Tools/t3dotgg/tstack

tstack

The agent skills I use every day. Works with Claude Code and Codex.

3.1k ★+824/wkemergingPythonMIT License →new this week

The Lens

By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.

Updated Oct 2026

tstack is Theo Browne's personal set of agent skills for Claude Code and Codex, published under MIT. All nine are about getting a code change to a merged pull request while you're elsewhere. full-send finishes the change, proves it, files the PR, babysits CI and review bots, then merges. council gets reviews from three models from different providers and loops until they agree.

Install is a git clone and a copy into your skills folder. You need an authenticated GitHub CLI and Python 3, and the skills call each other, so install the set. They're tuned for T3 Code, Theo's free agent app, with fallbacks elsewhere. Each council round runs three flagship models at high reasoning effort, so watch your usage.

Solo devs shipping many small PRs benefit most. Small teams: read the merge rules before anyone types the trigger. These are prompts, not software, so edit them to fit your repo.

The catch: saying "full send" lets the agent merge and force-push its own branch, and it overrides ask-first testing rules in your project files, including computer use. It won't bypass branch protection. If "ask before merging" is your only guardrail, two words remove it.

Free vs Self-Hosted vs Paid

fully free

Free: All nine skills (full-send, full-stop, council, sol-loop, file-pr, takeover, babysit-pr, modernize, leaving-pr-comments) are MIT. No account or service from the author.

Self-hosted: Copy the folders into ~/.claude/skills/ or ~/.codex/skills/. Needs an authenticated gh CLI and python3 for babysit-pr's pr-wait watcher. Works best inside T3 Code (MIT, free), which supplies delegate_task and watch_pull_request; elsewhere it falls back to native subagents and the bundled watcher.

Paid: No paid tier. You pay for the models: council uses one strong model from each of three providers at high reasoning effort per round, and sol-loop needs access to OpenAI's GPT Sol.

Free skills; the cost is model usage, and council runs three providers' flagship models per review round.

What to do by team size

Solo
free; best fit for one dev shipping many small PRs
Small team
free; agree on who may trigger full-send and keep branch protection on
Medium team
free; fork and edit the skills to your merge and testing policy first
Large team
free to borrow ideas from, but autonomous merging needs your own policy review
Self-hosting ops:trivial

Get tools like this every Wednesday

One featured tool, three on the radar. No fluff.

Score
70/100 · B+
Adoption17/30
Maintenance21/25
Community7/20
License15/15
Analysis10/10

A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores

Trust Signals

Notable author: 20,903 followers

About

Owner
Theo Browne (User)
Stars
3,124
Forks
230

Explore Further

More tools in the directory