extract

A command that examines a diary entry or described event from several viewpoints and saves the resulting lessons as memories.

In plain words
What is it for?
Use it after a debugging session, decision, or other event to explore root causes, motivations, and lessons learned.
Why use it?
It turns a raw account of what happened into reusable explanations, patterns, and lessons instead of leaving the insight buried in a diary.

Command for Claude Code

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 commands/spideynolove/memory/extract
Clone the repo
git clone --depth 1 https://github.com/spideynolove/memory

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,263 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 $0.00015 $0.01263
Opus 5 $0.00008 $0.00632
Sonnet 5 $0.00003 $0.00253
Haiku 4.5 $0.00002 $0.00126

Measured yesterday against content hash e277921ee204, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

extract 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.

.claude/commands/extract.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Dimensional Memory Extraction

Run three parallel analytical lenses on a diary entry or described event, synthesize with epistemic humility, then store the result via store_memory.

Input

The user provides one of:

  • A diary entry path: /extract .claude/diary/YYYY-MM-DD-session-N.md
  • A free-form description of an event: /extract "I spent 20 minutes debugging X before realizing Y"
  • "last" to process the most recent diary entry automatically

If "last":

ls -t /home/hung/MCPs/memory/.claude/diary/*.md 2>/dev/null | head -1

Stage 1: Three Parallel Analyses

Run these three lenses mentally in parallel on the input:

Lens A — Root Cause (Five Whys)

Ask why five times to find the fundamental cause:

  1. What happened on the surface?
  2. Why did that happen? (immediate cause)
  3. Why did that happen? (contributing factor)
  4. Why did that happen? (systemic cause)
  5. Why did that happen? (root cause)

Extract: The deepest "why" — what fundamental pattern or assumption caused this?

Lens B — Psychological Driver (Hidden Motivation)

Uncover the real motivation behind the behavior:

  • What was I trying to achieve?
  • What insecurity or assumption might be driving this?
  • What would never be admitted out loud?
  • What need is being served by this pattern?

Extract: The hidden motivation that explains why this pattern persists.

Lens C — Prevention Strategy (Systems Thinking)

Identify feedback loops and build a gate function:

  • What incentive structure caused this behavior?
  • What feedback loop reinforced it?
  • What corrective mechanism was missing?
  • Gate function: What check would have prevented this?

Extract: A concrete prevention strategy — what to check before acting to avoid this mistake.

Stage 2: Epistemic Humility Check

Before concluding, verify:

  1. Confidence (1–5): How certain am I?
  2. Assumptions: What am I assuming is true?
  3. Alternatives: Could this be interpreted differently?
  4. Evidence: What would make me wrong?
  5. Ambiguity: Is this a genuine tradeoff where both approaches have merit?
  6. Lesson type: Is this about HOW we solved it (methodology) or WHAT the solution was (technical)?

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 15 tokens per session scan A e277921ee204

Subscribe to this mod's changes

extract is a command published in the GitHub repository spideynolove/memory (3 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 1,263 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 2026-08-31.