Skip to content
BotsDots

Grok Bot template · Coding & Shipping

Proof Agent

Shared by @acolombiadev

Independent verification for AI-generated diffs: runs a sealed verify pipeline and reports PASS, FAIL, or PARTIAL without judging the code itself.

Add to Grok Bot ↗Share on XRe-check link

What this Grok bot does

Independent verification for AI-generated diffs. Coordinates the sealed verify.sh | proof-agent-verify-copilot pipe and reports Copilot’s PASS, FAIL, or PARTIAL. Does not judge the code itself.

— the creator's description on the bot's x.ai share page

Proof Agent at a glance

Proof Agent is an on demand coding bot shared by @acolombiadev and first listed on 2026-10-14. It works when you message it rather than on a timer, which keeps usage low. 4 independent public catalogs list it, and its x.ai share link was last checked live on 2026-10-15.

Access and permissions

Connects accounts It mentions connecting accounts, so connect them one at a time and start read-only where you can.

  • Code repos — Touches repositories, PRs or deploys

Derived from the public description. The live configuration on x.ai is the source of truth — review it before adding.

Before you add Proof Agent

  • Give it read-only repository access first and keep merging in human hands.
  • Open the x.ai page and read the full instructions, skills and routines it ships with.

Adding a template gives you an independent copy — never the creator's chats, sessions or keys. How adding a Grok Bot template works.

More from @acolombiadev

Every Monday, a plain summary of what the team shipped

CodingWeeklyConnects accounts

Similar Grok Bot templates

More coding bots →

Keep many cloud agent runs moving without babysitting each one. Kicks off runs, monitors, chases what's stuck, and summarizes the report.

CodingOn demandConnects accounts

Claude Code

@DanielZambrini

A dedicated coding agent that runs all software work through the Claude Code CLI.

CodingOn demandLow access

Astra Oracle

@NeuralCatAccel

Sits above your Cursor cloud coding agent and runs a Codex CLI session to write structured PLAN and REVIEW packets, never code

CodingOn demandLow access

A careful QA tester for any web app's staging site. It walks through features like a real user, grades each one Pass, Partial, Fail, Blocked or Not

CodingOn demandLow access

Grok Build

@SandeshAndrade

Runs the real Grok Build CLI for apps, code, and deep research at maximum effort - for anyone who wants Grok Build on an agent computer

CodingOn demandLow access

Grok Build

@zac70182

Runs the Grok Build CLI at full effort on an agent computer for apps, code, and deep research

CodingOn demandLow access