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.
npx agentmods add instructions/isaacriehm/cairn/agents-mdgit clone --depth 1 https://github.com/isaacriehm/cairnWrote 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.
[](https://agentmods.dev/instructions/isaacriehm/cairn/agents-md)<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>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 | $0.02181 | $0.02181 |
| Opus 5 | $0.01091 | $0.01091 |
| Sonnet 5 | $0.00436 | $0.00436 |
| Haiku 4.5 | $0.00218 | $0.00218 |
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.
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. |
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.
- 3d ago First seen · 168 lines · 2,181 tokens per session scan A fbe3ce081ae9
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.
Other instructions, from other repositories
hindsight CLAUDE.md
Claude Code instructions for vectorize-io/hindsight, covering claude.md, project overview, development commands, local development (api + ui) and start both api server and control plane ui.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.
dense-mem AGENTS.md
Instructions for markhuangai/dense-mem, covering dense-mem repository guidance, project context, architecture decision records, current stack and target architecture.
brainlayer AGENTS.md
Instructions for EtanHey/brainlayer, covering brainlayer — a letter from etan, brainlayer agent notes (operational), review guidelines, key paths and database.
mnemonic memory-files.instructions.md
Instructions for modeled-information-format/mnemonic, covering memory file guidelines (mif level 3), required frontmatter fields, optional temporal fields, optional provenance fields and memory types.