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 commands/lancejames221b/agent-hivemind/recallgit clone --depth 1 https://github.com/lancejames221b/agent-hivemindWrote 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/commands/lancejames221b/agent-hivemind/recall)<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>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 | $0.00012 | $0.02270 |
| Opus 5 | $0.00006 | $0.01135 |
| Sonnet 5 | $0.00002 | $0.00454 |
| Haiku 4.5 | $0.00001 | $0.00227 |
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.
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
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.
- 5d ago First seen · 277 lines · 0 tokens per session scan A d0c9d3e598a7
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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.