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.
git clone --depth 1 https://github.com/rhan1/crewlineWrote 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/commands/rhan1/crewline/forecast)<a href="https://agentmods.dev/commands/rhan1/crewline/forecast"><img src="https://agentmods.dev/badge/commands/rhan1/crewline/forecast/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/commands/rhan1/crewline/forecast"><img src="https://agentmods.dev/badge/commands/rhan1/crewline/forecast.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 | $0.00029 | $0.00435 |
| Opus 5.5 | $0.00012 | $0.00174 |
| Sonnet 5.5 | $0.00006 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
forecast 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 10d 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
Run the usage forecast and explain it in plain English.
node ~/.claude/scripts/quota-forecast.mjs
Then give a short read-out — the call, not the arithmetic:
- What's full — any window marked FULL/OVER/TIGHT: which sessions' jobs fill it and when it frees up (the reset time).
- What's waiting — jobs in the "waiting" list, whose they are, and when they start on their own (they re-check every 2 minutes and start the moment they fit; nothing needs doing).
- What to do — usually nothing. Say so. Only if an urgent job is waiting: re-run it with
DISPATCH_PRIORITY=pin, orDISPATCH_ADMIT=offto force it.
If asked "will X fit?", answer with a dry run, e.g.:
node ~/.claude/scripts/quota-forecast.mjs --admit --provider codex --tier high --size L --task what-if --dry-run
(--provider agy --tier flash for Gemini; sizes S/M/L/XL.)
Claude agents: running Claude subagents (all sessions) are counted on the Claude 5h row; they never wait — the agent router just avoids sending work to a 5h window that is already spoken for. The "Window sizes" line says whether the daily re-measure of each window's size changed anything.
How it decides (for questions): the caller picks the model from the task's needs; the forecast only decides when a job starts. It never switches vendor or downgrades a model. First come, first served; while another project is waiting, no project takes more than its fair share; a DISPATCH_PRIORITY=pin job goes first; a running job is never stopped. A job may fill a window to 85 % (100 % in the window's last hour).
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.
- 10d ago First seen · 26 lines · 29 tokens per session scan A a68e64c0d140
forecast is a command published in the GitHub repository rhan1/crewline (2 stars, last pushed 11d ago), licensed MIT. It adds 29 tokens to every session and 435 once invoked, about $0.0001 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 2026-10-26.
Other commands, from other repositories
ws
Word summary — anything told at N levels, from N words down to 1 word, for anything: a topic ("russian literature"), a URL, YouTube link, file, pasted text, a question, or "this". A leading number sets N (5 by default). Shortcut for the Fabric skill's WordSummary intent.
cancel-ralph
Cancel active Ralph Loop.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.
stuck
You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.
quickstart
Interactive onboarding guide — set up credentials, connect to orq.ai, and learn every command and skill.