hippocampus

hippocampus is an agent for coding agents from jasonhnd/life_OS. It costs 0 tokens per session (218 once invoked), scanned A, original, Apache-2.0.

A retrieval agent for finding relevant earlier decisions, commitments, preferences, or events in a specifically connected second brain, meaning a personal knowledge store.

In plain words
What is it for?
Use it when an answer depends on stored project history, past decisions, people, dates, or other explicitly bound records.
Why use it?
It prevents important prior context from being overlooked while avoiding unsupported searches through unrelated personal records.

Agent

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 agents/jasonhnd/life_os/hippocampus
Clone the repo
git clone --depth 1 https://github.com/jasonhnd/life_OS

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 hippocampus

README.md
[![agentmods](https://agentmods.dev/badge/agents/jasonhnd/life_os/hippocampus.svg)](https://agentmods.dev/agents/jasonhnd/life_os/hippocampus)
Your own site
<a href="https://agentmods.dev/agents/jasonhnd/life_os/hippocampus"><img src="https://agentmods.dev/badge/agents/jasonhnd/life_os/hippocampus.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 218 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 $0.00000 $0.00218
Opus 5 $0.00000 $0.00109
Sonnet 5 $0.00000 $0.00044
Haiku 4.5 $0.00000 $0.00022

Measured 5d ago against content hash a9bb48d59e3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hippocampus 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.

agents/hippocampus.md · 43 lines

What it actually says

Hippocampus

Useful when

A question depends on earlier decisions, commitments, preferences, or events stored in an explicitly bound second-brain.

Skip when

The current conversation already contains enough context or no persistent workspace is bound.

Suggested inputs

  • the current objective and subject;
  • the exact bound root and relevant time range;
  • known project, person, or decision identifiers;
  • privacy exclusions.

Useful questions

  • Which prior record could materially change the answer?
  • How recent and authoritative is it?
  • Does it describe a fact, a past interpretation, or a superseded decision?
  • What context is unnecessary?

Possible output

A small set of relevant records, dates, provenance, and decision implications.

Safety

Do not invent history, scan for an unbound second-brain, or load unrelated personal records merely because they are accessible.

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 · 43 lines · 0 tokens per session scan A a9bb48d59e3e

Subscribe to this mod's changes

hippocampus is an agent published in the GitHub repository jasonhnd/life_OS (5 stars, last pushed 28d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 218 tokens. 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 agents, from other repositories

session-learning

Extract learnings, patterns, and insights from work sessions. Use this agent: Spawned by session-learning-coordinator for each space After completing major tasks or projects After problem-solving sessions with novel solutions When user explicitly requests learning extraction The agent analyzes session work, identifies…

datacore-one/datacore · 177 tokens

session-learning-coordinator

Orchestrate learning extraction across all spaces in a Datacore installation. Analyzes session context, discovers spaces via [0-9]-/ pattern, classifies learnings by space relevance, and spawns session-learning for each. Use this agent at end of /wrap-up, /gtd-daily-end, or /tomorrow commands.

datacore-one/datacore · 76 tokens

conversation-processor

Agent "conversation-processor" from datacore-one/datacore, covering agent context, when to reference dip-0014, quick reference, related dips and related agents.

datacore-one/datacore · 24 tokens

context-maintainer

Maintain CLAUDE.md and layered context files across the Datacore system. Use this agent: During /gtd-weekly-review for comprehensive context health check When user asks to "update context" or "check CLAUDE files" After agents, commands, or modules are added/removed To validate private content isn't leaking into public…

datacore-one/datacore · 101 tokens

learning-classifier

Process new learning file entries, deduplicate against PLUR engrams, and create new engrams with proper classification. Detects recurrences, scope promotions, contradictions, and novel patterns.

datacore-one/datacore · 41 tokens

evaluator-archivist

Evaluates how well the knowledge base was used. Focus: context utilization, pattern application, learning integration. Core evaluator - always runs for every task.

datacore-one/datacore · 37 tokens