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-sanitizegit 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-sanitize)<a href="https://agentmods.dev/skills/mahmoudimus/simba/memories-sanitize"><img src="https://agentmods.dev/badge/skills/mahmoudimus/simba/memories-sanitize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mahmoudimus/simba/memories-sanitize"><img src="https://agentmods.dev/badge/skills/mahmoudimus/simba/memories-sanitize.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.00717 |
| Opus 5 | $0.00010 | $0.00358 |
| Sonnet 5 | $0.00004 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
memories-sanitize 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Sanitization Procedure
Review memories and identify those that are invalid, misleading, or outdated. This applies to any work session - debugging, feature development, refactoring, exploration, etc.
Step 1: List Memories
List all memories:
simba memory list
Or filter by type:
simba memory list --type GOTCHA
Each memory shows: id, type, confidence, and content.
Step 2: Identify Invalid Memories
Review each memory and mark as INVALID if it:
From Any Session Type
- Outdated information - Was true but no longer applies after changes
- Superseded by better approach - A newer, better solution exists
- Too specific/narrow - Only applied to a removed/changed feature
- Incorrect generalization - Specific case wrongly stated as general rule
From Debugging Sessions
- Red herring - An initial hypothesis that turned out to be wrong
- Wrong blame - Points to code that was actually working correctly
- Non-issue - Something suspected as a bug but wasn't
From Feature Development
- Abandoned approach - Design decision that was later reversed
- Prototype artifact - Workaround that was replaced by proper implementation
- Incomplete understanding - Early assumption corrected by later work
Step 3: Delete Invalid Memories
For each invalid memory, delete it:
simba memory delete <MEMORY_ID>
Step 4: Add Corrected Memories (Optional)
If an invalid memory should be replaced with a correct version:
simba memory store --type WORKING_SOLUTION --content "<CORRECT_LEARNING>" --context "<CONTEXT>" --confidence 0.95
Memory Types Reference
| Type | Use For |
|---|---|
GOTCHA |
Counterintuitive behaviors, traps, "watch out for this" |
WORKING_SOLUTION |
Commands, code, or approaches that worked |
PATTERN |
Recurring architectural decisions or workflows |
DECISION |
Explicit design choices with reasoning |
FAILURE |
What didn't work and why (useful to avoid repeating) |
PREFERENCE |
User's stated preferences |
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.
- 9d ago First seen · 95 lines · 19 tokens per session scan A ea152245deca
memories-sanitize is a skill published in the GitHub repository mahmoudimus/simba (6 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 717 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.