agentmods.dev

cairntir: Instructions file for Claude Code

CLAUDE.md

cairntir CLAUDE.md is an instructions file for Claude Code from pnmcguire480/cairntir. It costs 2,274 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for a project called Cairntir. The instructions describe the project's identity, purpose, background, ownership, repository, release status, and working rules.

In plain words
What is it for?
Use it as the project's main context file so Claude Code understands Cairntir, its goal of reducing cross-chat AI memory loss, and its current development and release details.
Why use it?
It gives an AI agent shared context about the project before it makes decisions. Keeping this information current helps prevent outdated assumptions from spreading across sessions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions Codex.

This is pnmcguire480/cairntir's own configuration. It tells Claude Code how to work on cairntir itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cairntir configures →

not rated 2repo changed today A scan 2,274 tokens original MIT
View source ↗ pnmcguire480/cairntir
Reuse

Borrowing it

Nothing to install: this file belongs to pnmcguire480/cairntir. 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/pnmcguire480/cairntir/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pnmcguire480/cairntir

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.

agentmods badge for cairntir CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pnmcguire480/cairntir/claude-md/github.svg)](https://agentmods.dev/instructions/pnmcguire480/cairntir/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pnmcguire480/cairntir/claude-md"><img src="https://agentmods.dev/badge/instructions/pnmcguire480/cairntir/claude-md/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.

agentmods 80×15 button for cairntir CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pnmcguire480/cairntir/claude-md"><img src="https://agentmods.dev/badge/instructions/pnmcguire480/cairntir/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,274 This file is loaded in full into every session.
When invoked 2,274 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02274 $0.02274
Opus 5 $0.01137 $0.01137
Sonnet 5 $0.00455 $0.00455
Haiku 4.5 $0.00227 $0.00227

Measured today against content hash 278b1ca33c99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cairntir CLAUDE.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 today.

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.

CLAUDE.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cairntir — project brief

Host-neutral, local-first memory and reasoning through MCP. Owner: Patrick McGuire (@pnmcguire480). License: MIT. Python 3.11–3.13.

Current state

Published version: 1.12.2; production installation: 1.12.1. The 1.12.2 release record records verified PyPI publication and fresh isolated CLI/MCP installation checks. The 1.12.1 release record records the production installation and automatic backup activation. Pending changes belong under Unreleased.

The core has verbatim SQLite drawers, explicit provenance, task-aware budgeted handoff, semantic and anchored recall, portable evidence, evaluated procedures, scoped local sharing, prediction settlements, discovery review, three skills, recipes, and 21 MCP tools. Transcript recovery supports Claude Code, Codex, and Qwen Code; Cursor returns an unsupported receipt.

The continuity delivery is COMPLETE and published as 1.10.0. The additive release retains the public tool surface and introduces schema 7 without new dependencies.

Working rules

Read this brief first. Before proposing a feature, read the manifesto, concepts, and ETHOS.md. Keep changes scoped to the active plan.

  • Preserve verbatim evidence; append corrections and outcomes.
  • Every exception must be typed and surfaced. Never silently suppress failures.
  • Use configured or platform-derived paths, never maintainer-specific paths.
  • Do not add dependencies without discussion.
  • Never import predecessor code or modify lineage/; it is read-only history.
  • Preserve executable commitments when retiring a plan.
  • Use small Conventional Commits and a green pull request to reach main.
  • Leave the checkout on main when work is landed.
  • Update this Last Session block with evidence, not a running transcript.
  • Check Unreleased fixes before closing; propose an immediate patch when users are blocked. Publication still requires explicit maintainer authority.
  • Never move a published tag or treat a changelog as a release.
  • Reserve 2.0.0 for a revolutionary change in purpose.

Read the full file on GitHub · 178 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. today Changed · -10 lines · -121 tokens per session 278b1ca33c99
  2. yesterday Changed · +27 lines · +461 tokens per session 41f94f613e54
  3. 2d ago Changed · -1,165 lines · -20,538 tokens per session e4dfbbf7087a
  4. 5d ago Changed · +27 lines · +541 tokens per session d2cfdf9037f6
  5. 9d ago First seen · 1,299 lines · 21,931 tokens per session scan A 7c789ea33e54

Subscribe to this mod's changes

cairntir CLAUDE.md is an instructions file published in the GitHub repository pnmcguire480/cairntir (2 stars, last pushed yesterday), licensed MIT. It adds 2,274 tokens to every session, about $0.0114 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.

Claude Codeai-memorydeveloper-toolsllm-memorylocal-firstmcp
Related

Other instructions, from other repositories

next.js AGENTS.md

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

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 · 5,153 tokens

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

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

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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens