What is agents-in-a-box AGENTS.md?

A project instruction file for Agents-in-a-Box, a setup that uses AI agents and a tool called Beads to manage development tasks.

Use it as a guide when working in an Agents-in-a-Box project to find available tasks, update their status, record follow-up work, run quality checks, and complete the required handoff steps.

It gives the agent rules for communication, issue tracking, and finishing a work session, including running checks and syncing changes with the remote code repository.

How stevengonsalvez/agents-in-a-box configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to stevengonsalvez/agents-in-a-box. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/stevengonsalvez/agents-in-a-box/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/stevengonsalvez/agents-in-a-box

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/stevengonsalvez/agents-in-a-box/agents-md/github.svg)](https://agentmods.dev/instructions/stevengonsalvez/agents-in-a-box/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/stevengonsalvez/agents-in-a-box/agents-md"><img src="https://agentmods.dev/badge/instructions/stevengonsalvez/agents-in-a-box/agents-md/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/instructions/stevengonsalvez/agents-in-a-box/agents-md"><img src="https://agentmods.dev/badge/instructions/stevengonsalvez/agents-in-a-box/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 729 This file is loaded in full into every session.

When invoked 729 The same file — it is already loaded in full.

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	$0.00729	$0.00729
Opus 5	$0.00365	$0.00365
Sonnet 5	$0.00146	$0.00146
Haiku 4.5	$0.00073	$0.00073

Measured 10d ago against content hash e4c81d7f1469, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agents-in-a-box 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 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.

AGENTS.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Communication

Caveman mode is mandatory default for all agent responses. Use caveman-full: drop articles, filler, pleasantries, and hedging; keep technical terms exact. Resume caveman after any necessary safety/clarity exception. Stop only if Stevie explicitly says normal mode or stop caveman.

Beads

This project uses bd (beads) for issue tracking. Run bd onboard to get started.

Quick Reference

bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --status in_progress  # Claim work
bd close <id>         # Complete work
bd sync               # Sync with git

Landing the Plane (Session Completion)

When ending a work session, complete ALL steps below. Work is NOT complete until git push succeeds.

MANDATORY WORKFLOW:

File issues for remaining work - Create issues for anything that needs follow-up
Run quality gates (if code changed) - Tests, linters, builds
Update issue status - Close finished work, update in-progress items

PUSH TO REMOTE - This is MANDATORY:

git pull --rebase
bd sync
git push
git status  # MUST show "up to date with origin"

Clean up - Clear stashes, prune remote branches
Verify - All changes committed AND pushed
Hand off - Provide context for next session

CRITICAL RULES:

Work is NOT complete until git push succeeds
NEVER stop before pushing - that leaves work stranded locally
NEVER say "ready to push when you are" - YOU must push
If push fails, resolve and retry until it succeeds

Fleet macOS app: validation is end-to-end or it is a failure

Testing the macOS Fleet app means driving it to a terminal user-visible outcome, not confirming it launched, connected, or rendered a card.

For an interview, exactly one of these is a pass:

It completes. The answer reaches the target session — verified in that session's JSONL tool_result (and, where it matters, the model's next message acting on it), not just a DELIVERED receipt or a line drawn in a tmux pane.
It shows the right status. The action was refused and the app says so, with the daemon's detail, matching the fleet_action_receipt row.

Read the full file on GitHub · 76 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.

10d ago First seen · 76 lines · 729 tokens per session scan A e4c81d7f1469

Subscribe to this mod's changes

agents-in-a-box AGENTS.md is an instructions file published in the GitHub repository stevengonsalvez/agents-in-a-box (23 stars, last pushed today), licensed MIT. It adds 729 tokens to every session, about $0.0036 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.

Claude Code Project management agentic-ai amazonqcli cline cursor gemini-cli

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

agents-in-a-box: Instructions file for Codex