By hoiung
Sequential three-tier code review (Haiku surface → Sonnet logic → Opus deep), restart-on-fail. Battle-tested across hundreds of solo issues.
Tier 1 (surface) Ralph Review. Dispatched by the /ralph-review command. Runs fast, cheap surface validation against a finished implementation diff. Never writes code.
Tier 3 (deep) Ralph Review. Dispatched by the /ralph-review command after Tier 2 passes. Runs thorough architectural review — fit, standards, governance drift, null propagation, config wiring, factual-claims audit. Never writes code.
Tier 2 (logic) Ralph Review. Dispatched by the /ralph-review command after Tier 1 passes. Runs medium-depth logic validation — evidence quality, scope alignment, fail-fast, observability, cross-boundary contracts. Never writes code.
Claude Code plugin marketplace for the SST3 harness review, workflow, and subagent patterns.
/plugin marketplace add hoiung/sst3-skills
/plugin install ralph-review-trio@sst3-skills
Then run /ralph-review on a finished implementation branch.
ralph-review-trioSequential three-tier code review. A reviewer at each tier runs a different-depth checklist; if any tier fails, the loop restarts from Tier 1. No next-tier-with-flag shortcut.
| Tier | Model | Role |
|---|---|---|
| 1 | Haiku | Surface checks — file structure, commits, debug code, common-culprit scan |
| 2 | Sonnet | Logic checks — scope alignment, fail-fast policy, observability, cross-boundary contracts |
| 3 | Opus | Deep analysis — architectural fit, standards compliance, dead code, null propagation, config wiring, factual-claims audit |
Runs as a /ralph-review slash command that dispatches the three subagents in order with a restart-on-fail controller.
See plugins/ralph-review-trio/skills/ralph-review-trio/SKILL.md for the triggering instruction, and plugins/ralph-review-trio/references/ for the per-tier checklists.
## Proof of Work section in the issue body — not timeline events. Tier A phase-deliverable vs Tier B cross-cutting-meta cadence discrimination.mcp_graph_available first-line discriminator: every subagent RESULT block that discusses code-graph queries must declare MCP availability on the first line, so the controller can distinguish "no MCP access" from "lazy fallback".Scrubbed from the private SST3 harness source at dotfiles@9249dbf. Business identifiers, private trading internals, and Hoi-specific filesystem paths removed. Review provenance kept intact so the pack retains its teeth.
MIT. Use, fork, publish, adapt.
Clone and install the pre-commit hooks before making changes. Pre-commit runs the voice guard + secret scanner locally; CI runs the same checks on every push and pull request.
git clone https://github.com/hoiung/sst3-skills.git
cd sst3-skills
pip install pre-commit
pre-commit install
Verify the hooks work:
pre-commit run --all-files
If this skips because no files are staged, add --files <path> or edit a file first.
Open an issue first. Keep PRs single-purpose.
Uses power tools
Uses Bash, Write, or Edit tools
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 hoiung/sst3-skills --plugin ralph-review-trioComplete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
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.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more