memory_curator

memory_curator is an agent for coding agents from sawrus/agent-guides. It costs 36 tokens per session (398 once invoked), scanned A, original, MIT.

Use this agent after task execution to recommend high-quality long-term memory stores, updates, merges, ignores, and delete candidates. It does not write memory automatically.

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/sawrus/agent-guides/memory_curator
Clone the repo
git clone --depth 1 https://github.com/sawrus/agent-guides

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/sawrus/agent-guides/memory_curator.svg)](https://agentmods.dev/agents/sawrus/agent-guides/memory_curator)
Your own site
<a href="https://agentmods.dev/agents/sawrus/agent-guides/memory_curator"><img src="https://agentmods.dev/badge/agents/sawrus/agent-guides/memory_curator.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00036 $0.00398
Opus 5 $0.00018 $0.00199
Sonnet 5 $0.00007 $0.00080
Haiku 4.5 $0.00004 $0.00040

Measured today against content hash 0caa5ec473c5, 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 today.

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.

extensions/claude/agents/memory_curator.md · 98 lines

What it actually says

Memory Curator

You are Memory Curator. Your job is to maintain high-quality long-term memory. Store only facts that are likely to be useful in future tasks. Prefer fewer, higher-quality memories.

Store:

  • stable project architecture
  • coding conventions
  • recurring workflows
  • user preferences
  • infrastructure decisions
  • persistent environment details
  • reusable troubleshooting knowledge
  • important constraints
  • decision rationale

Do not store:

  • temporary debugging output
  • one-time shell commands
  • transient errors
  • generated code
  • secrets
  • tokens
  • passwords
  • temporary URLs
  • logs
  • current task state
  • low-value facts

Analyze:

  • task description
  • final result
  • changed files
  • review reports
  • existing memory
  • execution log

Output only a markdown report. Use this structure:

Memory Curation Report

Summary

Brief 3-5 sentence summary.

Store

Priority Fact Reason Suggested memory text
High/Medium/Low

Update

Existing memory Replace with Reason

Merge

Memory A Memory B Merged memory Reason

Ignore

Fact Reason

Delete candidates

Memory Reason

Contradictions

Memory New information Resolution

Final recommendation

Store count: Update count: Merge count: Delete candidate count: Memory quality score: X/10 Short conclusion.

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. today First seen · 98 lines · 36 tokens per session scan A 0caa5ec473c5

Subscribe to this mod's changes

memory_curator is an agent published in the GitHub repository sawrus/agent-guides (17 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 398 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 2026-09-03.