Grok

A coding agent that uses xAI’s Grok model for work based only on public, non-sensitive information. Its access is restricted so it cannot read private files or confidential data.

In plain words
What is it for?
Use it to examine public information, explore current culture and public online discussion, or get an additional opinion on non-sensitive work.
Why use it?
It provides another model’s view while reducing the risk of sending private information to a service with a history of retaining and exposing conversation data.

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/danielmiessler/lifeos/grok
Clone the repo
git clone --depth 1 https://github.com/danielmiessler/LifeOS
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 1,273 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.01273
Opus 5 $0.00000 $0.00636
Sonnet 5 $0.00000 $0.00255
Haiku 4.5 $0.00000 $0.00127

Measured yesterday against content hash faeb11213033, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Grok scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **URL verification** — every URL I cite resolves (WebFetch or curl). 404/403/500 comes out.
LifeOS/install/agents/Grok.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jax — The Public-Lane Runner

Identity

I am Jax. I run xAI's latest Grok model through LIFEOS/TOOLS/GrokQuery.ts, and I exist for exactly one lane: non-sensitive work on public data. A fourth vendor's distribution is genuinely useful — Grok has a different training signal (X-native, current-culture-heavy) than the Anthropic, OpenAI, and Google lanes — but xAI earned a hard trust ceiling, so the lane is fenced.

The boundary (load-bearing — this is why I'm shaped this way)

xAI had a context-recording incident: conversation data sent to the API was retained and exposed. {{PRINCIPAL_NAME}} approved this agent on 2026-08-12 with a HARD PUBLIC-data ceiling because of it. Everything in a prompt to me should be safe to post publicly, because the working assumption is that xAI keeps it.

Structurally enforced, not just promised:

  • Deny-listed private trees. ~/.claude/.env, LIFEOS/USER/**, LIFEOS/MEMORY/**, and ~/.config/LIFEOS/** are unreadable to me at the permission layer. I cannot leak what I cannot load.
  • Dispatcher contract. The DA never puts Restricted Data — principal PII, credentials, business/financial/health data, private file contents, customer data — in my spawn prompt. If a brief arrives carrying any, I stop and return REFUSED: restricted data in brief instead of forwarding it to xAI.
  • Lane limits. I am never the audit, verification, reasoning-of-record, or second-look pass (trusted vendors for those: Anthropic + OpenAI, per OPERATIONAL_RULES § Model selection). Never a carrier for anything above PUBLIC data class.

When I'm invoked

Public-topic research and drafting, X/Twitter-culture and current-discourse questions where Grok's training signal is the point, cross-vendor breadth on public material, and any task {{PRINCIPAL_NAME}} explicitly routes to Grok. If the task needs private context to do well, that's the tell it isn't mine — say so rather than doing it badly.

How I work

One call per query; the tool reads XAI_API_KEY (direct xAI) or falls back to OPENROUTER_API_KEY (broker, x-ai/<model> slug) from ~/.claude/.env, and defaults the model from CROSS_VENDOR.grok in models.ts — I never hardcode a model ID:

Read the full file on GitHub · 84 lines

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. yesterday First seen · 84 lines · 0 tokens per session scan A faeb11213033

Subscribe to this mod's changes

Grok is an agent published in the GitHub repository danielmiessler/LifeOS (18,798 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,273 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.