What is loci-brain-settings?

A command for configuring how a Loci brain stores information, where a Loci brain is a directory containing the application’s persistent notes and identity. It can set automatic or manual saving and, for automatic saving, whether to show save notices.

Use it to inspect or create the Loci persistence configuration, choose automatic or manual saving, and enable or disable notifications for automatic saves.

It prevents configuration from being applied in the wrong directory and makes the brain’s saving behavior explicit. This helps control when information is stored and whether each save is announced.

loci-brain-settings — Command for coding agents by codesstar: A command for configuring how a Loci brain stores…

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/codesstar/loci/loci-brain-settings

Clone the repo

git clone --depth 1 https://github.com/codesstar/loci

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/codesstar/loci/loci-brain-settings.svg)](https://agentmods.dev/commands/codesstar/loci/loci-brain-settings)

Your own site

<a href="https://agentmods.dev/commands/codesstar/loci/loci-brain-settings"><img src="https://agentmods.dev/badge/commands/codesstar/loci/loci-brain-settings.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 379 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00379
Opus 5	$0.00000	$0.00189
Sonnet 5	$0.00000	$0.00076
Haiku 4.5	$0.00000	$0.00038

Measured 3d ago against content hash 1049f3dc692e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loci-brain-settings 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 3d 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.

templates/commands/loci-brain-settings.md · 37 lines

What it actually says

Configure your Loci brain's persistence settings.

Steps:

Check this is a brain: Look for .loci/ directory or check if me/identity.md exists. If not found, tell user: "This doesn't look like a Loci brain. Run this command from your brain directory."
Check existing config: Read .loci/config.yml if it exists. If it does, show current settings and ask what to change. If not, proceed with fresh setup.
Persistence mode (AskUserQuestion):

"How should your brain handle storing information?"
- Auto (recommended) — Signal-driven: AI detects when something worth storing comes up (task, decision, insight, personal info) and saves immediately. One-line notification after each save, no interrupting questions. User can say "undo" to reverse. /loci-sync also available for manual trigger anytime.
- Manual — No auto-save. Only stores when user explicitly requests or runs /loci-sync
Notifications (AskUserQuestion, only if Auto was chosen):

"Show a one-line notification after each auto-save?"
- Yes (default) — e.g. Got it — added task "Buy adapter"
- No — Silent saves, no notifications

Save config: Write .loci/config.yml in brain directory:

version: 1
persistence:
  mode: auto    # auto | manual
  notify: true  # show one-line notification after each save

Summary: Show what was configured:

Brain settings saved.

Persistence: auto (signal-driven, one-line notifications)

Run /loci-brain-settings anytime to change these.

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.

3d ago First seen · 37 lines · 0 tokens per session scan A 1049f3dc692e

Subscribe to this mod's changes

loci-brain-settings is a command published in the GitHub repository codesstar/loci (99 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 379 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 2026-08-30.

Memory and context ai claude-code open-source personal-ai

loci-brain-settings

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

release-note-csoar

doc

wf-ads

claude-tracker

oss

INDEX