memories-learn

memories-learn is a skill for Claude Code from mahmoudimus/simba. It costs 17 tokens per session (580 once invoked), scanned A, original, MIT.

A procedure for extracting useful lessons from coding-session transcripts and saving them in a semantic memory database. The lessons can include solutions, warnings, patterns, and decisions.

In plain words
What is it for?
Finding pending transcripts, identifying reusable coding lessons, and storing them with a type, explanation, confidence score, session, and project path.
Why use it?
Important discoveries from a session can otherwise be lost or mixed with notes from another project. This procedure links each saved lesson to its source session and project.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the simba plugin — 10 skills shipped together

Good fit Finding pending transcripts, identifying reusable coding lessons, and storing them with a type, explanation, confidence score, session, and project path.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mahmoudimus/simba/memories-learn
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.

Any agent
npx skills add mahmoudimus/simba --skill memories-learn
Clone the repo
git clone --depth 1 https://github.com/mahmoudimus/simba

Made for: Claude Code.

Or install simba, the plugin that ships this one along with the rest of its 10 skills.

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 memories-learn

README.md
[![agentmods](https://agentmods.dev/badge/skills/mahmoudimus/simba/memories-learn.svg)](https://agentmods.dev/skills/mahmoudimus/simba/memories-learn)
Your own site
<a href="https://agentmods.dev/skills/mahmoudimus/simba/memories-learn"><img src="https://agentmods.dev/badge/skills/mahmoudimus/simba/memories-learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 580 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 $0.00017 $0.00580
Opus 5 $0.00009 $0.00290
Sonnet 5 $0.00003 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 7d ago against content hash aa2a5f59d8fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

memories-learn 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 7d 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.

src/simba/skills/memories-learn/SKILL.md · 61 lines

What it actually says

Check the dispatch mode:

simba config get hooks.learn_async

Resolve the transcript for THIS project (never the global latest.json — it is a single symlink overwritten by whichever session compacted last, across all projects, so it cross-wires sessions):

simba transcript pending --json

This prints the newest pending_extraction transcript whose project_path matches the current working directory: {transcript_path, session_id, project_path} (or {} + exit 1 if there is nothing to extract for this project — in that case stop, there is no work to do). Use those three values below.

Build this Task prompt:

Read the transcript at <TRANSCRIPT_PATH> and extract learnings to store in the semantic memory database.

For each learning found, store it by running:
simba memory store --type <TYPE> --content "<LEARNING>" --context "<CONTEXT>" --confidence <SCORE> --session-source "<SESSION_ID>" --project-path "<PROJECT_PATH>"

LEARNING TYPES:
- WORKING_SOLUTION: Commands, code, or approaches that worked
- GOTCHA: Traps, counterintuitive behaviors, "watch out for this"
- PATTERN: Recurring architectural decisions or workflows
- DECISION: Explicit design choices with reasoning
- FAILURE: What didn't work and why
- PREFERENCE: User's stated preferences

RULES:
- Be specific - include actual commands, paths, error messages
- Confidence 0.95+ for explicitly confirmed, 0.85+ for strong evidence
- Skip generic programming knowledge Claude already knows
- Focus on user-specific infrastructure, preferences, workflows
- Keep content within the configured `memory.max_content_length` (default 200 characters), use context field for details
- Preserve proper nouns, file paths, and identifiers verbatim — never replace them with generic words
- Preserve numeric precision: keep exact values exact; never weaken an exact number to a range or approximation
- Resolve relative dates to absolute ones (e.g. "yesterday" -> the actual date)

Extract 5-15 quality learnings.

Dispatch using the Task tool with subagent_type=memory-extractor:

  • If hooks.learn_async is "true": set run_in_background=true (fire and forget)
  • Otherwise: dispatch normally and wait for completion

After the extractor finishes (synchronous mode only), mark the transcript done so it isn't re-extracted on the next run:

simba transcript mark-extracted <SESSION_ID>

(In async mode, skip this — the background agent owns completion.)

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. 7d ago First seen · 61 lines · 17 tokens per session scan A aa2a5f59d8fd

Subscribe to this mod's changes

memories-learn is a skill published in the GitHub repository mahmoudimus/simba (6 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 580 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.

Related

Other skills, from other repositories

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

cloud-sync

Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.

thedotmack/claude-mem · 64 tokens

hivemind-memory

Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.

activeloopai/hivemind · 33 tokens

memory-audit-pattern-extraction

A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.

Dataojitori/nocturne_memory · 48 tokens

init

Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.

grpcer/ownmem · 43 tokens

mnemo-cortex

Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.

GuyMannDude/mnemo-cortex · 44 tokens