Borrowing it
Nothing to install: this file belongs to EricAndrechek/Pacer. 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/EricAndrechek/Pacer/main/.claude/skills/account-rotation/SKILL.mdgit clone --depth 1 https://github.com/EricAndrechek/PacerWrote 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/ericandrechek/pacer/account-rotation)<a href="https://agentmods.dev/skills/ericandrechek/pacer/account-rotation"><img src="https://agentmods.dev/badge/skills/ericandrechek/pacer/account-rotation/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/ericandrechek/pacer/account-rotation"><img src="https://agentmods.dev/badge/skills/ericandrechek/pacer/account-rotation.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 | $0.00075 | $0.03257 |
| Opus 5.5 | $0.00030 | $0.01303 |
| Sonnet 5.5 | $0.00015 | $0.00651 |
| Haiku 4.5 | $0.00007 | $0.00326 |
Grade A, and why
account-rotation 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.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Account rotation
Read $ROTATE_HOME/LOCAL.md for this machine's owner rules before acting; they
override defaults here.
A detached bash controller does the switching. No model is needed for that: it
reads usage every minute, decides, and runs cswap switch. Your job is to keep
it running, watch what it does, and handle the people and sessions around it.
Requirements
- macOS with more than one Claude login managed by
claude-swap (
cswap, a version withcswap list --json). Without it there is nothing to rotate. - Pacer, for burn rates and fresher readings through its local API
(
http://127.0.0.1:7223/metrics). Without it the controller still runs on cswap's readings and assumesBURN_UNKNOWN. - bash 4+ at
/opt/homebrew/bin/bash(associative arrays),jq,python3. analysis/only:uv(it runs withuv run --with duckdb --with pyarrow) and theduckdbCLI for the queries.
Install
Run the controller and watcher from a copy outside git, so a branch switch or a pruned worktree never pulls a script out from under a running process:
mkdir -p ~/.local/state/pacer-account-rotation/bin
cp rotate.sh watch.sh stuck.py burn.py ~/.local/state/pacer-account-rotation/bin/
cp -n rotate.conf.example ~/.local/state/pacer-account-rotation/rotate.conf
Re-copy after changing the tracked scripts, then stop and start.
Commands
D=.claude/skills/account-rotation # from the repo root
$D/rotate.sh status # running? last status/switch lines, active account
$D/rotate.sh start "why" # detached; survives the starting session and a Claude Code restart
$D/rotate.sh stop
$D/rotate.sh log 30 # last 30 lines of state/rotate.log
$D/rotate.sh dry # one decision pass on live readings, printed; never switches
$D/watch.sh 55 # run in the background: EXITS on something to act on (the wake)
python3 -I $D/burn.py 60 # who is spending the 5h window: per-session weight, ctx, turns/h
python3 -I $D/stuck.py 6 # main sessions whose last turn was a usage-limit stop
$D/tests.sh <script> # decision tests against a fake cswap, e.g. tests.sh $D/rotate.sh
What ships with it
10 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.
- 7d ago First seen · 218 lines · 75 tokens per session scan A 0d06c224d446
account-rotation is a skill published in the GitHub repository EricAndrechek/Pacer (11 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 3,257 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 2026-10-22.
Other skills, from other repositories
vellum-memory-v2-migration
Perform a one-time migration from memory v1, to memory v2, which was introduced in 0.8.0.
vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
memory-corpus-ingest
Ingest a large dataset into memory as a skimmed map. Cold-store the raw files under a workspace imports directory, census them into a slice plan, skim each slice into compact map pages that point back at the raw files, ingest the map with the memory ingest CLI, and author a drill-in retrieval skill so the corpus stays…
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.