Multi-agent pull request review that surfaces every finding instead of hiding low-confidence ones. /deep-review:review scores each issue, then presents all of them in-session triaged into now/soon/optional tiers and posts to the PR on confirm. /deep-review:auto skips scoring, auto-applies fixes for every issue to the working tree, and posts a summary comment - no confirmation.
A Claude Code plugin for multi-agent pull request review that surfaces every finding instead of hiding the low-confidence ones.
The built-in /code-review command runs a 5-agent review, scores each candidate issue 0-100 for confidence, then filters out everything below 80 and posts only the survivors. That hard cutoff hides medium- and low-confidence findings entirely. deep-review keeps the same review engine but changes what happens to the findings.
/deep-review:review [pr-number|pr-url|branch]The default, full-fidelity review.
/code-review: eligibility check, CLAUDE.md gathering, PR summary, 5 parallel reviewers, and per-issue 0-100 confidence scoring./deep-review:auto [pr-number|pr-url|branch]A faster, no-confirmation variant.
git diff, then commit and push yourself. The command never commits or pushes.claude plugin marketplace add ringo380/robworks-claude-code-plugins
claude plugin install deep-review@robworks-claude-code-plugins
Then restart Claude Code. The commands appear namespaced as /deep-review:review and /deep-review:auto.
gh) authenticated against the repo you are reviewing./deep-review:auto: the pull request's head branch checked out locally with a clean tree./code-review/code-review | /deep-review:review | /deep-review:auto | |
|---|---|---|---|
| Confidence scoring | yes | yes | no |
| Drops issues below 80 | yes | no (triages instead) | n/a |
| Shows all findings in-session | no | yes | n/a |
| Confirmation before posting | no | yes | no |
| Applies fixes | no | no | yes (working tree, uncommitted) |
MIT - Ryan Robson and Robworks Software LLC.
No model invocation
Executes directly as bash, bypassing the AI model
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub ringo380/robworks-claude-code-plugins --plugin deep-reviewDrive Google Colab from Claude Code over a bundled MCP server — open Drive notebooks, run code in the kernel, manage multiple sessions, upload/download VM files, mount Drive, read Colab secrets, inspect variables, edit notebook cells, and run fine-tune round-trip + local MLX conversion helpers. Optional headless/Playwright backend. Includes guided /colab:setup and /colab:help commands.
Capture session learnings into the right Claude Code memory tier. /notation:notate grounds itself in the session transcript and project profile, turns each learning into a routed proposal (global CLAUDE.md, ~/.claude/notes/, per-project MEMORY.md, or project docs), and applies them through an interactive picker - with a lean bias that keeps CLAUDE.md small. /notation:notate-all applies every proposal without the picker. Ships a notation-audit skill that flags bloat, stale notes, and orphaned index entries.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Real-time statusline HUD for Claude Code - context health, tool activity, agent tracking, and todo progress
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer