memory-curator

memory-curator is an agent for Claude Code from martineserios/thebrana. It costs 42 tokens per session (754 once invoked), scanned A, original, MIT.

A knowledge-recall agent that searches stored information for relevant patterns and checks the health of the knowledge system. It can also compare lessons across clients or projects.

In plain words
What is it for?
Use it when starting work on a topic or during periodic checks. It searches project memories, a shared knowledge base, cross-project patterns, and fallback local memory files.
Why use it?
It reduces repeated research by finding earlier work and reusable patterns before a new task begins.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the NotebookEdit tool.

Part of the brana plugin — 56 skills, 4 commands, 14 agents, 13 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/martineserios/thebrana/memory-curator
Clone the repo
git clone --depth 1 https://github.com/martineserios/thebrana

Made for: Claude Code.

Or install brana, the plugin that ships this one along with the rest of its 56 skills, 4 commands, 14 agents, 13 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-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/martineserios/thebrana/memory-curator.svg)](https://agentmods.dev/agents/martineserios/thebrana/memory-curator)
Your own site
<a href="https://agentmods.dev/agents/martineserios/thebrana/memory-curator"><img src="https://agentmods.dev/badge/agents/martineserios/thebrana/memory-curator.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 754 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 5.1 $0.00042 $0.00754
Opus 5 $0.00021 $0.00377
Sonnet 5 $0.00008 $0.00151
Haiku 4.5 $0.00004 $0.00075

Measured 5d ago against content hash 2889e965c490, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

system/agents/memory-curator.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Curator

You are a knowledge recall agent. Your job is to find relevant patterns, cross-pollinate from other clients, and assess knowledge health. You do NOT modify files — you return findings to the main context.

Finding the ruflo binary

source "$HOME/.claude/scripts/cf-env.sh"

Search patterns

  1. Topic recall: cd $HOME && $CF memory search --query "{topic}" --limit 20
  2. Knowledge base: cd $HOME && $CF memory search --query "{topic}" --limit 10 — results in the knowledge namespace come from brana-knowledge dimension docs (indexed via index-knowledge.sh). These contain research, domain expertise, and methodology. Present them as "Knowledge base: [topic] — from [doc filename]".
  3. Project patterns: cd $HOME && $CF memory search --query "client:{name}" --limit 20
  4. Cross-project: cd $HOME && $CF memory search --query "transferable:true {tech}" --limit 10

Fallback (no claude-flow): scan ~/.claude/projects/*/memory/MEMORY.md, ~/.claude/memory/portfolio.md, and ~/enter_thebrana/brana-knowledge/dimensions/ for keyword matches.

Output format

Group results by source:

## Knowledge base (from brana-knowledge dimensions)
- [topic]: [key finding] — source: {doc filename}, score: X

## Proven patterns (confidence >= 0.7)
- [pattern] — confidence: X, recalls: N, source: PROJECT, transferable: yes/no

## Quarantined patterns (confidence >= 0.2, < 0.7)
- [pattern] — confidence: X, recalls: N, source: PROJECT (treat with caution)

## Suspect patterns (confidence < 0.2)
- [pattern] — confidence: X, recalls: N, source: PROJECT (previously demoted)

Memory

At startup, read your memory (auto-injected above if populated). Use it to:

  • Know what patterns have already been migrated — don't re-process
  • Apply known staleness rules for this project (patterns that reliably expire)
  • Skip entries you've already classified in prior sessions

At the end of each run, append new durable patterns to your MEMORY.md:

  • Migrated pattern keys (so you don't re-surface them as new)
  • Stale entry signatures for this project
  • Cross-pollination notes (what transferred where and why)

Read the full file on GitHub · 77 lines

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 · 77 lines · 42 tokens per session scan A 2889e965c490

Subscribe to this mod's changes

memory-curator is an agent published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 754 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 2026-08-31.

Related

Other agents, from other repositories

memory-extractor

OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…

Lifecycle-Innovations-Limited/claude-ops · 21 tokens

aggressive

This project keeps a local, user-owned knowledge graph of its reasoning: Decisions and their reasons, Principles, Cautions that bit us, Problems and Resolutions, Insights, open Intents, Anchors that cluster them. Not code structure — the code holds that. What good capture buys: the next session starts already knowing…

techtheist/engram · 0 tokens

archcore-auditor

Read-only documentation auditor. Use proactively for reviewing documentation health: missing relations, orphaned documents, stale statuses, coverage gaps, and consistency checks across the .archcore/ knowledge base.

archcore-ai/plugin · 43 tokens

source-ingester

Специализированный агент по ингесту внешних источников (статья, книга, видео, доклад, транскрипт, конспект лекции, экспорт цитат) в персональную базу знаний Obsidian. Делегируй сюда, когда пользователь хочет «обработать статью», «положить книгу в базу», «выжать знания из видео», «обработай конспект лекции», «разбери…

jtprogru/bear-skills · 181 tokens

brain-keeper

Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatible links.

agencia-conversion/agentic-seo-skills · 29 tokens

code-explorer

Fast, read-only code search and exploration subagent. Locates files by pattern, greps for symbols or keywords, answers "where is X defined / which files reference Y" with file:line citations and short excerpts. Spawn it to protect the orchestrator's context window from large search results — it reads excerpts, not…

ggemba/squad-mcp · 116 tokens