A command for putting a research question or coding task into an overnight queue for claude-overnight. Research jobs run later, while coding jobs for the current repository are placed on a reviewable overnight branch.

Use it to queue research questions, queue implementation or refactoring work for the current project, trust an approved repository, and receive confirmation that the job is scheduled.

It lets work wait until usage limits reset instead of requiring the task to run immediately. It also handles repository trust when a coding job needs permission to use the project.

queue — Command for Claude Code by rohanprichard/claude-overnight

Install

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.

Clone the repo

git clone --depth 1 https://github.com/rohanprichard/claude-overnight

Made for: Claude Code.

Or install claude-overnight, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/rohanprichard/claude-overnight/queue/github.svg)](https://agentmods.dev/commands/rohanprichard/claude-overnight/queue)

Your own site

<a href="https://agentmods.dev/commands/rohanprichard/claude-overnight/queue"><img src="https://agentmods.dev/badge/commands/rohanprichard/claude-overnight/queue/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/rohanprichard/claude-overnight/queue"><img src="https://agentmods.dev/badge/commands/rohanprichard/claude-overnight/queue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 173 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00018	$0.00173
Opus 5.5	$0.00007	$0.00069
Sonnet 5.5	$0.00004	$0.00035
Haiku 4.5	$0.00002	$0.00017

Measured 2mo ago against content hash de59d9e8606a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

queue 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 2mo 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.

commands/queue.md · 16 lines

What it actually says

Queue the user's request for the overnight batch:

If it is a research question, run overnight add "$ARGUMENTS".
If it is a coding task for the current project (implement/fix/refactor something here), run overnight add --repo "$(pwd)" "$ARGUMENTS". If the output warns the repo is not trusted, ask the user whether to trust it, and on yes run overnight trust "$(pwd)".

Then confirm it was queued and mention it will run in the next overnight window (coding jobs land on an overnight/* branch to review in the morning).

Changes

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.

2mo ago First seen · 16 lines · 18 tokens per session scan A de59d9e8606a

Subscribe to this mod's changes

queue is a command published in the GitHub repository rohanprichard/claude-overnight (13 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 173 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 2026-08-31.

Claude Code Project management anthropic automation claude cli rate-limits

queue next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
queuerohanprichard/claude-overnight	Command	13	1mo ago	MIT	A	18	Claude Code
agentloop-audit-queryalibaba/loongsuite-pilot	Command	239	yesterday	Apache-2.0	A	5	Claude Code
atomic-plandamusix/atomic-claude	Command	115	5d ago	MIT	A	54	Claude Code
follow-updamusix/atomic-claude	Command	115	5d ago	MIT	A	0	Claude Code
review-branchdamusix/atomic-claude	Command	115	5d ago	MIT	A	35	Claude Code
session-reportdamusix/atomic-claude	Command	115	5d ago	MIT	A	31	Claude Code
commitdamusix/atomic-claude	Command	115	5d ago	MIT	A	55	Claude Code