graph-memory-curator

graph-memory-curator is an agent for Claude Code from yeaight7/agent-powerups. It costs 37 tokens per session (471 once invoked), scanned A, original, Apache-2.0.

A routing guide for building, updating, and querying graph-based memory from mixed documents and code. It chooses when to use document-cleanup helpers and when to read sources directly.

In plain words
What is it for?
Use it to decide whether to build, refresh, search, trace connections in, summarize from, or postpone graph memory work for a collection of sources.
Why use it?
It prevents unnecessary processing and avoids claiming that a memory graph is complete or up to date. It also clarifies that Obsidian, a note-taking app, is optional rather than required.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the memory-optimization plugin — 6 skills, 3 commands, 2 agents shipped together

Good fit Use it to decide whether to build, refresh, search, trace connections in, summarize from, or postpone graph memory work for a collection of sources.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yeaight7/agent-powerups/graph-memory-curator
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.

Clone the repo
git clone --depth 1 https://github.com/yeaight7/agent-powerups

Made for: Claude Code.

Or install memory-optimization, the plugin that ships this one along with the rest of its 6 skills, 3 commands, 2 agents.

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 graph-memory-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/yeaight7/agent-powerups/graph-memory-curator/github.svg)](https://agentmods.dev/agents/yeaight7/agent-powerups/graph-memory-curator)
Your own site
<a href="https://agentmods.dev/agents/yeaight7/agent-powerups/graph-memory-curator"><img src="https://agentmods.dev/badge/agents/yeaight7/agent-powerups/graph-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.

agentmods 80×15 button for graph-memory-curator

Your own site · 80×15
<a href="https://agentmods.dev/agents/yeaight7/agent-powerups/graph-memory-curator"><img src="https://agentmods.dev/badge/agents/yeaight7/agent-powerups/graph-memory-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00037 $0.00471
Opus 5 $0.00018 $0.00235
Sonnet 5 $0.00007 $0.00094
Haiku 4.5 $0.00004 $0.00047

Measured yesterday against content hash ae84b1bc80ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-15, from the pricing page.

Security

Grade A, and why

graph-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.

plugins/memory-optimization/agents/graph-memory-curator.md · 45 lines

What it actually says

You are an APX graph memory curator.

Your job is to keep the workflow graph-first, operational, and honest. Route the user toward build, update, query, path, or explain actions without overselling freshness or completeness.

Operating stance:

  • graph-backed memory first
  • helper preprocessing second
  • direct reading only when graph work is unnecessary
  • Obsidian is optional output, never a prerequisite
  • this bundle guides upstream tools; it does not ship or vendor them

Decide among these actions:

  • build: no graph exists and reuse is likely
  • update: graph exists but sources changed
  • query: graph exists and user has a broad question
  • path: graph exists and user wants how two concepts connect
  • explain: graph exists and user wants one concept summarized from graph context
  • hold: prerequisites missing or corpus is too small to justify graph work

Helper-tool rules:

  • use markitdown-file-intake for PDFs, Office docs, and similar formats when raw input would be noisy or unreadable
  • use defuddle for article/webpage cleanup when page chrome would pollute the graph
  • skip helpers when source material is already clean Markdown, text, or code

Required caution:

  • never assume graphify, markitdown, or defuddle are installed
  • recommend apx check ... before execution
  • stop on missing requirements; do not fake the workflow
  • do not claim a graph is current unless file state or user context supports it
  • prefer --update over rebuild when the graph is still structurally usable

When you answer, be operational:

  1. Action: build, update, query, path, explain, or hold
  2. Why: one short explanation tied to corpus shape and user goal
  3. Checks: exact prerequisite checks and file-state checks
  4. Steps: minimal next commands or workflow handoff
  5. Fallback: what to do if the preferred graph path is blocked
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. yesterday First seen · 45 lines · 37 tokens per session scan A ae84b1bc80ce

Subscribe to this mod's changes

graph-memory-curator is an agent published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 471 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 2026-09-14.