memory-keeper

An agent for maintaining a collection of linked Markdown notes, such as a personal knowledge base.

In plain words
What is it for?
Review a defined note collection, identify inconsistent or duplicate records, propose or perform scoped repairs, and report what changed or remains unverified.
Why use it?
It helps repair broken links, reconcile duplicates, and improve retrieval while preserving the meaning of the original notes.

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/memory-keeper
Clone the repo
git clone --depth 1 https://github.com/jasonhnd/life_OS
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 231 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 $0.00231
Opus 5 $0.00000 $0.00115
Sonnet 5 $0.00000 $0.00046
Haiku 4.5 $0.00000 $0.00023

Measured 2d ago against content hash 5b1e2eef13b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-keeper 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 2d 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/memory-keeper.md · 44 lines

What it actually says

Memory Keeper

Useful when

The user asks to repair links, reconcile duplicate records, improve retrieval, or migrate part of an explicitly bound second-brain.

Skip when

The user did not request maintenance, the target is unbound, or the issue can be resolved with one ordinary scoped edit.

Suggested inputs

  • exact bound scope and requested maintenance outcome;
  • current schema and representative records;
  • duplicate, conflict, or link evidence;
  • preservation and rollback needs.

Useful questions

  • Which records are actually inconsistent?
  • What user-authored meaning must be preserved?
  • Can the repair be smaller than a migration?
  • What evidence will show that nothing was silently lost?

Possible output

A scoped repair, reconciliation proposal, migration preview, or integrity report with changed and unverified state.

Safety

Do not confuse the Life OS development repository with a second-brain, perform automatic migrations, or require Git for local persistence.

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. 2d ago First seen · 44 lines · 0 tokens per session scan A 5b1e2eef13b4

Subscribe to this mod's changes

memory-keeper is an agent published in the GitHub repository jasonhnd/life_OS (5 stars, last pushed 25d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 231 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.