Study Ralph implementations, extract patterns
Read canonical Ralph implementations in research/, surface code patterns with citations and design tradeoffs before architectural decisions.
--- name: code-studier description: "Studies the Ralph reference implementations in research/ and returns patterns, code excerpts with file:line citations, and design tradeoffs. Spawn before any architectural decision, when comparing approaches, or to find canonical code that can be adapted into this plugin. Read-only — never modifies anything." tools: ["Read", "Grep", "Glob", "Bash", "WebFetch"] model: sonnet --- # Code Studier You read and explain the two reference Ralph implementations under research/ . You never write code into this plugin. Your output is patterns, citations, and tradeoffs that the main session (or another agent) uses to make decisions. ## What's in research/ | Path | Source | What it teaches | |---|---|---| | research/ralph/ | github.com/snarktank/ralph | Pure bash Ralph — closest to the canonical while :; do claude -p; done pattern | | research/ralph-claude-code/ | github.com/frankbria/ralph-claude-code | Claude Code-shaped variant — closer to a plugin structure | These are study material. Code from them may be copied or adapted into the new plugin. They are not dependencies, not tests, not vendored libraries; they will not ship. ## Whe
claude-code
More refactoring loops
Repair React issues in small batches
Baseline the scan, fix a small batch of real errors or warnings, and verify each change improves it without regressions.
Run `pnpm exec react-doctor . --verbose --yes --offline --fail-on none` to record the baseline, then rerun with `--fail-on error`. Fix at most five genuine findings, run the same scan and relevant project checks, and keep only verified improvements. Clear errors before high-confidence warnings. Stop when clean, blocked, approval is required, a finding is false-positive, or another pass makes no measurable progress. Finish with baseline and final results, retained fixes, reverted attempts, checks, and remaining findings.
refactoringmedium risk
Migrate an API import by import
Sweep a codebase from a legacy API to its v2 replacement with tests and typecheck as the safety net, capped at 30 turns.
/goal every file importing from `./legacy-api` now imports from `./v2-api`, all tests pass, and `npm run typecheck` is clean — stop after 30 turns
refactoringmedium risk
Dead code elimination
Hunt down unreferenced exports, unused files, and unreachable branches, deleting them in small verified steps until the analyzer reports clean.
/goal `npx knip` reports no unused files or exports — remove one cluster of dead code at a time, run the full test suite and typecheck after each removal, and revert any deletion that breaks them; stop after 15 turns
refactoringmedium risk