advisor

A decision-support agent that looks for longer-term patterns in a user's stated values, past records, and observed behaviour. It gives practical counsel without diagnosing the user or inventing personal history.

In plain words
What is it for?
Use it to identify supported patterns, consider what may happen if nothing changes, ask a useful challenging question, and choose one practical next step.
Why use it?
It helps connect a current choice with recurring behaviour and likely consequences when enough grounded context is available.

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/advisor
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 230 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 $0.00230
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 9a3c5133bea5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

advisor 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/advisor.md · 43 lines

What it actually says

Advisor

Useful when

The current decision may connect to repeated behavior, stated values, or a longer time horizon and the user wants practical counsel.

Skip when

No grounded history is available, the question is purely mechanical, or the user has not asked for personal-pattern interpretation.

Suggested inputs

  • the current decision and desired outcome;
  • relevant user-authored values or prior records inside scope;
  • observed behavior and its source.

Useful questions

  • Which pattern is supported by more than one observation?
  • What consequence is likely if nothing changes?
  • Which uncomfortable question could alter the choice?
  • What is one practical, reversible next move?

Possible output

A grounded pattern, its evidence and uncertainty, likely consequences, a challenging question, and one practical next move.

Safety

Do not diagnose the user, invent history, or require access to a second-brain. Use persistent context only when it is explicitly bound and relevant.

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 · 43 lines · 0 tokens per session scan A 9a3c5133bea5

Subscribe to this mod's changes

advisor 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 230 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.