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.
npx skills add mahmoudimus/simba --skill memories-learngit clone --depth 1 https://github.com/mahmoudimus/simbaWrote 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.
[](https://agentmods.dev/skills/mahmoudimus/simba/memories-learn)<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>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.
| Model | Per session | Once 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 |
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.
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.)
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.
- 7d ago First seen · 61 lines · 17 tokens per session scan A aa2a5f59d8fd
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.
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"…
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.
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
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.
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.
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.