A clearer view of AI.
THE INDEPENDENT AI.

CODING AGENT / DEV TOOL · WORTH A LOOK

tstack (Theo Browne's agent skills)

MIT-licensed pack of nine agent skills for Claude Code and Codex covering the pull-request lifecycle: full-send (takes a change to a merged PR…

Visit github.com ↗

What tstack (Theo Browne's agent skills) does

MIT-licensed pack of nine agent skills for Claude Code and Codex covering the pull-request lifecycle: full-send (takes a change to a merged PR unattended), full-stop (stops before merge for human approval), council (three models from different providers review until they agree), sol-loop, file-pr, takeover, babysit-pr, modernize, leaving-pr-comments. Published 26 Oct 2026 by Theo Browne (T3).

Good for

  • Study a real-world skill pack as a template for your own team's SOP skills
  • Use council to get three-model review on important changes before merging

Try this in 10 minutes

  1. Write skill descriptions as triggers (when to use it), not summaries. (shown at 03:56 in the video)
  2. Tell review agents to make the smallest possible change, to stop scope creep. (shown at 05:28 in the video)
  3. Cap review loops (default 3 rounds; 5 for security/auth changes). (shown at 05:46 in the video)

From our fact-or-hype test list for “Theo (t3.gg): tstack, his agent skills for Claude Code and Codex (sol-loop, full-send, full-stop, takeover)”.

Honest take

Some claims not independently checked

  • Fact or hype verdict on Theo (t3.gg): tstack, his agent skills for Claude Code and Codex (sol-loop, full-send, full-stop, takeover): a clean, real-world example of turning daily routines into named skills that call each other; worth copying the patterns (trigger-style descriptions, capped review loops, "when to ask me" rules) even if you never run his exact setup. Source video
  • Caution: full-send grants the agent permission to merge and force-push (--force-with-lease); start with full-stop or council.

What we couldn’t verify

  • Fact vs hype: verified on GitHub README and skills.sh.

Worth testing

Pricing

Free (MIT). Needs Claude Code or Codex, an authenticated GitHub CLI and python3; council/sol-loop need a harness that can run other providers' models (extra model costs).

Prices as listed by the maker when we last checked (2026-10-27); usually in US dollars. Check the website for current prices.

Latest update

  • 2026-10-26: Released publicly with a 30-minute walkthrough video.

Is tstack (Theo Browne's agent skills) worth it? Quick answers

Is tstack (Theo Browne's agent skills) worth it?

tstack (Theo Browne's agent skills) is worth a look if it matches a job you already do (Coding agent / dev tool). It is free to use, so the main cost is your time. Some of the maker's claims have not been independently checked.

How much does tstack (Theo Browne's agent skills) cost?

Free (MIT). Needs Claude Code or Codex, an authenticated GitHub CLI and python3; council/sol-loop need a harness that can run other providers' models (extra model costs).

What is tstack (Theo Browne's agent skills) used for?

MIT-licensed pack of nine agent skills for Claude Code and Codex covering the pull-request lifecycle: full-send (takes a change to a merged PR… Typical uses: study a real-world skill pack as a template for your own team's SOP skills; use council to get three-model review on important changes before merging.