PromptQueue AGENTS.md

Repository instructions for PromptQueue, a tool that saves prompts for delivery at a specified local time to an AI service. A prompt is the text given to an AI to request work.

In plain words
What is it for?
Use them when scheduling a prompt for Claude, Claude Code, Codex, or another supported target, especially when AI usage limits reset later.
Why use it?
They preserve quoted or multiline prompts correctly and ensure a runner is active when a queued prompt becomes due.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/atharvamaik/promptqueue/agents-md
Clone the repo
git clone --depth 1 https://github.com/AtharvaMaik/PromptQueue

Made for: Codex, OpenCode.

Per session 434 This file is loaded in full into every session.
When invoked 434 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00434 $0.00434
Opus 5 $0.00217 $0.00217
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00043 $0.00043

Measured 2d ago against content hash 5a645d83a976, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

PromptQueue AGENTS.md 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 2d 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.

AGENTS.md · 69 lines

What it actually says

PromptQueue Agent Instructions

Use this repo to schedule prompts for later delivery through promptqueue.py.

When To Use

When the user says their AI limits reset at a time, asks to send/paste a prompt later, or asks to queue a prompt for an AI tool, schedule it here.

Example user request:

my limits reset at 7:30 pm, schedule prompt "ABC"

Schedule

Run commands from the repo root.

Prefer --stdin so quoted and multiline prompts survive shell parsing:

@'
ABC
'@ | python promptqueue.py add --stdin 19:30 TARGET

Use local machine time. Convert natural times like 7:30 pm to 19:30. HH:MM schedules today if still future, otherwise tomorrow. Use a dated time when the user gives a date:

@'
ABC
'@ | python promptqueue.py add --stdin "2026-06-24 19:30" TARGET

After queueing, make sure a runner will be alive when the job is due:

python promptqueue.py run

Use run --once only for already-due jobs or smoke tests.

Targets

Infer the target from the user's wording. If no target is named, use the AI tool the user is currently talking to when it has a matching target.

claude       Claude web UI
claude-code  Claude CLI
codex        Codex desktop UI
codex-exec   Codex CLI
cursor       Cursor UI
antigravity  Google Antigravity UI
chatgpt      ChatGPT web UI
gemini       Gemini web UI
copilot      Copilot web UI
copy         clipboard only; use only if asked

Run this if target availability is unclear:

python promptqueue.py targets

Use --no-submit only when the user asks to paste but not send.

After scheduling, tell the user the printed job id, target, and scheduled time.

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.

  1. 2d ago First seen · 69 lines · 434 tokens per session scan A 5a645d83a976

Subscribe to this mod's changes

PromptQueue AGENTS.md is an instructions file published in the GitHub repository AtharvaMaik/PromptQueue (7 stars, last pushed 1mo ago), licensed MIT. It adds 434 tokens to every session, about $0.0022 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 2026-08-31.