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/jojoprison/mnemo/claude-mdgit clone --depth 1 https://github.com/jojoprison/mnemoWrote 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/jojoprison/mnemo/claude-md)<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>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 | $0.01014 | $0.01014 |
| Opus 5 | $0.00507 | $0.00507 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
mnemo CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mnemo Agent Instructions
mnemo is a dual-runtime Agent Skills plugin for Codex and Claude Code. Keep Claude Code compatibility intact while adding Codex support.
Design philosophy & non-goals: read docs/design-decisions.md first — the one principle everything follows (human-authored vault, non-destructive, in-agent) and the features deliberately not shipped (auto-ingest, web-search imputation, hot.md), each with an on-philosophy way to add it if you want it.
Compatibility Rules
- The install/package ID and public brand stay
mnemoin both marketplaces. - Claude Code's manifest namespace is intentionally
mn, giving users exact/mn:*commands. - Codex's manifest namespace stays
mnemo; its deterministic explicit IDs are$mnemo:*, whileagents/openai.yamlpresents the matchingmn:*labels in skill UI. - The only canonical skills are
ask,save,session,review,connect,setup, andhealth. Keep one implementation per skill inplugins/mnemo/skills/*/SKILL.md— no alias skill directories or legacycommands/routers. - Runtime-specific presentation belongs in manifests and
agents/openai.yaml, not duplicated skill bodies. Claude'smodel/contextfrontmatter 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.
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 · 45 lines · 1,014 tokens per session scan A 6bd7efd726a6
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.
Other instructions, from other repositories
hindsight CLAUDE.md
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.
plur CLAUDE.md
Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
remnic AGENTS.md
Instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
mulch AGENTS.md
Instructions for jayminwest/mulch, covering agents.md, what this project is, tech stack at a glance, project layout and commands.
EverMe AGENTS.md
Instructions for EverMind-AI/EverMe, covering agents.md, goal (pick one per pr), build & test, pre-pr checks (match ci gates) and commit & pr.
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.