memory-search

memory-search is a skill for Claude Code, Codex from aksika/abtars. It costs 14 tokens per session (526 once invoked), scanned A, original, Apache-2.0.

A command-line search for persistent agent memory containing facts, decisions, and past conversations.

In plain words
What is it for?
Use it to recall previous decisions, look up information about a person or project, or find recent discussion history.
Why use it?
It helps recover relevant context from earlier discussions instead of relying only on the current chat. English search terms, optional original-language terms, dates, stages, and entities can narrow the results.

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/aksika/abtars/memory-search
Any agent
npx skills add aksika/abtars --skill memory-search
Clone the repo
git clone --depth 1 https://github.com/aksika/abtars

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 memory-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/aksika/abtars/memory-search.svg)](https://agentmods.dev/skills/aksika/abtars/memory-search)
Your own site
<a href="https://agentmods.dev/skills/aksika/abtars/memory-search"><img src="https://agentmods.dev/badge/skills/aksika/abtars/memory-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 526 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 $0.00014 $0.00526
Opus 5 $0.00007 $0.00263
Sonnet 5 $0.00003 $0.00105
Haiku 4.5 $0.00001 $0.00053

Measured 5d ago against content hash 8d0275f19a0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 5d 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.

templates/skills/memory-search/SKILL.md · 49 lines

What it actually says

Full documentation for abmind recall. See TOOLS.md for quick reference.

abmind recall --translated "kw1,kw2" --chat-id 7773842843 [--original "szó"] [--time-start <ms>] [--time-end <ms>] [--max-classification 0-2] [--stages S1,S3] [--entity "Name"]

Parameter rules

  • --translated: ALWAYS English keywords. Translate the user's words to English.
  • --original: If the user spoke in a non-English language, pass the original keyword here. Omit if the conversation is in English. Example: user says "chien" → --translated "dog" --original "chien"
  • --stages: Optional. Run only specific stages (S1-S7, Se). Omit to run all.
  • --entity: Optional. Filter results to memories linked to a specific entity (person, agent, project). Example: "what do you know about Alice?" → --entity "Alice"
  • Legacy: --keywords is accepted as alias for --translated.

Keyword rules

  • Use English content words for --translated, NOT meta-words ("recent", "last session")
  • For vague queries ("what did we talk about?"): use "summary,discussion,update,decision" + --time-start 24-48h ago
  • DB uses FTS5 — only actual content matches

Classification in context

  • --max-classification 0: group chats, A2A (UNCLASSIFIED only)
  • --max-classification 2: direct messages (default, up to CONFIDENTIAL)
  • SECRET (3) always excluded

Expand source messages

abmind expand --ids 451,452,453

Use when results have source_ids and you need original context or "when did I say that?"

When to use

  • User's message doesn't make sense in current context
  • User asks to recall: "do you remember", "emlékszel", "what did we talk about"
  • User references past topic/person/event not in current conversation

When NOT to use

  • Short confirmations ("yes", "ok", "do it")
  • Current context already explains the message
  • User giving clear new instructions
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. 5d ago First seen · 49 lines · 14 tokens per session scan A 8d0275f19a0a

Subscribe to this mod's changes

memory-search is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 526 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.

Related

Other skills, from other repositories

personal-assistant

A personalized assistant that remembers your preferences.

NVIDIA/SkillSpector · 11 tokens

memory-consolidate

Reflective consolidation pass over Serena memory files. Separates durable context (preferences, working style, key relationships, recurring workflows) from dated context (projects, deadlines, one-off tasks), merges duplicate topic files onto the richer path, converts relative dates to absolute ones, and tidies…

rjmurillo/ai-agents · 137 tokens

memory-enhancement

Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, checking memory health, or verifying code references are still valid. Use when you say "add a citation", "verify this memory's code refs", "check memory health". Do NOT use for searching or creating…

rjmurillo/ai-agents · 80 tokens

memory

Thin router for the tiered memory system. Points callers at the focused sub-skills for each operation, Tier 1 search, the reflexion write path, the memory-first gate, maintenance, and consolidation. Use when you ask "what do we know about X", "recall prior context", or "search memory" and are not sure which operation…

rjmurillo/ai-agents · 99 tokens

curating-memories

Guidance for maintaining Forgetful record quality and in-file Serena supersession markers. Covers updating outdated records, marking obsolete content, and linking related knowledge. Use when you say "how do I update a memory", "how do I mark a memory obsolete", or "how do I deduplicate Forgetful memories". Do NOT use…

rjmurillo/ai-agents · 89 tokens

memory-gate

Memory-First Gate (BLOCKING) and the Chesterton's Fence investigation protocol, split out of the memory router per ADR-063. Forces a memory search before you change existing code, constraints, or protocol, so the "why" is recovered before the fence comes down. Use when you say memory-first gate, search memory before…

rjmurillo/ai-agents · 109 tokens