cairn AGENTS.md

cairn AGENTS.md is an instructions file for Codex, OpenCode from isaacriehm/cairn. It costs 2,181 tokens per session, scanned A, original, MIT.

Repository guidance for coding agents working on Cairn, a tool that stores project decisions and context and makes them available to agents. It explains the project, its documents, rules, and workspace layout.

In plain words
What is it for?
Use it to orient agents, locate project documentation, follow workspace rules, and understand how Cairn connects to Claude Code, Cursor, and Codex.
Why use it?
It helps an agent understand the repository before changing code and find the right project information without guessing.

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/isaacriehm/cairn/agents-md
Clone the repo
git clone --depth 1 https://github.com/isaacriehm/cairn

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 cairn AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/isaacriehm/cairn/agents-md.svg)](https://agentmods.dev/instructions/isaacriehm/cairn/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/isaacriehm/cairn/agents-md"><img src="https://agentmods.dev/badge/instructions/isaacriehm/cairn/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,181 This file is loaded in full into every session.
When invoked 2,181 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 $0.02181 $0.02181
Opus 5 $0.01091 $0.01091
Sonnet 5 $0.00436 $0.00436
Haiku 4.5 $0.00218 $0.00218

Measured 3d ago against content hash fbe3ce081ae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cairn 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 · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cairn — Agent Orientation

This is the portable instruction entrypoint for Claude Code, Cursor, and Codex. It is the table of contents for agents working on this repo. Real content lives in docs/.

What this project is

Cairn = state + context-loading layer for AI coding agents. It curates .cairn/ground/ (decisions, §V invariants, canonical-map, brand, quality-grades), exposes that state via an MCP server, and ships a shared agent plugin that wires adoption + the daily flow inline.

Claude Code, Cursor, and Codex are supported from one plugin package and runtime. The CLI (cairn ...) is the bootstrap and debug entrypoint. There is no separate orchestration runtime; agents use their native dispatch tools.

Document index

What Where
Quick start + concepts README.md
Layered architecture (locked) docs/ARCHITECTURE.md
Plugin spec — adoption phases, hooks, multi-dev enforcement (locked) docs/PLUGIN_ARCHITECTURE.md
MCP tool surface — tool-by-tool reference docs/MCP_SURFACE.md
.cairn/ directory contract docs/FILESYSTEM_LAYOUT.md
License LICENSE

Operator profile (apply when communicating with the operator)

Trait Behavior
Communication Terse-direct. Lead with answer or action. No filler.
Decisions Fast-intuitive. Don't present options unless explicitly asked. When the operator states a decision, treat it as final.
Explanations Concise. Root cause in 1-2 sentences then the fix.
UX philosophy Design-conscious. UX is equal in importance to functional correctness.
Vendor choices Opinionated. Do not suggest alternative libraries / frameworks unless they avoid a real risk.
Env vars The operator hates env vars. Hardcode model aliases (haiku/sonnet/opus) and paths in code — never a dated ID like claude-sonnet-4-6, never an env var. Every LLM call names its tier; never inherit the session model.
Tests "Tests are shitware. Only E2E with real DB matters." Sensors + E2E smokes only — no unit-test framing.
Backward compat The operator hates backward-compat shims. Hard cutovers only.
Mobile mode When the operator is on mobile, AskUserQuestion options get truncated; switch to chat-mode A/B/C with concise option labels.
Caveman ultra mode Active for chat replies. Documents stay in full English.

Read the full file on GitHub · 168 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. 3d ago First seen · 168 lines · 2,181 tokens per session scan A fbe3ce081ae9

Subscribe to this mod's changes

cairn AGENTS.md is an instructions file published in the GitHub repository isaacriehm/cairn (6 stars, last pushed 1mo ago), licensed MIT. It adds 2,181 tokens to every session, about $0.0109 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.