A development guide for repositories that use Cairn, a tool that compares a declared architecture map with the actual code.

Navigating the architecture, adding or moving files, recording decisions or todos, investigating Cairn findings, and running its scan and commit checks.

It shows agents how to understand the project, interpret architecture findings, and check that changes keep the map and code aligned.

How sdotj/sleeper-bot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sdotj/sleeper-bot. 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/sdotj/sleeper-bot/main/.claude/skills/cairn-dev/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/sdotj/sleeper-bot

Made for: Claude Code.

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/skills/sdotj/sleeper-bot/cairn-dev/github.svg)](https://agentmods.dev/skills/sdotj/sleeper-bot/cairn-dev)

Your own site

<a href="https://agentmods.dev/skills/sdotj/sleeper-bot/cairn-dev"><img src="https://agentmods.dev/badge/skills/sdotj/sleeper-bot/cairn-dev/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/skills/sdotj/sleeper-bot/cairn-dev"><img src="https://agentmods.dev/badge/skills/sdotj/sleeper-bot/cairn-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 907 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod 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	$0.00063	$0.00907
Opus 5.5	$0.00025	$0.00363
Sonnet 5.5	$0.00013	$0.00181
Haiku 4.5	$0.00006	$0.00091

Measured 2mo ago against content hash c5dc9daf7559, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cairn-dev 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 2mo 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.

Origin

This is a copy

100% identical to cairn-dev — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/cairn-dev/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cairn-dev

This repository declares its architecture in cairn.blueprint; cairn reconciles that declaration against the code and reports the gap. This file is a router: load the one reference your task needs, and only that one.

Authority

The target repository outranks this guide: its AGENTS.md, CLAUDE.md, and CONTRIBUTING.md decide conventions, gates, and workflow, and accepted decisions in the graph (cairn rationale <node>) bind the nodes they name. Where this guide disagrees with either, this guide is wrong.

First move

cairn context

It returns the nodes, edges, artefacts, and current findings, and names the node that owns the area you were asked about. Run it before opening files. Orient from the queries, never from map.json or map.md: those are generated review snapshots for humans reading a diff, not agent context.

The gate

cairn scan        # zero findings is the target
cairn hook all    # exit 0 means the commit is safe

Run both before you hand work back. Fix the cause of an Error finding. Never bypass a hook.

Routes

Match the session to one row and load only that reference. Paths are relative to this file.

The task is	Load
Find why something misbehaves, then fix it	`references/task-bug-investigation.md`
Restructure code without changing behaviour	`references/task-refactoring.md`
Understand how a system fits together	`references/task-architecture-discovery.md`
Build something new, or extend a module	`references/task-feature-implementation.md`
Mine an existing codebase into proposed decisions	`references/task-brownfield-decision-extraction.md`
Write or edit `cairn.blueprint`	`references/blueprint-syntax.md`
Interpret a finding code	`references/finding-codes.md`
Write a decision, research, source, or todo	`references/artefact-schemas.md`
Look up a command or flag	`references/command-reference.md`
Navigate the graph, read source through it, or resolve a node id	`references/graph-navigation.md`
Run one full cairn development iteration	`references/loop-mode.md`, if installed, and only on explicit request (see below)

Read the full file on GitHub · 85 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 85 lines · 63 tokens per session scan A c5dc9daf7559

Subscribe to this mod's changes

cairn-dev is a skill published in the GitHub repository sdotj/sleeper-bot (0 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 907 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to cairn-dev, differing in 0 lines, and is treated as a copy.

cairn-dev next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cairn-devsdotj/sleeper-bot	Skill	0	1mo ago	MIT	A	63	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

sleeper-bot: Skill for Claude Code