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 skills add anthony-maio/mnemos --skill mnemos-codexgit clone --depth 1 https://github.com/anthony-maio/mnemosWrote 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/skills/anthony-maio/mnemos/mnemos-codex)<a href="https://agentmods.dev/skills/anthony-maio/mnemos/mnemos-codex"><img src="https://agentmods.dev/badge/skills/anthony-maio/mnemos/mnemos-codex.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 5.1 | $0.00058 | $0.00556 |
| Opus 5 | $0.00029 | $0.00278 |
| Sonnet 5 | $0.00012 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
mnemos-codex 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 7d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mnemos for Codex
Use this skill to put Mnemos on the supported Codex path without overstating host automation. In Codex, the practical Mnemos workflow is:
- recall at the start of substantial work
- curate durable facts during or after the task
- consolidate before finishing
Default path
- Prefer
pip install "mnemos-memory[mcp]"andmnemos ui. - Treat the blessed Codex setup as two parts: MCP config plus a repo-level
AGENTS.mdmemory block. - Read
references/install.mdfor install and validation. - Read
references/operations.mdfor daily use, troubleshooting, and honest capability framing.
Claim discipline
- Safe to claim: Mnemos works in Codex through MCP, shared
MNEMOS_CONFIG_PATH, repo-levelAGENTS.md, and optional maintenance Automations. - Do not claim built-in prompt/tool lifecycle hooks or Claude Code parity.
- Hard auto-capture in Codex is host-dependent and not shipped by Mnemos today.
Daily loop
- Start in recall mode: call
mnemos_retrievewith a task-focused query and repo-scoped arguments. - Do the work, then switch to curator mode: store only durable facts with
mnemos_store. - Use
mnemos_inspectbefore storing a correction or when a retrieved memory looks suspicious. - Finish substantial work with
mnemos_consolidate. - If Mnemos MCP tools are unavailable, continue normally instead of blocking work.
Recall mode
- Use at the start of coding, debugging, review, or handoff tasks.
- Query for architecture, current repo conventions, recent fixes, environment quirks, and user preferences that matter for this task.
- In Codex, prefer
current_scope=project,scope_id=<workspace or repo name>, andallowed_scopes=project,global.
Curator mode
- Use during or near the end of a substantial task.
- Store decisions, constraints, environment facts, recurring bug patterns, and stable preferences.
- Skip one-off chatter, ephemeral plans, stack traces without reusable lessons, and secrets.
Avoid
- Do not present Codex Automations as session capture.
- Do not tell users to type memories manually as the primary workflow.
- Do not market Codex as Tier 1 until real daily-use validation is complete.
What ships with it
2 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.
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.
- 7d ago First seen · 52 lines · 58 tokens per session scan A 64499c128385
mnemos-codex is a skill published in the GitHub repository anthony-maio/mnemos (27 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 556 once invoked, about $0.0003 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.
Other skills, from other repositories
kayba-ace
This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.
plur-memory
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.