Skip to main content
plugin

slicewise — Claude Code plugin: what it does, how to install

slicewise breaks feature work into small slices, runs a test gate, compares two independent reviews, and leaves the commit decision to you.

Apache-2.0 ★ 1,013 updated 2026-08-12

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add ccplugins/awesome-claude-code-plugins
/plugin install slicewise@awesome-claude-code-plugins
Open on GitHub

What slicewise does

slicewise gives Claude Code a slice-by-slice feature workflow. Each slice goes through the project’s test gate, then two independent reviewers inspect it and a reconcile pass compares their findings. The plugin includes a skill that reacts to requests such as implementing a feature or fixing a bug, a read-only code-review agent dispatched in parallel, and the explicit /slicewise <task> command.

The default path needs no configuration because the plugin detects the project toolchain. Add .slicewise.yml at the repository root when you need a custom test command, extra documentation, or a Codex reviewer. The plugin does not commit changes automatically. You decide what lands after the tests and review results.

What it helps with

  • break feature work into reviewable slices
  • run a full test gate for each slice
  • get two independent code reviews
  • reconcile reviewer findings before committing

Example prompts for the agent

  • Implement this feature one slice at a time and test each slice.
  • Fix this bug, send the change through two independent reviews, then reconcile the findings.
  • Run /slicewise <task> to start the slice-based workflow explicitly.

How to install slicewise

Plugin marketplace

/plugin marketplace add ccplugins/awesome-claude-code-plugins
/plugin install slicewise@awesome-claude-code-plugins

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about slicewise

How do I install slicewise in Claude Code?

In Claude Code, run /plugin marketplace add ccplugins/awesome-claude-code-plugins, then run /plugin install slicewise@awesome-claude-code-plugins.

What does slicewise do?

It structures feature work as small slices. Each slice passes through tests, two separate reviews, and a reconciliation step before you decide whether to commit it.

Can I customize the slicewise workflow?

Yes. Put .slicewise.yml in the repository root to set a custom test command, include extra documentation, or add a Codex reviewer. The default workflow detects the toolchain automatically.

Source text

slicewise · Apache-2.0
# slicewise (plugin)

A disciplined, self-verifying feature-dev loop for Claude Code. Builds one slice at a time; every
commit unit gets a full test gate plus two independent reviewers reconciled against each other; you run
the commit yourself.

> Full docs, the loop diagram, and a worked example live in the
> [repository README](https://github.com/pjw81226/slicewise).

## What's in this plugin

| Component | File | Role |
|---|---|---|
| Skill | `skills/slicewise/SKILL.md` | The discipline — triggers on "implement this", "fix this bug", "refactor this", "this PR is stuck", etc. |
| Agent | `agents/code-reviewer.md` | Read-only, lens-parameterized reviewer dispatched in parallel during the review phase. |
| Command | `commands/slicewise.md` | `/slicewise <task>` — explicit entry point. |

## Install

```
/plugin marketplace add pjw81226/slicewise
/plugin install slicewise@slicewise
```

## Use

Describe a slice and let the skill trigger, or run `/slicewise <task>` explicitly. Zero config
needed — the loop auto-detects your toolchain. To customize (custom test command, extra docs, a Codex
reviewer), add a `.slicewise.yml` at your repo root; see
[docs/configuration.md](https://github.com/pjw81226/slicewise/blob/main/docs/configuration.md).

## License

[MIT](https://github.com/pjw81226/slicewise/blob/main/LICENSE)

© jwpark · Apache-2.0 · ccplugins/awesome-claude-code-plugins

Similar plugins

All plugins for Code review and refactoring →
code-review-checklist curiositech code-review-checklist is a Claude Code skill that builds a review checklist from a PR diff, using the project’s language and conventions. It highlights what reviewers should examine. CX Codex +1 185installs vitest-testing-patterns curiositech vitest-testing-patterns provides Vitest and React Testing Library conventions for coding agents. Useful for writing component tests, API route checks, and dependency mocks. CX Codex +1 373installs superpowers obra superpowers — a plugin for Claude Code and Codex that teaches the agent a complete methodology: requirements gathering, design, TDD, and subagent-driven development. Triggers automatically when you start building something new. CX Codex ★ 323,788repo stars ponytail DietrichGebert ponytail is a Claude Code plugin that steers coding tasks toward short, practical solutions. Its review command checks related code for bugs, security issues, and missing tests. ★ 196,420repo stars mattpocock-skills Matt Pocock mattpocock-skills — a set of skills for grilling, TDD, code review, and specification work. Use it when an agent needs to clarify the task before changing the code. ★ 329,816repo stars understand-anything Egonex-AI understand-anything turns codebases or markdown wikis into an interactive knowledge graph with a browser dashboard. Helps navigate unfamiliar repositories without reading files blindly. ★ 93,566repo stars serena official Oraios serena — a Claude Code plugin that integrates language server protocol for semantic analysis. Provides refactoring suggestions, code navigation, and symbol lookups across the codebase. ★ 47,914repo stars security-guidance official Anthropic security-guidance — a Claude Code plugin that reviews generated code in three layers. Regex warnings fire on edits, an LLM checks the diff after every turn, and an agentic reviewer walks related files before commits. ★ 47,914repo stars

From the same set184

The whole set →
session-tax session-tax measures token overhead in Claude Code opening context before you type. It reveals how many tokens load from unused skills, hooks, and tool schemas. ★ 1,013repo stars claude-session-tint claude-session-tint is a Claude Code plugin that colors Terminal.app windows by project and highlights a window when a reply arrives out of focus. Shared-window tabs get a title marker instead. ★ 1,013repo stars rote rote turns a skill you already trust into a deterministic pipeline with no model in the loop, then serves the compiled result back to Claude as an MCP tool. ★ 1,013repo stars bullpen bullpen — a set of skills that brings senior engineer instincts into Claude Code. It helps challenge bad assumptions, attack code before shipping, and verify results before marking tasks done. ★ 1,013repo stars craftsman craftsman is a Claude Code plugin with agents, skills and hooks that keeps changes within scope, finds a bug's root cause and reports what was verified. ★ 1,013repo stars fable-baton fable-baton turns Fable 5 into an orchestrator in Claude Code, routing implementation to tiered Opus, Sonnet, and Haiku subagents. ★ 1,013repo stars claude-bionify claude-bionify is a Claude Code plugin that applies bionic reading to model responses. It bolds the start of each word in the live terminal stream to guide eye fixations. ★ 1,013repo stars ai-meeting ai-meeting is a Claude Code plugin that runs structured decision reviews with Codex, Claude Code, and CLI adapters. ★ 1,013repo stars

Project sponsors

Companies that keep this analytics open