recall

recall is a command for Claude Code from lancejames221b/agent-hivemind. It costs 12 tokens per session (2,270 once invoked), scanned A, original, MIT.

A command-line search tool for retrieving stored memories from the hAIveMind collective knowledge base.

In plain words
What is it for?
Use it to search natural-language queries, narrow results by category, limit them by time or machine, view full details, or sort findings as a timeline.
Why use it?
It helps you find earlier incidents, decisions, procedures, and solutions instead of solving the same problem again or searching through unrelated records.

Command for Claude Code

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 commands/lancejames221b/agent-hivemind/recall
Clone the repo
git clone --depth 1 https://github.com/lancejames221b/agent-hivemind

Made for: Claude Code.

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 recall

README.md
[![agentmods](https://agentmods.dev/badge/commands/lancejames221b/agent-hivemind/recall.svg)](https://agentmods.dev/commands/lancejames221b/agent-hivemind/recall)
Your own site
<a href="https://agentmods.dev/commands/lancejames221b/agent-hivemind/recall"><img src="https://agentmods.dev/badge/commands/lancejames221b/agent-hivemind/recall.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,270 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 $0.00012 $0.02270
Opus 5 $0.00006 $0.01135
Sonnet 5 $0.00002 $0.00454
Haiku 4.5 $0.00001 $0.00227

Measured 5d ago against content hash d0c9d3e598a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recall 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.

.claude/commands/recall.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

recall - Memory Retrieval

Purpose

Search and retrieve stored memories from the hAIveMind collective knowledge base using advanced semantic and text-based search capabilities.

When to Use

  • Historical Research: Find past incidents, solutions, or decisions
  • Learning from Experience: Discover how similar problems were solved
  • Context Gathering: Get background before starting new tasks
  • Documentation Lookup: Find stored procedures, configs, or guides
  • Pattern Recognition: Identify recurring issues or successful approaches
  • Knowledge Discovery: Explore collective expertise on topics

Syntax

recall "search query" [category] [options]

Parameters

  • search query (required): What to search for (can be natural language)
  • category (optional): Narrow search to specific types
    • infrastructure, incidents, security, deployments, monitoring, runbooks
  • options (optional):
    • --recent=hours: Limit to memories from last N hours
    • --limit=N: Maximum results to return (default: 10)
    • --machine=name: Search memories from specific machine
    • --detailed: Include full memory content in results
    • --timeline: Sort results chronologically

Search Capabilities

Semantic Search

  • Understands context and meaning, not just keywords
  • Finds conceptually related information
  • Works with natural language queries
  • Excellent for exploratory research

Full-Text Search

  • Exact phrase matching with quotes: "error 502"
  • Boolean operators: elasticsearch AND performance
  • Wildcard matching: mysql*
  • Technical term precision

Hybrid Intelligence

  • Combines semantic understanding with precise text matching
  • Ranks results by relevance and recency
  • Filters duplicate or near-duplicate memories
  • Provides confidence scores

Real-World Examples

Incident Investigation

recall "database connection timeout errors" incidents --recent=168

Result: Recent database connectivity issues, solutions, and patterns

Read the full file on GitHub · 277 lines

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 · 277 lines · 0 tokens per session scan A d0c9d3e598a7

Subscribe to this mod's changes

recall is a command published in the GitHub repository lancejames221b/agent-hivemind (7 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 2,270 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.