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 aayoawoyemi/Ori-Mnemos --skill hermesgit clone --depth 1 https://github.com/aayoawoyemi/Ori-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/aayoawoyemi/ori-mnemos/hermes)<a href="https://agentmods.dev/skills/aayoawoyemi/ori-mnemos/hermes"><img src="https://agentmods.dev/badge/skills/aayoawoyemi/ori-mnemos/hermes/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.
<a href="https://agentmods.dev/skills/aayoawoyemi/ori-mnemos/hermes"><img src="https://agentmods.dev/badge/skills/aayoawoyemi/ori-mnemos/hermes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.02890 |
| Opus 5 | $0.00027 | $0.01445 |
| Sonnet 5 | $0.00011 | $0.00578 |
| Haiku 4.5 | $0.00005 | $0.00289 |
Grade A, and why
ori-memory 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 12d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ori Mnemos
Durable memory that compounds over time. A knowledge graph on markdown files with learning retrieval — capture what you find, decide, or learn during work, and retrieve it when the same problem comes up weeks or months later. The system gets better at finding things the more you use it.
When to Use
Use this skill when:
- you learn something worth retrieving a week, a month, or a year from now
- you make a decision and want to remember why (not just what)
- you find research, references, or technical details during work that would be expensive to rediscover
- you need to maintain persistent identity, goals, or methodology across sessions
- you want to search across everything you have ever captured, not just what fits in context
The core question: would losing this hurt if the same situation comes up again? If yes, capture it.
Ori vs Hermes built-in memory
Hermes has MEMORY.md and USER.md — a frozen snapshot injected into every system prompt. That is the right place for always-on context: user preferences, environment facts, communication style, things the agent needs on every turn.
Ori is a searchable knowledge graph. It scales to thousands of notes because you retrieve on demand, not inject everything. Use Ori for durable knowledge that is too much to carry in every prompt but too valuable to lose — research findings, architectural decisions, project history, lessons learned, accumulated insights.
Do not use Ori for ephemeral task state: current file being edited, intermediate reasoning steps, temporary paths, things that only matter in this conversation.
Prerequisites
Install Ori globally:
npm install -g ori-memory
ori --version
Setup
One-command bridge install
ori init ~/brain
ori bridge hermes --vault ~/brain
This writes the MCP server config to ~/.hermes/config.yaml and installs a native lifecycle plugin at ~/.hermes/plugins/ori/. Restart Hermes after running.
What the bridge installs
What ships with it
4 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.
- 12d ago First seen · 358 lines · 54 tokens per session scan A 3e91f31f02d8
ori-memory is a skill published in the GitHub repository aayoawoyemi/Ori-Mnemos (323 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 2,890 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
plur-create-engrams
Create or improve PLUR engrams from conversations, documents, decisions, observations, and explicit preferences. Use for memory extraction, engram authoring, or reviewing proposed memories, including global, scoped, pinned, retrieved, and provisional knowledge. Ordinary use of existing memories does not require this…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
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-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.