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 agentmods add skills/lh8ppl/core-memory-kit/memory-searchnpx skills add LH8PPL/core-memory-kit --skill memory-searchgit clone --depth 1 https://github.com/LH8PPL/core-memory-kitWrote 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/lh8ppl/core-memory-kit/memory-search)<a href="https://agentmods.dev/skills/lh8ppl/core-memory-kit/memory-search"><img src="https://agentmods.dev/badge/skills/lh8ppl/core-memory-kit/memory-search.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 | $0.00208 | $0.02192 |
| Opus 5 | $0.00104 | $0.01096 |
| Sonnet 5 | $0.00042 | $0.00438 |
| Haiku 4.5 | $0.00021 | $0.00219 |
Grade A, and why
memory-search 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 4d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recalling from deep memory
You are a memory-retrieval agent. Search the kit's memory archive for: $ARGUMENTS
Query well: search the core noun phrases (e.g. "deploy target", "auth library decision"), not a full sentence. If the line above carries NO query (you run isolated and cannot see the conversation), start from the "When the query is vague" section below instead.
Memory is the ground truth for documented knowledge and prior decisions (the injected-snapshot authority rule). Your job is to find what is already recorded and return ONLY a curated summary — never the raw dumps.
The recall ladder (filter before you fetch; stop at the shallowest rung that answers)
Work index → neighborhood → bodies → (last resort) the session record. Full bodies are ~10x the tokens of an index line; fetch them only for the ids that survived filtering. Stop climbing the moment a rung answers the question — most questions end at step 1 or 2.
Step 1 — Search the index. Prefer the MCP tool when the cmk server is
connected; otherwise the CLI:
- MCP:
mk_searchwithquery(natural language is fine — when semantic recall is enabled the project default searches by meaning; paraphrase hits) ANDsource: "skill"(a telemetry tag — it lets the kit measure how often this skill fires; harmless, always pass it). - CLI:
cmk search "<query>" --source skill
Each hit is one line: id, tier/trust, source location, snippet. Run 1-3 query variants if the first misses (synonyms; the key noun alone). Drop hits that are clearly off-topic or too generic.
Score the survivors before you fetch. After dropping off-topic hits, rate each remaining hit 1-3 for how directly it answers the question (3 = likely answers it, 1 = tangential). Fetch full bodies (step 3) ONLY when at least 2 hits survive at score ≥ 2 — a lone weak hit rarely repays the tokens; answer from the index line + a re-query instead. This is the policy-retriever discipline: filter hard, fetch little.
Relative-answer re-query. If the question is relative — "the same X as Sarah", "like the auth project", "whatever we used last time" — a single search often can't resolve it. Re-query the REFERENT first (search "Sarah" / "auth project" to find X), THEN search X for the actual answer. Two cheap searches beat one that can't land.
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.
- 4d ago First seen · 173 lines · 208 tokens per session scan A e5da1254bfa2
memory-search is a skill published in the GitHub repository LH8PPL/core-memory-kit (7 stars, last pushed today), licensed MIT. It adds 208 tokens to every session and 2,192 once invoked, about $0.0010 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
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
Effective Memory
The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.
emulo
Use when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history and native emulo:mine is not available. This is the cross-agent skills.sh bootstrap, not the native namespaced plugin.
plur-memory
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.
emulo
Load the user's Emulo profile, mined from their local Claude Code, Codex, and OpenCode session logs, so you work like them instead of a cold start. Use before working on their task.
mengram-memory
Long-term memory with 3 types (facts, events, workflows). Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, or tracking completed workflows.