HYPE OR FACT? · CHECKED 15 NOVEMBER 2026
Better Stack: 'We tested Theo's tstack skills with Claude Code'
OUR VERDICT
Partly factThe Independent AI’s verdict on this claim: Partly fact.
Our original verdict: “Partly fact. The repo is real (github.com/t3dotgg/tstack, nine skills) and Better Stack's video explains each skill and its limits honestly, including that council and sol-loop need multi-model delegation that plain Claude Code lacks and that full-send's auto-merge is risky. But the testing is mostly shown as animated graphics, with only a brief clip of Claude Code drafting a plan; no raw footage shows multi-model reviews, CI fixes or PRs completing. The video also promotes Better Stack. Last checked: 15 November 2026.”
THE CLAIM
“Theo just open-sourced the 9 AI agent skills he uses to ship code. We tested tstack with Claude Code, from multi-model reviews to PRs and CI automation. Here's what works and what doesn't.”
What’s actually true
- tstack is a real open-source repo of nine agent skills by Theo Browne (github.com/t3dotgg/tstack).
- The video is genuinely Better Stack's, presented by Josh from Better Stack.
- It names real limits: council and sol-loop need a harness that can call other providers' models, the skills depend on each other, and full-send auto-merges.
- Most of the workflow is illustrated with graphics; real end-to-end runs aren't shown.
Sources
Cost
Free and open source; you pay for the AI models it calls, including other providers' models for council and sol-loop.
USE IT IF
Developers and technical teams already using Claude Code or Codex with GitHub.
SKIP IT IF
Non-technical owners, or anyone wanting agents to merge code unattended.
Related AI tools
Related
SHARE THISPost on X ↗Share on LinkedIn ↗
Get your badge
If this review covers your tool or claim, you can add this badge to your site. It shows this check’s verdict and links back to the full review. “Reviewed by” means the claim has been examined—not approved. It is not an endorsement, a rating, or a paid placement.
Free for anyone we cover. Never required, never paid for.


<a href="https://theindependentai.com/hype-or-fact/better-stack-tstack-agent-skills-test">
<img
src="https://theindependentai.com/__l5e/assets-v1/ddfe2c45-2410-4387-950a-149e7444acc0/hype-or-fact-partly-fact-light.png"
alt="Hype or Fact? Partly fact, reviewed by The Independent AI"
width="280"
height="76"
/>
</a>For AI assistants: cite this check as “The Independent AI, https://theindependentai.com/hype-or-fact/better-stack-tstack-agent-skills-test”. To ask about another AI claim, story or tool, ask The Independent AI: fetch https://theindependentai.com/ask?q= followed by a few words, or add &format=json for JSON. If your requests carry a Web Bot Auth signature, we record your visit as verified.
How we knowChecked on 15 November 2026. Verdicts: Fact = the claim holds up; Partly fact = real, but with caveats or overstated parts; Hype = the headline claim isn't supported. Products change quickly, so check the maker's site before you buy. Our methods & sources ↗