babysitter AGENTS.md

babysitter AGENTS.md is an instructions file for Codex, OpenCode from a5c-ai/babysitter. It costs 305 tokens per session, scanned A, original, MIT.

Repository-specific instructions for AI coding agents working in the a5c-ai/babysitter project.

In plain words
What is it for?
They help agents use the Babysitter skill, handle unclear requirements, avoid unwanted shell subtasks, and run the project's build, test, and metadata checks.
Why use it?
They give agents the project's required workflow, exceptions, reference documents, and verification commands instead of leaving those decisions implicit.

Instructions file for CodexOpenCode

About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,769 stars · on GitHub

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/a5c-ai/babysitter/agents-md
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

Made for: Codex, OpenCode.

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.

agentmods badge for babysitter AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/a5c-ai/babysitter/agents-md.svg)](https://agentmods.dev/instructions/a5c-ai/babysitter/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/a5c-ai/babysitter/agents-md"><img src="https://agentmods.dev/badge/instructions/a5c-ai/babysitter/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 305 This file is loaded in full into every session.
When invoked 305 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 $0.00305 $0.00305
Opus 5 $0.00152 $0.00152
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured 5d ago against content hash c6e13469be42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

babysitter 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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 32 lines

What it actually says

AGENTS.md

This file is the short entrypoint for AI coding agents working in this repository.

Always use the Babysitter skill to fulfill user requests in this repo, but not agent-to-agent delegated requests.

Repo-Specific Overrides

  • For babysitter:call processes in this repo, do not generate kind: 'shell' subtasks unless the user explicitly asks for a shell-oriented workflow.
  • Keep breakpoints sparse. Use them only when user input is genuinely critical or ambiguous.
  • Still include an interview phase when requirements are unclear.

Those rules are captured in more detail in docs/agent-reference/process-authoring.md.

Reference Map

Quick Commands

npm run build:sdk
npm run test:sdk
npm run verify:metadata
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. 5d ago First seen · 32 lines · 305 tokens per session scan A c6e13469be42

Subscribe to this mod's changes

babysitter AGENTS.md is an instructions file published in the GitHub repository a5c-ai/babysitter (1,769 stars, last pushed today), licensed MIT. It adds 305 tokens to every session, about $0.0015 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.