mnemos: Instructions file for Claude Code

CLAUDE.md

mnemos CLAUDE.md is an instructions file for Claude Code from Riley-Coyote/mnemos. It costs 1,251 tokens per session, scanned A, original, MIT.

Repository instructions for working on Mnemos, a memory system. They emphasize checking behavior directly, distinguishing verified facts from assumptions, and testing changes across processes.

In plain words
What is it for?
Use them when changing Mnemos, running its test suites, verifying configuration or memory paths, and preparing releases.
Why use it?
They help catch failures where the system appears to succeed but does not actually store or retrieve information correctly.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event.

This is Riley-Coyote/mnemos's own configuration. It tells Claude Code how to work on mnemos 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 mnemos configures →

Reuse

Borrowing it

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

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 mnemos CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/riley-coyote/mnemos/claude-md"><img src="https://agentmods.dev/badge/instructions/riley-coyote/mnemos/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,251 This file is loaded in full into every session.
When invoked 1,251 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 $0.01251 $0.01251
Opus 5 $0.00626 $0.00626
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured 9d ago against content hash 72e50cc7862f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mnemos 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 9d 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.

CLAUDE.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working on Mnemos

Guidance for agents and contributors working in this repository.

Mnemos is a memory system. Its failure mode is not a crash — it is a layer that silently reports success while carrying nothing. Most of the bugs found in this codebase have been of exactly that shape: a scope that did not match, a config that was never applied, a promotion that never fired. Everything below exists to make that failure mode visible.


Verify, don't assume

If a claim is checkable, check it before stating it.

  • Run it. Reading the code and reasoning about what it will do is not verification. Install it, call it, look at the output.
  • No "too trivial to test" exemption. The small, obvious changes are where untested assumptions slip through.
  • Say what you actually know. Distinguish "I verified X, here is the command" from "I believe X." If something was not verified, say so.

For this repo specifically, a change to the memory path is not done until a capture written in one process has been read back in another.


Tests

pytest -q                     # the whole suite
uv run --extra dev --extra mcp pytest -q   # exactly what CI runs

A bug fix lands with a test that fails on the previous code. Confirm that directly — stash the fix, run the test, watch it fail, restore. A test that passes both before and after documents behaviour; it does not protect it.

Beware tests that pass the same explicit arguments to the writer and the reader. The scope split-brain survived 202 green tests because every scope test hand-matched both sides. Exercise the defaults, because defaults are what an agent actually calls.


Release process

main is public and is what users install. It stays green.

All work happens on a branch and lands through a pull request. Agents run the entire pipeline — nothing here requires anyone to open GitHub.

git checkout -b <type>/<slug> origin/main
# work, atomic commits
git push -u origin <type>/<slug>
gh pr create --title "..." --body "..."
gh pr checks --watch                    # CI gate
gh pr merge --squash --delete-branch
git checkout main && git pull
gh run list --branch main --limit 1     # confirm main is green after the merge

Read the full file on GitHub · 139 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. 9d ago First seen · 139 lines · 1,251 tokens per session scan A 72e50cc7862f

Subscribe to this mod's changes

mnemos CLAUDE.md is an instructions file published in the GitHub repository Riley-Coyote/mnemos (49 stars, last pushed 1mo ago), licensed MIT. It adds 1,251 tokens to every session, about $0.0063 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 2026-08-30.

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

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