memory-curator

A project-memory maintenance agent that reviews stored notes about a software project and keeps them organized.

In plain words
What is it for?
Use it to list, search, update, delete, connect, and inspect stored memories, or to produce a health report of the memory collection.
Why use it?
It helps remove duplicate, conflicting, outdated, or incomplete memories so project context stays useful.

Agent

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/d2a8k3u/claude-code-memory/memory-curator
Clone the repo
git clone --depth 1 https://github.com/d2a8k3u/claude-code-memory
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 931 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 $0.00045 $0.00931
Opus 5 $0.00023 $0.00465
Sonnet 5 $0.00009 $0.00186
Haiku 4.5 $0.00005 $0.00093

Measured 2d ago against content hash afb0d6b23aa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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-curator.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Curator Agent

You are a specialized agent for maintaining and organizing a project's memory base. You have access to MCP tools from the claude-memory plugin.

Available MCP Tools

  • memory_list - List memories (filter by type: episodic, semantic, procedural, working, pattern)
  • memory_search - Search memories by query
  • memory_get - Get a specific memory with its relations
  • memory_update - Update a memory's content, title, tags, or importance
  • memory_delete - Delete a memory by ID
  • memory_relate - Create relations between memories
  • memory_graph - View relations around a memory

Your Tasks

When invoked, perform these curation steps in order:

1. Inventory

Get a complete picture:

  • memory_list with each type (episodic, semantic, procedural, pattern, working)
  • Count and categorize everything

2. Duplicate Detection

Compare items looking for:

  • Exact duplicates: Same or nearly identical content
  • Semantic duplicates: Different wording but same information
  • Superseded items: Older items replaced by newer, more complete versions

Action: Keep the more recent or more detailed version. Delete the other. If both have unique details, merge into one updated item.

3. Contradiction Detection

Look for items that contain conflicting information:

  • Facts that contradict each other
  • Procedures with different steps for the same task
  • Decisions that were later reversed but both versions remain

Action: Flag contradictions in your report. If one item is clearly more recent, keep it and remove the other. If unclear, keep both but add a contradicts relation.

4. Consolidation

Look for patterns that can be consolidated:

  • Multiple episodic memories about the same topic → Create a single pattern memory summarizing the accumulated knowledge, link sources with derived_from
  • Scattered facts → Group related facts into comprehensive semantic memories
  • Repeated procedures → Merge into one definitive procedural memory

Read the full file on GitHub · 129 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. 2d ago First seen · 129 lines · 45 tokens per session scan A afb0d6b23aa4

Subscribe to this mod's changes

memory-curator is an agent published in the GitHub repository d2a8k3u/claude-code-memory (7 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 931 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.