Borrowing it
Nothing to install: this file belongs to SVerITG/Metis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SVerITG/Metis/main/.claude/agents/memory-curator.mdgit clone --depth 1 https://github.com/SVerITG/MetisWrote 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/agents/sveritg/metis/memory-curator)<a href="https://agentmods.dev/agents/sveritg/metis/memory-curator"><img src="https://agentmods.dev/badge/agents/sveritg/metis/memory-curator.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 | $0.00000 | $0.00507 |
| Opus 5 | $0.00000 | $0.00253 |
| Sonnet 5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
memory-curator 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 yesterday.
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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- yesterday First seen · 50 lines · 0 tokens per session scan A bfd0b74db8f2
memory-curator is an agent published in the GitHub repository SVerITG/Metis (3 stars, last pushed yesterday), licensed AGPL-3.0. It costs nothing until one of its globs matches a file; then it loads 507 tokens. 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 2026-09-05.
Other agents, from other repositories
session-learning
Extract learnings, patterns, and insights from work sessions. Use this agent: Spawned by session-learning-coordinator for each space After completing major tasks or projects After problem-solving sessions with novel solutions When user explicitly requests learning extraction The agent analyzes session work, identifies…
session-learning-coordinator
Orchestrate learning extraction across all spaces in a Datacore installation. Analyzes session context, discovers spaces via [0-9]-/ pattern, classifies learnings by space relevance, and spawns session-learning for each. Use this agent at end of /wrap-up, /gtd-daily-end, or /tomorrow commands.
conversation-processor
Agent "conversation-processor" from datacore-one/datacore, covering agent context, when to reference dip-0014, quick reference, related dips and related agents.
context-maintainer
Maintain CLAUDE.md and layered context files across the Datacore system. Use this agent: During /gtd-weekly-review for comprehensive context health check When user asks to "update context" or "check CLAUDE files" After agents, commands, or modules are added/removed To validate private content isn't leaking into public…
learning-classifier
Process new learning file entries, deduplicate against PLUR engrams, and create new engrams with proper classification. Detects recurrences, scope promotions, contradictions, and novel patterns.
evaluator-archivist
Evaluates how well the knowledge base was used. Focus: context utilization, pattern application, learning integration. Core evaluator - always runs for every task.