memory-extractor

memory-extractor is an agent for coding agents from Lifecycle-Innovations-Limited/claude-ops. It costs 21 tokens per session (970 once invoked), scanned A, original, MIT.

A background agent that turns chat and email history into structured notes about people, preferences, ongoing topics, and things to avoid. It reads WhatsApp and email data and stores the notes as Markdown files.

In plain words
What is it for?
Building contact profiles, tracking active conversations and deadlines, recording communication preferences, and capturing corrections or complaints.
Why use it?
Important context is spread across old conversations, making it easy to forget how someone prefers to communicate or what remains unresolved. The notes give other operations tools context before they draft replies.

Agent

Part of the ops plugin — 66 skills, 21 agents, 5 hooks, 1 MCP server 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/lifecycle-innovations-limited/claude-ops/memory-extractor
Clone the repo
git clone --depth 1 https://github.com/Lifecycle-Innovations-Limited/claude-ops

Or install ops, the plugin that ships this one along with the rest of its 66 skills, 21 agents, 5 hooks, 1 MCP server.

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-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/lifecycle-innovations-limited/claude-ops/memory-extractor.svg)](https://agentmods.dev/agents/lifecycle-innovations-limited/claude-ops/memory-extractor)
Your own site
<a href="https://agentmods.dev/agents/lifecycle-innovations-limited/claude-ops/memory-extractor"><img src="https://agentmods.dev/badge/agents/lifecycle-innovations-limited/claude-ops/memory-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 970 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 $0.00021 $0.00970
Opus 5 $0.00010 $0.00485
Sonnet 5 $0.00004 $0.00194
Haiku 4.5 $0.00002 $0.00097

Measured 5d ago against content hash 24444675eba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-extractor 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.

claude-ops/agents/memory-extractor.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.

Purpose

Builds structured memory from raw chat data so ops skills (inbox, comms, go) can draft context-aware messages. Reads WhatsApp (bridge messages.db) and email (gog) history, calls Claude Sonnet for extraction, and writes/merges structured markdown memory files.

Memory Location

~/.claude/plugins/data/ops-ops-marketplace/memories/

File Types

File Contents
contact_*.md Per-contact profile cards (one per person)
preferences.md User communication patterns, tone, scheduling
topics_active.md Ongoing conversations, pending decisions, deadlines
donts.md Things to avoid — extracted from corrections and complaints
.health JSON health status written after each run

How Skills Use This

Before drafting any reply, skills check memories/ for:

  1. Contact profilecontact_<slug>.md for the recipient
  2. Topic contexttopics_active.md for active threads
  3. User preferencespreferences.md for tone/style/language
  4. Restrictionsdonts.md for things to never do

Example usage in a skill:

MEMORIES="${HOME}/.claude/plugins/data/ops-ops-marketplace/memories"

# Load contact profile
CONTACT_FILE=$(ls "${MEMORIES}/contact_"*jane-doe* 2>/dev/null | head -1)
[[ -f "${CONTACT_FILE}" ]] && cat "${CONTACT_FILE}"

# Load user preferences
[[ -f "${MEMORIES}/preferences.md" ]] && cat "${MEMORIES}/preferences.md"

# Load restrictions
[[ -f "${MEMORIES}/donts.md" ]] && cat "${MEMORIES}/donts.md"

Data Sources

  • WhatsApp: direct sqlite3 query on bridge messages.db:
    DB="${WHATSAPP_BRIDGE_DB:-$HOME/.local/share/whatsapp-mcp/whatsapp-bridge/store/messages.db}"
    sqlite3 "$DB" "SELECT chat_jid, sender, content, timestamp, is_from_me FROM messages WHERE timestamp >= '<yesterday>' ORDER BY timestamp DESC LIMIT 200;"
    
    • Requires bridge running: lsof -i :8080 | grep LISTEN
  • Email: gog gmail search -j --results-only --no-input --max 20 "newer_than:1d"
    • Requires gog available

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. 5d ago First seen · 129 lines · 21 tokens per session scan A 24444675eba2

Subscribe to this mod's changes

memory-extractor is an agent published in the GitHub repository Lifecycle-Innovations-Limited/claude-ops (184 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 970 once invoked, about $0.0001 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 2026-08-30.