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 ncz-os/mnemos --skill mnemos-memorygit clone --depth 1 https://github.com/ncz-os/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/ncz-os/mnemos/mnemos-memory)<a href="https://agentmods.dev/skills/ncz-os/mnemos/mnemos-memory"><img src="https://agentmods.dev/badge/skills/ncz-os/mnemos/mnemos-memory/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/ncz-os/mnemos/mnemos-memory"><img src="https://agentmods.dev/badge/skills/ncz-os/mnemos/mnemos-memory.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 | $0.00082 | $0.01032 |
| Opus 5.5 | $0.00033 | $0.00413 |
| Sonnet 5.5 | $0.00016 | $0.00206 |
| Haiku 4.5 | $0.00008 | $0.00103 |
Grade A, and why
mnemos-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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MNEMOS Memory
MNEMOS is persistent memory shared across agent sessions. It is a network service, not a prompt. Reads and writes happen through the mnemos MCP server.
When to search MNEMOS
Before you commit to an approach on any of these, run a quick search_memories:
- Infrastructure — ports, hostnames, service locations, credential storage layout
- Decisions — architecture choices, tradeoffs the team has already settled
- Solutions — workarounds for known bugs, fixes already applied elsewhere
- Patterns — reusable approaches already validated
- Projects — current project state, owners, milestones
- Standards — conventions, quality gates, review criteria
If the user's task looks like something that might have been solved before, search first. One query is cheap; wasted work is not.
Search patterns
- Start broad with full-text:
search_memories(query="topic keywords", limit=10)before narrowing - Filter by category when you know the domain:
search_memories(query="auth flow", category="decisions") - Use semantic search for concept-level matches:
search_memories(query="...", semantic=true) - Large context loads: use
POST /v1/memories/rehydratedirectly via the REST API (this path is not an MCP tool in the currentmnemos.mcp.stdiobridge). Chain multiplesearch_memoriescalls with a running token tally if you need to stay within MCP.
When to store
Store after:
- Solving a non-trivial problem (store the solution and the failure mode, not just the fix)
- Making an architectural decision with rationale (use
category=decisions; include why and tradeoffs) - Discovering infrastructure shape (endpoint, port, auth scheme) that future sessions will need
- Establishing a pattern that other agents should follow (
category=patternsorstandards)
Do not store:
- Session transcripts (the session ingest endpoint handles that separately)
- Temporary state that will be stale in a day
- Information the user will see in the diff (recent commits, current branch)
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.
- 1mo ago First seen · 90 lines · 82 tokens per session scan A 5782f0a775da
mnemos-memory is a skill published in the GitHub repository ncz-os/mnemos (35 stars, last pushed 4d ago), licensed Apache-2.0. It adds 82 tokens to every session and 1,032 once invoked, about $0.0003 per session on Opus 5.5. 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
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…
company-brain
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work…
ctx
A project-context tool for recording important lessons about bugs and failure-prone code in nearby AGENTS.md documents. These documents give coding agents repository-specific guidance.
gsd-resume-work
Resume work from previous session with full context restoration.
saferskills
Use SaferSkills to find, evaluate, and safely install AI agent capabilities (skills, MCP servers, hooks, plugins, rules) and to assess a whole agent. Run this before you install, add, recommend, or trust any capability — or when asked whether one is safe or what its score is: scan and score it first with npx…
hygiene
Data-retention and memory-hygiene summarization. Compress one calendar day of source-table rows, or a cluster of older same-source memories, into a single dense paragraph. Use when bounding storage growth while preserving the gist for retrieval.