An engineering loop for Claude Code: the main session leads, ponytail builds, critic reviews. Adapted from pstack by Lauren Tan.
概览
keel is an engineering loop for Claude Code and Codex. The main session you talk to is the lead, ponytail builds, and critic reviews. pstack's method, skills, playbooks, principles and writing are hers, released under the MIT license, apart from material pstack itself adapted from others, which THIRD_PARTY_NOTICES.md credits. keel ports them from Cursor to Claude Code and Codex and reorganizes the agents around them, so the credit for how keel works belongs to pstack first. keel is an independent project and is not affiliated with or endorsed by Lauren Tan, Cursor, Anthropic or OpenAI. See credits and license. In this README, lowercase passages are pstack's original text, lightly adapted. Sentence-case passages are keel's. - is the main session. For real engineering work it loads the Claude Code or Codex lead skill, routes the task to one of 23 playbooks, and owns the design, plan, review and verification. Small asks it just does.
README
以下为原文 README 节选,完整内容请查看原文。
keel
keel is an engineering loop for Claude Code and Codex. The main session you talk to is the lead, ponytail builds, and critic reviews.
keel is adapted from pstack by Lauren Tan (poteto). pstack’s method, skills, playbooks, principles and writing are hers, released under the MIT license, apart from material pstack itself adapted from others, which THIRD_PARTY_NOTICES.md credits. keel ports them from Cursor to Claude Code and Codex and reorganizes the agents around them, so the credit for how keel works belongs to pstack first. keel is an independent project and is not affiliated with or endorsed by Lauren Tan, Cursor, Anthropic or OpenAI. See credits and license. In this README, lowercase passages are pstack’s original text, lightly adapted. Sentence-case passages are keel’s.
what it is
- The lead is the main session. For real engineering work it loads the Claude Code or Codex lead skill, routes the task to one of 23 playbooks, and owns the design, plan, review and verification. Small asks it just does.
- ponytail (Claude agent) owns one slice or pull request end to end: build, test, prove it on the real artifact, commit. In Codex, the lead gives that brief to a worker. A ponytail owner merges only under autopilot or when its brief says to land it.
- critic (Claude agent), generalized from pstack’s comment-review persona, Comment Sicko, reviews a diff through one lens: comments by default, or correctness, security, simplicity, tests or user impact. Codex gives the same brief to an independent reviewer.
keel keeps 54 of pstack’s 57 skills (its 24 principles are among them) and all 23 playbooks. Differences from pstack lists what changed.
install
Claude Code
keel needs Claude Code, git, the GitHub CLI gh (signed in), python3 for the git guard, bun for the playbook scripts and node for the multi-phase plan checker. Optional: the Codex CLI for the cross-model review lane and tmux for driving interactive terminal apps.
claude plugin marketplace add tristanphvn/keel
claude plugin install keel@keel
To try it for one session without installing, clone the repository and run claude --plugin-dir ./keel.
Skills run as /keel:, and the agents are keel:ponytail and keel:critic. The main session loads lead on its own when a task needs it, or you type /keel:lead. The other keel skills are user-invoked, except typescript-best-practices, which loads on its own for .ts and .tsx files. lead reads the user-invoked ones by path when a step needs one.
Codex
推荐工具
换一个关键词,或者移除筛选条件。
安装
npx skillfish add tristanphvn/keel