StackMap
Subscribe

squid vs zeroshot

Claude Code plugin that turns a feature spec into a reviewed PR through a 5-agent pipeline — PA → SWE → Tester → PR-Reviewer → On-Call — with exactly two human gates. — versus — Executor–verifier orchestration for code changes: a conductor classifies the task, an executor works in an isolated worktree, and a separate verifier must reproduce the evidence — looped to approval.

The curated verdict

Squid is a fixed 5-agent Claude Code pipeline (PA → SWE → Tester → PR-Reviewer → On-Call) with exactly two human gates. Zeroshot routes dynamically by complexity and type, is provider-agnostic, and is built to finish without you.

squidzeroshot
Stars1821.8k
Forks29165
LanguageShellJavaScript
LicenseApache-2.0MIT
Last activity1 months agotoday
Topicscoding, orchestrationcoding, orchestration
Curated connections76

squid — the curator's take

Squid is for people who already live in Claude Code and are tired of re-explaining team conventions every session: markdown specs + five adversarial agents (no agent both writes code and judges it) turn a spec into a PR while you only show up to approve the plan and merge. When NOT: you don't use Claude Code (it's a plugin, not a standalone tool), your stack is Rust/Java/mobile (specs are Python/TS/Go for now), or you already trust an in-house pipeline. Early days and opinionated by design — adopt the opinions or skip it.

zeroshot — the curator's take

Built on one good sentence: the agent that wrote the code shouldn't be the one that says it works. A conductor scores every task on complexity (TRIVIAL→CRITICAL) and type (INQUIRY/TASK/DEBUG) with a junior model, escalating to a senior model when it answers UNCERTAIN, and that score picks the workflow — from single-worker with no validator up to debug pipelines with investigator/fixer/tester/completion-detector. Validators never share the executor's session or reasoning, and must reproduce reported failures. Runs default in a git worktree, keeps a crash-safe SQLite ledger, brings your own provider CLI and stores no keys. Reach for it when unattended runs need to be trustworthy, not fast. Skip it for interactive pair-programming: multi-agent verification loops cost several times a single agent's tokens and can run 90 minutes for one change. Linux and macOS only; the bundled Rust product is a separate, newer track.