By cssherry-wp
Team fork of superpowers (TDD, debugging, brainstorming, plans) with the team docs-path convention baked in. Enable instead of stock superpowers — never both.
Use when implementing any feature or bugfix, before writing implementation code
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin marketplace for the team. It packages our coding standards, common-task
helpers, and a curated plugin setup so everyone gets the same Claude Code experience from a single
git repo.
Verified against Claude Code 2.1.211.
This repo is itself the marketplace (.claude-plugin/marketplace.json). It ships three plugins:
| Plugin | What it gives you |
|---|---|
| wp-labs-standards | Coding-standard skills (general-coding-guidelines, python-style, typescript-style, css-style, sql-style, team-docs-convention) plus the common-task workflows /commit (structured commit-message format), change-review (broad review dispatcher — see review-skills map), github-pr-prepare, and github-pr-review. A PreToolUse hook also injects the matching standard deterministically by file type on every edit (see Deterministic standards). |
wp-labs-sdlc v0.3 | The scaffolding-sdlc skill with two modes: repo mode bootstraps a repo's full SDLC (runnable starter app, Makefile, pre-commit hook, GitHub Actions CI/security/Claude-PR-automation, Dependabot, PR-status labels, PR auto-rebase, optional hosting with Docker + Azure Bicep); --setup-claude mode configures the global ~/.claude/ environment on a fresh machine (settings, plugins, CLAUDE.md, glob-scoped coding rules). See Setting up a new machine. |
| wp-labs-superpowers | A fork of superpowers with our docs-path convention baked in. Enabled by default (the stock superpowers@claude-plugins-official is disabled to avoid duplicate skill names). See plugins/wp-labs-superpowers/FORK.md. |
We also use a curated set of external plugins (see Recommended setup).
The fastest path on a fresh machine or new Claude Code install:
git clone https://github.com/cssherry-wp/wp-labs-starter.git
cd wp-labs-starter
bash plugins/wp-labs-sdlc/skills/scaffolding-sdlc/scripts/setup-claude.sh
This writes ~/.claude/settings.json (marketplaces + plugins), ~/.claude/CLAUDE.md (commit policy, output style rules), and ~/.claude/rules/ (glob-scoped coding guidelines). Restart Claude Code — it auto-installs any plugin listed in enabledPlugins on first launch.
Alternatively, once Claude Code is running, invoke the skill:
/scaffolding-sdlc --setup-claude
See docs/setting-up-claude-environment.md for full details.
To add the marketplace and install manually:
/plugin marketplace add cssherry-wp/wp-labs-starter
/plugin install wp-labs-standards@wp-labs-starter
/plugin install wp-labs-sdlc@wp-labs-starter
/plugin install wp-labs-superpowers@wp-labs-starter
Then the external plugins:
/plugin install code-review@claude-plugins-official
/plugin install code-simplifier@claude-plugins-official
/plugin install security-guidance@claude-plugins-official
/plugin install explanatory-output-style@claude-plugins-official
/plugin install frontend-design@claude-plugins-official
/plugin install typescript-lsp@claude-plugins-official
/plugin install chrome-devtools-mcp@claude-plugins-official
/plugin install context7@claude-plugins-official
/plugin install claude-md-management@claude-plugins-official
/plugin install ralph-loop@claude-plugins-official
/plugin install playwright@claude-plugins-official
/plugin marketplace add lackeyjb/playwright-skill
/plugin install playwright-skill@playwright-skill
/plugin marketplace add DietrichGebert/ponytail
/plugin install ponytail@ponytail
Browse or manage everything anytime with /plugin.
The full recommended config lives in:
plugins/wp-labs-sdlc/skills/scaffolding-sdlc/templates/claude/settings.json
This is the single source of truth for marketplaces, enabledPlugins, the ponytail status-line badge,
the Stop hook, and team-wide Claude settings. The --setup-claude mode and the repo scaffold both
deep-merge from this file.
wp-labs-standards, wp-labs-sdlc, wp-labs-superpowers (fork), ponytail,
playwright-skill, code-review, code-simplifier, security-guidance,
explanatory-output-style, frontend-design, typescript-lsp, chrome-devtools-mcp,
context7, claude-md-management, ralph-loop, playwright.
superpowers@claude-plugins-official is explicitly disabled — the fork (wp-labs-superpowers)
replaces it. Never enable both (duplicate skill names).
npx claudepluginhub cssherry-wp/wp-labs-starter --plugin wp-labs-superpowersTeam coding-standard skills (auto-load by language) + the docs-path convention, plus common-task workflows: /commit, github-pr-prepare, and github-pr-review.
Repo SDLC bootstrapping: scaffolding-sdlc skill wires lint, tests, Playwright e2e, security scanning, Dependabot, PR-status labels, and Claude PR automation onto new or existing repos. Includes --setup-claude mode for bootstrapping the global ~/.claude/ environment on a fresh machine.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.