memory-orchestrator

memory-orchestrator is an agent for coding agents from anthony-maio/mnemos. It costs 33 tokens per session (214 once invoked), scanned A, original, MIT.

An agent that manages Mnemos, a long-term memory system for coding work. It retrieves relevant notes at the start, saves only important facts during execution, and combines the notes before handoff.

In plain words
What is it for?
Use it for complex tasks where repository constraints, architecture decisions, recurring fixes, or user preferences should remain available later.
Why use it?
It keeps future sessions aware of stable project details without filling memory with temporary status updates or low-value conversation. It also gives a short account of retrieved and stored context.

Agent

Part of the mnemos-memory plugin — 2 skills, 3 agents, 4 hooks shipped together

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 agents/anthony-maio/mnemos/memory-orchestrator
Clone the repo
git clone --depth 1 https://github.com/anthony-maio/mnemos

Or install mnemos-memory, the plugin that ships this one along with the rest of its 2 skills, 3 agents, 4 hooks.

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 memory-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/anthony-maio/mnemos/memory-orchestrator.svg)](https://agentmods.dev/agents/anthony-maio/mnemos/memory-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/anthony-maio/mnemos/memory-orchestrator"><img src="https://agentmods.dev/badge/agents/anthony-maio/mnemos/memory-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 214 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00033 $0.00214
Opus 5 $0.00016 $0.00107
Sonnet 5 $0.00007 $0.00043
Haiku 4.5 $0.00003 $0.00021

Measured 5d ago against content hash b484a0290b0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-orchestrator 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 5d 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.

agents/memory-orchestrator.md · 30 lines

What it actually says

Mnemos Memory Orchestrator

You are responsible for keeping long-term memory useful and compact.

Working Protocol

  1. At task start, call mnemos_retrieve with a query derived from the user's intent.
  2. Keep only high-value memory writes:
    • stable user preferences
    • environment/tooling facts
    • architecture decisions and rationale
    • recurring bug patterns + fixes
  3. Avoid storing transient chatter or one-off low-signal details.
  4. Before finishing major work, call mnemos_consolidate.

Output

  • Provide a short context recap from retrieval.
  • Mention what was stored (if anything) and why.
  • Mention consolidation outcome when run.
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. 5d ago First seen · 30 lines · 33 tokens per session scan A b484a0290b0f

Subscribe to this mod's changes

memory-orchestrator is an agent published in the GitHub repository anthony-maio/mnemos (27 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 214 once invoked, about $0.0002 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.