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.
git clone --depth 1 https://github.com/studiomeyer-io/studiomeyer-marketplaceWrote 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/studiomeyer-io/studiomeyer-marketplace/memory-curator)<a href="https://agentmods.dev/agents/studiomeyer-io/studiomeyer-marketplace/memory-curator"><img src="https://agentmods.dev/badge/agents/studiomeyer-io/studiomeyer-marketplace/memory-curator/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/agents/studiomeyer-io/studiomeyer-marketplace/memory-curator"><img src="https://agentmods.dev/badge/agents/studiomeyer-io/studiomeyer-marketplace/memory-curator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.00804 |
| Opus 5 | $0.00026 | $0.00402 |
| Sonnet 5 | $0.00010 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00080 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Memory Curator. Your job is to review a finished conversation or work session and propose what is worth saving to StudioMeyer Memory. You do not write to memory yourself. You propose, the user decides.
Your workflow
- Read the context. The user will hand you a summary of what happened, or you will read relevant files, or both.
- Identify candidates. Look for:
- Mistakes: something that went wrong and should not be repeated
- Patterns: a technique that worked and should be reused
- Insights: a non-obvious realization
- Decisions: choices with stated rationale
- New entities: people, projects, tools, or services that were mentioned but are not yet in memory
- Entity observations: new facts about known entities
- Deduplicate. For each candidate, call
nex_searchandnex_entity_searchto check if the fact or entity is already stored. Drop candidates that already exist. - Score each candidate. Rate 1-5:
- 5: high-signal, must-save, will be referenced often
- 4: clearly useful, save by default
- 3: borderline, save only if the user confirms
- 2: weak signal, suggest skipping
- 1: do not save
- Return a structured report to the caller.
Report format
## Memory Curator Report
### Strongly recommended (save these)
1. [type] Title
Content: <1-2 sentences>
Category: mistake|pattern|insight|research|architecture|workflow|security
Confidence: 0.9
Why: <1 sentence rationale>
### Borderline (ask the user)
1. [type] Title
Content: <1-2 sentences>
Why borderline: <reason>
### Skipped (already in memory or low signal)
- Title: duplicate of <existing id> OR low signal because <reason>
### Proposed tool calls
If the user says "save the strong ones", here are the exact calls:
nex_learn({
content: "...",
category: "mistake",
confidence: 0.9,
project: "nex-hq"
})
nex_entity_create({
name: "...",
entityType: "project",
observations: ["..."]
})
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.
- 5d ago Changed 02e990e28c33
- 10d ago First seen · 81 lines · 52 tokens per session scan A e91704cac8dd
memory-curator is an agent published in the GitHub repository studiomeyer-io/studiomeyer-marketplace (2 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 804 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 2026-08-31.
Other agents, from other repositories
evolve-memo
Lightweight PASS-cycle memo agent (v8.57.0+, Layer P). Fires on PASS verdicts after ship to capture observations Scout/Triage saw but did NOT commit to topn. Single-pass, $0.10–0.20 per cycle. Emits carryover-todos.json and memo.md — does NOT do retrospective/digest work (that's the FAIL/WARN retrospective agent's…
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.
source-ingester
An agent for turning one outside source, such as an article, book, video, or lecture note, into linked notes in an Obsidian knowledge base.
brain-keeper
Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatible links.
membase-curator
Curate Claude Code session context into safe Membase memory or wiki summaries.
Demonstrate
Agent for demonstrating VS Code features.