advanced-memory-search

advanced-memory-search is a skill for Claude Code, Codex from BrianV1981/aim. It costs 35 tokens per session (117 once invoked), scanned A, original, MIT.

A deep search tool for an Engram database, which stores an agent's past information or decisions. It combines meaning-based search with exact text matching.

In plain words
What is it for?
It is for questions such as what was decided about a topic last week across the entire database.
Why use it?
It helps find an old decision or piece of context even when the current wording does not exactly match the stored note.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/brianv1981/aim/advanced-memory-search
Any agent
npx skills add BrianV1981/aim --skill advanced-memory-search
Clone the repo
git clone --depth 1 https://github.com/BrianV1981/aim

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for advanced-memory-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/brianv1981/aim/advanced-memory-search.svg)](https://agentmods.dev/skills/brianv1981/aim/advanced-memory-search)
Your own site
<a href="https://agentmods.dev/skills/brianv1981/aim/advanced-memory-search"><img src="https://agentmods.dev/badge/skills/brianv1981/aim/advanced-memory-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 117 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00117
Opus 5 $0.00017 $0.00059
Sonnet 5 $0.00007 $0.00023
Haiku 4.5 $0.00003 $0.00012

Measured 4d ago against content hash ae24a1ddafcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

advanced-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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/advanced-memory-search/SKILL.md · 15 lines

What it actually says

Runs a deep hybrid (semantic + FTS5) search across the entire Engram DB — perfect for "what did we decide about X last week?"

To execute this skill, run the included Python script and pass any JSON arguments if required by the prompt:

python3 scripts/run.py '{"arg_name": "arg_value"}'
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 4d ago First seen · 15 lines · 35 tokens per session scan A ae24a1ddafcc

Subscribe to this mod's changes

advanced-memory-search is a skill published in the GitHub repository BrianV1981/aim (13 stars, last pushed 22d ago), licensed MIT. It adds 35 tokens to every session and 117 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 2026-08-30.

Related

Other skills, from other repositories

wrapup

Wrap up and save the current session summary to the session log. Use at end of session when the user says 'bye', 'wrap up', 'save session', or an end-of-session signal is detected. /wrapup writes to 07-logs/ only. Do NOT use for: promoting insights to memory/ (use recap), synthesizing a topic across sessions (use…

onebrain-ai/onebrain · 91 tokens

onboarding

First-run setup for OneBrain : personalize identity, communication style, and vault configuration. Use only on first install or when the user wants to fully reconfigure OneBrain from scratch — manual only. Do NOT use for: teaching a single preference (use learn), updating system files (use update), or reviewing memory…

onebrain-ai/onebrain · 70 tokens

memory-review

Interactive review of all memory/ files — keep, update, deprecate, or delete entries one by one. Use when the user wants to audit and prune accumulated memory — 'review my memory', 'clean up what you remember'. Do NOT use for: teaching a new fact (use learn), recalling something specific (read memory directly), or…

onebrain-ai/onebrain · 81 tokens

recap

Batch-promote recurring insights from session logs into memory/ files with frequency filtering. Use when the user wants to extract persistent lessons or patterns from recent sessions — 'recap my recent sessions', 'what have I been learning lately'. Do NOT use for: saving a single fact now (use learn), writing today's…

onebrain-ai/onebrain · 86 tokens

consolidate

Review inbox and recent notes, synthesize and merge into the knowledge base. Use when the user wants to process, organize, or clear the inbox regardless of topic — 'clean up my inbox', 'process my notes'. Do NOT use for: capturing new information now (use capture or braindump), synthesizing already-vaulted notes on a…

onebrain-ai/onebrain · 95 tokens

learn

Teach the agent a new fact or behavioral preference and save it to memory/ for future recall. Use when the user says 'remember that', 'from now on', 'always do X', or corrects agent behavior they want persisted. Do NOT use for: capturing a general note or idea (use capture), saving a session summary (use wrapup), or…

onebrain-ai/onebrain · 84 tokens