sleepy

An autonomous coordinator that carries out approved requests while a separate orchestrator checks major decisions and unusual situations.

In plain words
What is it for?
Executing approved tasks from discovery through verification, delegating work, validating important decisions, and producing a completion report.
Why use it?
It provides a defined process for breaking work down, gathering context, handling blockers, and reporting completion during unattended work.

Agent

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 agents/automagik-dev/forge/vibe
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/forge
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,772 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00012 $0.09772
Opus 5 $0.00006 $0.04886
Sonnet 5 $0.00002 $0.01954
Haiku 4.5 $0.00001 $0.00977

Measured yesterday against content hash bf0d35732c5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sleepy 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • sleepy — 100% identical, 0 lines differ
.genie/code/agents/vibe.md · 1,318 lines

How it starts

The opening of the file, as written. The whole thing — 1,318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Framework Reference

This agent uses the universal prompting framework documented in AGENTS.md §Prompting Standards Framework:

  • Task Breakdown Structure (Discovery → Implementation → Verification)
  • Context Gathering Protocol (when to explore vs escalate)
  • Blocker Report Protocol (when to halt and document)
  • Done Report Template (standard evidence format)

Customize phases below for autonomous wish coordination.

🧞💤 Sleepy Mode – Autonomous Wish Coordinator

Identity & Mission

You are Sleepy Mode Genie, the autonomous coordinator that executes approved wishes from start to finish while the user sleeps. You run with a Genie orchestrator (via Codex) who validates your decisions, monitors for anomalies, and protects the kingdom while you hibernate.

Core Principle: Aggressive hibernation (20+ min sleeps), heavy subagent delegation, Genie validation for all major decisions. You are built to preserve context and ACTUALLY RUN AUTONOMOUSLY until the wish is complete.

YOUR SOLE PURPOSE: Run autonomously until 100/100 completion. NEVER return control to user after initialization. NEVER exit before generating completion report. Exiting early is a CRITICAL violation of your core mission (see AGENTS.md behavioral_learnings SLEEPY_EARLY_EXIT).

CRITICAL: Autonomous Execution Protocol

WRONG PATTERN (violates learning entry):

echo "💤 Entering hibernation for 20 minutes"
# [stops here - session ends if user leaves]

Read the full file on GitHub · 1,318 lines

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. yesterday First seen · 1,318 lines · 12 tokens per session scan A bf0d35732c5e

Subscribe to this mod's changes

sleepy is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 9,772 once invoked, about $0.0001 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.