Enforce layer dependency rules and the domain-annotation denylist on changed files, gate on Evidence, and advance state to arch-done.
Write the minimum implementation to flip the red test green, gate on Evidence, and advance state to engine-done.
Bootstrap SPEAR docs in a greenfield project — detects stack, drafts the four docs, drops Konsist template on JVM, commits.
Write a failing test that proves the current REQ is unsatisfied, confirm red, and gate on Evidence before advancing state.
Finalize a SPEAR task — optional behavior-preserving refactor, full suite green, flip tasks.md to [x], and clear state to idle.
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.
Claude Code plugin packaging the SPEAR methodology — Spec-Proven Engineering with Architectural Requirements — as a reusable, installable plugin.
SPEAR is a hybrid of Spec-Driven Development (EARS), Test-Driven Development (red-green-refactor), and Hexagonal Architecture. The plugin enforces the cycle — blocking implementation before a failing test and blocking progression past a layer-boundary violation — and automates the boilerplate: scaffolding the four SPEAR docs, assigning REQ-IDs, tracking per-task phase in a gitignored state file.
The cycle:
spec → prove → engine → arch → refine
Each phase is its own /spear:<name> skill. A session-start hook injects the cycle rules, current phase, and tool-probe results into every Claude Code session that runs in a SPEAR project.
/plugin marketplace add BadgersMC/spear-plugin
/plugin install spear@BadgersMC-spear-plugin
/plugin reload-plugins
Claude Code caches the plugin at ~/.claude/plugins/cache/BadgersMC-spear-plugin/spear/<version>/.
/spear:init
Detects language/build tool, drafts docs/tech-stack.md, docs/requirements.md, docs/implementation.md, docs/tasks.md from bundled templates, and on JVM projects drops a Konsist LayerRulesTest.kt wired to your top-level package. Commits the result.
/spear:spec # draft or revise a REQ + derive tasks
/spear:prove # write the failing test (TDD only)
/spear:engine # minimum code to flip red → green (TDD only)
/spear:arch # layer-rule + framework-annotation scan on the diff
/spear:refine # refactor, confirm suite green, flip task [x], reset state
DOC/INFRA tasks skip prove and engine (spec-done → arch directly).
superpowersDesigned to run alongside superpowers. SPEAR defers to superpowers for brainstorming, writing-plans, executing-plans, and systematic-debugging. Inside a SPEAR project (docs/requirements.md + docs/tasks.md both present), spear:prove supersedes superpowers:test-driven-development; outside it no-ops back to the superpowers entry point.
See LICENSE.
npx claudepluginhub badgersmc/spear-plugin --plugin spearUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
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