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-recall-verifygit 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-recall-verify)<a href="https://agentmods.dev/skills/mahmoudimus/simba/memories-recall-verify"><img src="https://agentmods.dev/badge/skills/mahmoudimus/simba/memories-recall-verify/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-recall-verify"><img src="https://agentmods.dev/badge/skills/mahmoudimus/simba/memories-recall-verify.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 | $0.00042 | $0.00674 |
| Opus 5 | $0.00021 | $0.00337 |
| Sonnet 5 | $0.00008 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
memories-recall-verify 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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Correcting Recall
Use this when you are about to answer a question whose answer depends on stored memory (preferences, decisions, facts, "what did we decide about X"), and the memories you have are ambiguous, conflicting, or incomplete. The goal is to ground the answer in the right memory — not the first plausible one — and to admit when memory doesn't contain the answer.
Step 1 — Recall
simba memory recall "<the user's question, as a statement>"
Each line is: <id> [<TYPE>] (<similarity>) <content>.
Step 2 — Detect a problem
Inspect the recalled set and decide whether you can answer directly. You cannot yet if any of these hold:
- Ambiguous reference — the question names a generic thing ("the API key", "the staging DB", "the meeting") and the memories describe multiple distinct instances of it. You must not blend facts across instances.
- Conflicting values — two memories give different values for the same attribute of the same subject.
- Scope mismatch — the memories are about a different target than the one asked about (right attribute, wrong entity).
- Insufficient — nothing recalled actually contains the asked-for value.
If none hold, answer directly from the recalled memory.
Step 3 — Re-query (the self-correction)
For an ambiguous or scope-mismatched result, run a narrower recall naming the specific entity and attribute:
simba memory recall "<specific entity> <attribute>"
Repeat once or twice with sharper terms. Broaden only if nothing returns:
simba memory recall --limit 8 "<broader phrasing>"
Step 4 — Resolve conflicts by recency
When two memories conflict, prefer the fresher one:
- Recalled context tags the most recently created memory with
recency="newest"and shows each memory'screateddate — prefer it. - For knowledge-graph facts, the currently-valid edge is the one with no
valid_to; check withsimba db facts(it printsoccurred:event dates).
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.
- 11d ago First seen · 76 lines · 42 tokens per session scan A d1683f2c6134
memories-recall-verify is a skill published in the GitHub repository mahmoudimus/simba (6 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 674 once invoked, about $0.0002 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"…
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.
honcho-integration
Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.