mnemo CLAUDE.md

mnemo CLAUDE.md is an instructions file for coding agents from jojoprison/mnemo. It costs 1,014 tokens per session, scanned A, original, MIT.

Project instructions for mnemo, an agent-skills plugin that provides human-managed memory features for Codex and Claude Code.

In plain words
What is it for?
Use them when changing mnemo's memory commands, plugin manifests, setup, health checks, reviews, or cross-platform support.
Why use it?
They define the shared compatibility rules, canonical skill names, design principles, and differences between the two agent platforms.

Instructions file

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/jojoprison/mnemo/claude-md
Clone the repo
git clone --depth 1 https://github.com/jojoprison/mnemo

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 mnemo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jojoprison/mnemo/claude-md.svg)](https://agentmods.dev/instructions/jojoprison/mnemo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jojoprison/mnemo/claude-md"><img src="https://agentmods.dev/badge/instructions/jojoprison/mnemo/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,014 This file is loaded in full into every session.
When invoked 1,014 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 $0.01014 $0.01014
Opus 5 $0.00507 $0.00507
Sonnet 5 $0.00203 $0.00203
Haiku 4.5 $0.00101 $0.00101

Measured 3d ago against content hash 6bd7efd726a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mnemo 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 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.

CLAUDE.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mnemo Agent Instructions

mnemo is a dual-runtime Agent Skills plugin for Codex and Claude Code. Keep Claude Code compatibility intact while adding Codex support.

Design philosophy & non-goals: read docs/design-decisions.md first — the one principle everything follows (human-authored vault, non-destructive, in-agent) and the features deliberately not shipped (auto-ingest, web-search imputation, hot.md), each with an on-philosophy way to add it if you want it.

Compatibility Rules

  • The install/package ID and public brand stay mnemo in both marketplaces.
  • Claude Code's manifest namespace is intentionally mn, giving users exact /mn:* commands.
  • Codex's manifest namespace stays mnemo; its deterministic explicit IDs are $mnemo:*, while agents/openai.yaml presents the matching mn:* labels in skill UI.
  • The only canonical skills are ask, save, session, review, connect, setup, and health. Keep one implementation per skill in plugins/mnemo/skills/*/SKILL.md — no alias skill directories or legacy commands/ routers.
  • Runtime-specific presentation belongs in manifests and agents/openai.yaml, not duplicated skill bodies. Claude's model/context frontmatter extensions are an intentional dual-runtime exception accepted by Codex plugin validation.

Memory Backends

  • Obsidian is the primary user-visible memory store.
  • claude-mem is optional and may be intentionally disabled — or fully removed (plugin + marketplace + chroma LaunchAgent). Never auto-start ChromaDB or the claude-mem worker, never reinstall or "repair" claude-mem unless the user explicitly asks: a missing/dead claude-mem is intended state, the cascade must degrade silently.
  • In Codex, ${CODEX_HOME:-~/.codex}/memories/ is Codex-generated read-only state. mnemo may retrieve verified project-scoped evidence but never writes a fallback copy there.
  • In Claude Code, save may use the active, enabled auto-memory directory resolved by Claude's settings; honor CLAUDE_CONFIG_DIR, explicit overrides, and disable controls instead of guessing a project slug.

Read the full file on GitHub · 45 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 · 45 lines · 1,014 tokens per session scan A 6bd7efd726a6

Subscribe to this mod's changes

mnemo CLAUDE.md is an instructions file published in the GitHub repository jojoprison/mnemo (6 stars, last pushed 13d ago), licensed MIT. It adds 1,014 tokens to every session, about $0.0051 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.