intelig-agent-playbook AGENTS.md

intelig-agent-playbook AGENTS.md is an instructions file for Codex, OpenCode from InteliGHQ/intelig-agent-playbook. It costs 1,227 tokens per session, scanned A, original, MIT.

A compact AGENTS.md guide that gives coding agents the essential context for a customer-platform codebase, including its architecture, current work, and key rules. AGENTS.md is a file that many coding assistants read automatically.

In plain words
What is it for?
Use it to define a project's purpose, domain boundaries, lifecycle states, coding priorities, and where important documentation lives.
Why use it?
It keeps agents oriented on every turn without loading a large document. It also points them to deeper documentation when they need more detail.

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/intelighq/intelig-agent-playbook/agents-md
Clone the repo
git clone --depth 1 https://github.com/InteliGHQ/intelig-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 intelig-agent-playbook AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/intelighq/intelig-agent-playbook/agents-md.svg)](https://agentmods.dev/instructions/intelighq/intelig-agent-playbook/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/intelighq/intelig-agent-playbook/agents-md"><img src="https://agentmods.dev/badge/instructions/intelighq/intelig-agent-playbook/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,227 This file is loaded in full into every session.
When invoked 1,227 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 $0.01227 $0.01227
Opus 5 $0.00613 $0.00613
Sonnet 5 $0.00245 $0.00245
Haiku 4.5 $0.00123 $0.00123

Measured 4d ago against content hash f0eeb7bce72b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intelig-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 4d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Customer Platform — Agent Context

This is the canonical context file. Every agent reads it (Claude Code reads it via the @AGENTS.md line in CLAUDE.md; Codex, Cursor, Copilot, Gemini CLI, Aider and others read AGENTS.md natively). Keep it lean — it loads on every turn. Put detail in the files it links to, not here.

What you are working on

Fork note — replace this block with your product. One or two sentences: what the system is, the bounded context this repo owns, and its core lifecycle/invariants. Keep it tight; it loads on every turn. Pattern: "A <kind of system>. This codebase is its <Context> context: <what it does>, moving them through <STATE → STATE → STATE>. Small surface, real invariants."

Example used throughout this repo: a B2B SaaS backend whose Customer context registers a customer (a company + a primary contact) and moves it through PENDING → ACTIVE → SUSPENDED — a teaching example for building cleanly with an agent.

Prime directives

  1. Spec before code. Work is organized by domain: each bounded context lives in product/domains/<domain>/ (its README.md is the durable description), and keeps its spec-first work-items in product/domains/<domain>/work-items/<work-item>/ (requirements → design → tasks → acceptance). Read the spec; implement one task at a time; stop at the acceptance gate. Don't invent scope the spec doesn't ask for.
  2. Standards are law. Before writing code in an area, read the matching family in standards/ (start at standards/STANDARDS_INDEX.md → it tells you which families apply). Cite the rule ID where it clarifies intent (commit, PR, or a brief code comment, e.g. // DOM-002: factory method, no public constructor). Rule IDs read <FAMILY>-<NNN> — families are ARCH DOM CQRS API ES DB TS, each listed in standards/STANDARDS_DIGEST.md (so DOM-002 = the 2nd rule in the domain-model family).
  3. Advisory vs enforced. Rules here are advisory. The mandatory ones are enforced by fitness-function tests (see standards/architecture.rules.md → Enforcement Map). If a test would stop you, the rule is not optional. If you keep wanting to break a rule, that's a signal to change the test, not to sneak past it.
  4. Tag work to strategy. Active initiatives are in product/initiatives.md (the session hook prints them for you). Reference the initiative ID in the commit subject so code links back to why it exists.

Read the full file on GitHub · 78 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. 4d ago First seen · 78 lines · 1,227 tokens per session scan A f0eeb7bce72b

Subscribe to this mod's changes

intelig-agent-playbook AGENTS.md is an instructions file published in the GitHub repository InteliGHQ/intelig-agent-playbook (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,227 tokens to every session, about $0.0061 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.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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