agent-playbook AGENTS.md

agent-playbook AGENTS.md is an instructions file for Codex, OpenCode from storious/agent-playbook. It costs 372 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining an agent playbook: a set of files that defines how an AI coding agent starts work, manages context, and records handoffs.

In plain words
What is it for?
Use them to load the right project instructions, maintain a small working set, preserve decisions and evidence, and prepare state for the next session.
Why use it?
They keep the agent focused on the active task and clarify that written configuration does not grant permissions or tools.

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/storious/agent-playbook/agents-md
Clone the repo
git clone --depth 1 https://github.com/storious/agent-playbook

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 agent-playbook AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/storious/agent-playbook/agents-md.svg)](https://agentmods.dev/instructions/storious/agent-playbook/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/storious/agent-playbook/agents-md"><img src="https://agentmods.dev/badge/instructions/storious/agent-playbook/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 372 This file is loaded in full into every session.
When invoked 372 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 $0.00372 $0.00372
Opus 5 $0.00186 $0.00186
Sonnet 5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 3d ago against content hash 1d2cbcead40b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-playbook 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 3d 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 · 37 lines

What it actually says

Agent Playbook Maintainer

Session Bootstrap

  1. Read .agents/agulater.json for the top-level Agent Operational Contract.
  2. Read .agents/AGENTS.md for the portable operating contract.
  3. Read .agents/harness.json for context, loop, tool, and checkpoint policy.
  4. Read .agents/context/core.md before orienting to a new task.
  5. Read .agents/context/task-brief.md and update the working set only for the active task.
  6. Load a matching skill from .agents/skills/ only when its description fits the task.

Context Discipline

  • Keep this root file short; it is a bootstrap route, not a full project dump.
  • Treat the active working set and handoff as compact state, not hidden memory.
  • When context pressure or a phase boundary occurs, preserve goal, evidence, decisions, verification, risk, and the next action in .agents/context/handoff.md.

Runtime Boundary

This configuration describes intended behavior. It does not grant tools, permissions, network access, file mutation, or background execution. The host runtime remains authoritative for those capabilities.

Project Rules

  • Treat .agents/agulater.json as this repository's dogfooded Agent Operational Contract.
  • Keep Agulater's owned model central: context, harness, loop, graph, capabilities, and evidence. External systems are references, not semantic authorities.
  • When changing generated contract structure, update the generator, the root dogfood kit, the research example, tests, and audit together.
  • Use Bun + TypeScript for authoring tools. Keep them local-only and do not add execution authority, model calls, or hidden memory.
  • Validate with bun run test before handing off a change.
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. 3d ago First seen · 37 lines · 372 tokens per session scan A 1d2cbcead40b

Subscribe to this mod's changes

agent-playbook AGENTS.md is an instructions file published in the GitHub repository storious/agent-playbook (2 stars, last pushed 3d ago), licensed MIT. It adds 372 tokens to every session, about $0.0019 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.