.