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 lukacf/meerkat --skill memory-retrievalgit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/memory-retrieval)<a href="https://agentmods.dev/skills/lukacf/meerkat/memory-retrieval"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/memory-retrieval/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/lukacf/meerkat/memory-retrieval"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/memory-retrieval.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 | $0.00015 | $0.00327 |
| Opus 5.5 | $0.00006 | $0.00131 |
| Sonnet 5.5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
Memory Retrieval 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 1mo 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
Memory Retrieval
Use memory for knowledge retrieval and long-horizon context recall. Memory is not live work state, not a scheduler, and not a commitment graph.
Operating Rules
- Memory is scoped to the current session: it recalls turns compacted away earlier in this session, including turns compacted before a restart or resume of the same session.
- Use
memory_searchwhen compacted context from earlier in this session would materially improve the current answer. It acceptsqueryand an optionallimit(default 5, capped at 20). - Treat matches as recalled evidence with similarity scores, not as current truth. Verify against live stores, files, APIs, or WorkGraph when correctness matters.
- Search results carry source message ranges when available. Use that typed provenance rather than guessing which later turn caused the compaction.
- Compaction summaries and host-injected context are intentionally excluded from memory indexing. Memory indexes eligible content discarded by compaction, not every message the model has seen.
- Use WorkGraph for pending, blocked, claimed, or terminal work.
- Use Schedule for future wakeups and recurrence.
- Use builtin tasks for private scratch tracking.
Scores
- Scores range from
0.0to1.0. - Higher scores are more similar, not automatically more authoritative.
- Prefer several corroborating matches over one weak match.
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.
- 1mo ago First seen · 37 lines · 15 tokens per session scan A ac022fccf713
Memory Retrieval is a skill published in the GitHub repository lukacf/meerkat (23 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 327 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.
memory-recall
Persistent cross-session memory system with fact extraction, semantic search, and compiled memory layers. Your agent remembers everything across sessions — user preferences, project context, past decisions, personal details. Use when: (1) User references something from a previous conversation, (2) Agent needs project…
session-checkpoint
Re-orient a long, dense, or interruption-prone agent session without replacing the underlying evidence. Use when the user asks for a recap, orientation, simple teaching explanation, or spoken summary; when a session has accumulated many turns or tool calls; before context compaction; or when a Brief-Spec hook says a…
memory-continuity
Preserves cross-session continuity with deterministic MEMORY.md, index.md, and snapshot handoffs under .agentic/memories/.
plan-memory-index
Maintains concise indexed memory entries for applied plans under .agentic/memories/ with clear boundaries between memory and plan sources. Memory retrieval is prioritized before loading historical plan files.
llm-wiki
Karpathy's LLM Wiki: build/query interlinked markdown KB.