squid: Instructions file for Claude Code

Squid: An Opinionated Software Factory for Claude Code

This repo is a Claude Code plugin. The contract layer is markdown — agents and skills; nothing else ships.

Consumers install it two ways:

1. /plugin marketplace add iusztinpaul/squid && /plugin install squid@iusztinpaul — global, all Claude Code sessions. The repo is a one-plugin marketplace (.claude-plugin/marketplace.json) named iusztinpaul (the GitHub account) cataloguing the squid plugin (the repo). The plugin's source is ./ — the plugin is the marketplace repo, so Claude Code resolves it from the marketplace checkout instead of re-cloning. Same shape as caveman, ponytail, and the official marketplace.
2. claude --plugin-dir /path/to/squid — for plugin-development sessions only; loads the plugin from the working tree without registering or installing anything.

Either way they get an opinionated agent team plus a /squid-scaffold flow that bootstraps new repos from a light spec library.

For users of this plugin: read README.md. This file is for people editing the plugin itself.

Key Principles You Will Respect All Over Your Work

• Prefer removing instructions over adding them; write docs, code, and rules with the minimum words that achieve the goal.
• Whenever you add a new rule within the memory (such as AGENTS.md), resources or skills, support it with a clear, concise explanation, plus a set of good and bad examples. Good examples: "a 200-token chunk size", "sub-100ms latency". Bad examples: "a powerful architecture", "a robust pipeline".

What's in the repo

.
├── .claude-plugin/
│   ├── plugin.json                    # Claude Code plugin manifest (name, version, description)
│   └── marketplace.json               # one-plugin marketplace catalog so `/plugin install squid@iusztinpaul` works
├── agents/                            # five sub-agents
├── skills/
│   ├── squid-scaffold/                # /squid-scaffold — bootstrap a new repo (create) or audit drift (evaluate)
│   │   └── evaluate.md                # mode=evaluate flow (E1–E4), loaded on demand
│   ├── squid-plan/                    # /squid-plan — feature spec → approved Tasks Plan (+ worktree)
│   ├── squid-implement-task/          # /squid-implement-task — autonomous task loop (SWE↔Tester, commit each)
│   ├── squid-implement-night/         # /squid-implement-night — end-to-end pipeline (thin orchestrator)
│   ├── squid-review/                  # /squid-review — push + PA acceptance + PR-Reviewer
│   ├── squid-review-ci/               # /squid-review-ci — On-Call drives CI green
│   ├── squid-grilling/                # /squid-grilling — stress-test a plan (used inside /squid-plan; adapted from mattpocock/skills, MIT)
│   ├── squid-testing-python/          # test-writing conventions
│   │                                  # below: standalone, not wired into the pipeline
│   ├── squid-refactor/                # /squid-refactor — refactor planner
│   ├── squid-triage-issue/            # /squid-triage-issue — bug intake
│   ├── squid-architecture-review/     # /squid-architecture-review — audit
│   ├── squid-clean-docs/              # /squid-clean-docs — prose cleanup: docs, comments, docstrings
│   ├── squid-clean-memory/            # /squid-clean-memory — memory-file shrink: compress, dedupe, merge
│   ├── squid-clean-harness/           # /squid-clean-harness — .agents shrink: skills + resources, same logic fewer tokens
│   └── squid-write-skill/             # /squid-write-skill — skill-authoring reference (vendored from mattpocock/skills, MIT)
└── README.md                          # user-facing (install + what's inside)