Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By rhuss
Enforces specification-driven development with process discipline: refine ideas into specs, plan and implement in isolated worktrees, review code against specs with multi-agent analysis, auto-fix issues, and verify compliance before merging.
npx claudepluginhub rhuss/cc-spex --plugin spexRefine rough ideas into executable specifications through collaborative dialogue
Multi-perspective code review with 5 specialized agents, autonomous fix loop, and Deep Review Report
Reconcile spec/code mismatches with AI-guided evolution and user control
Quick reference for all spex commands
Initialize or update the project using the `specify` CLI (--refresh for templates, --update to upgrade CLI). Do NOT search for speckit or spec-kit binaries.
You MUST use this before any creative work - refines rough ideas into executable specifications through collaborative questioning, alternative exploration, and incremental validation. Use this skill when called from a command.
Multi-perspective code review with autonomous fix loop - dispatches 5 specialized review agents, merges findings, auto-fixes Critical/Important issues
Use when spec and code diverge - AI analyzes mismatches, recommends update spec vs fix code with reasoning, handles evolution with user control or auto-updates
Quick reference for all spex commands
Initialize or update the project using the `specify` CLI (--refresh for templates, --update to upgrade CLI). Do NOT search for speckit or spec-kit binaries.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Spec Driven Development toolkit - structured specification, planning, and implementation workflows for systematic feature development
Spec-driven development using GitHub spec-kit methodology. Constitution-first approach with specify, plan, tasks, and implement phases.
Specification-driven development workflow: specify → plan → tasks → implement
Skills-first specification-driven development framework with 7 agent skills for planning, implementation, review, and shipping. Natural language activation with intelligent agent orchestration. Includes /plan, /implement, /research commands plus managing-specifications, implementing-features, and reviewing-and-shipping skills.
Spec-Driven Development Workflow for Claude Code. A 6-step pipeline: Requirements → Code Analysis → Design → Implement → Verify → Self-Improve. Specifications are the source of truth, code is a verified artifact.
Spec-driven development with search, conflict detection, and reporting
Evidence-based presentation creation with Slidev, enforced design guardrails, and multi-platform diagrams
Proactive content generation with human voice and AI slop prevention for Claude Code
JIRA workflow management plugin for Red Hat AI development workflows
Hugo + Blowfish blog platform management: init, preview, migrate, legal pages
Conduct systematic security threat model assessments by analyzing code against countermeasurement requirements and generating compliance documentation with optional JIRA integration
Extend Spec-Kit with composable traits and additional workflow commands for Claude Code.
[!IMPORTANT] Starting with v4.0.0, cc-spex requires Spec-Kit 0.5.0 or later. For older Spec-Kit versions, use a 3.0.x release.
[!NOTE] This project was previously named cc-sdd. It has been renamed to cc-spex in v3.0.0 to avoid confusion with the unrelated gotalab/cc-sdd project. If you were using cc-sdd, see Migrating from sdd below.
Spec-Kit is a great foundation for specification-driven development. cc-spex is a Claude Code plugin that stays as close to upstream Spec-Kit as possible while adding orthogonal features through traits, a composable overlay mechanism similar to aspect-oriented programming for Claude Code plugins.
Each trait injects cross-cutting behavior into Spec-Kit's existing commands without modifying them. Quality gates, git worktree isolation, parallel agent execution: these concerns live outside the core workflow. Traits let you opt into them selectively, and Spec-Kit's commands remain the same underneath.
cc-spex also adds its own commands for things Spec-Kit doesn't cover, like interactive brainstorming, spec/code drift detection, and review workflows. For hands-on work, you call each step yourself in the order that fits your situation. For full automation, /spex:ship chains the entire workflow from brainstorm to verification with configurable oversight.
The recommended workflow has two phases, each producing a pull request:
Start with an idea, refine it through brainstorming, then create a formal spec and implementation plan. The output is a PR containing spec.md, plan.md, tasks.md, and a REVIEWERS.md that guides reviewers through what to look for during spec review.
/spex:brainstorm # Refine the idea through dialogue
/speckit-specify # Create formal spec
/spex:review-spec # Validate spec quality
/speckit-plan # Generate implementation plan + tasks
/spex:review-plan # Validate plan, generate REVIEWERS.md
Open a PR with these artifacts. Reviewers use REVIEWERS.md as a starting point to understand the spec's scope, key decisions, and areas that need scrutiny.
After the spec PR is reviewed and merged, implementation can proceed in one or more PRs (one per logical phase is ideal). Each implementation PR updates REVIEWERS.md with code-specific review hints, compliance notes, and areas where the reviewer should focus.
/speckit-implement # Build following the plan
/spex:review-code # Spec compliance + deep review
/spex:stamp # Final gate
If spec/code drift is detected during implementation, use /spex:evolve to reconcile: either update the spec or fix the code, then continue.
/spex:shipFor smaller features or solo projects, /spex:ship chains the entire workflow from brainstorm through verification in a single session, without intermediate PRs. It runs all nine stages autonomously with configurable oversight levels (--ask always|smart|never) and can optionally create a PR at the end with --create-pr. See Ship Command below for details.
flowchart TD
Start([Idea]) --> HasClarity{Clear<br>requirements?}
HasClarity -->|Not yet| Brainstorm["/spex:brainstorm<br>Refine idea"]
HasClarity -->|Yes| Specify["/speckit-specify<br>Create spec"]
Brainstorm --> Specify
Brainstorm -->|Full auto| Ship["/spex:ship<br>Autonomous pipeline"]
Specify --> ReviewSpec["/spex:review-spec<br>Validate spec"]
ReviewSpec --> Plan["/speckit-plan<br>Generate plan + tasks"]
Plan --> ReviewPlan["/spex:review-plan<br>Create REVIEWERS.md"]
ReviewPlan -->|PR #1: Spec| SpecPR([Spec Review & Merge])
SpecPR --> Implement["/speckit-implement<br>Build with TDD"]
Implement --> ReviewCode["/spex:review-code<br>Spec compliance +<br>deep review"]
ReviewCode --> Verify{Tests pass?<br>Spec compliant?}
Verify -->|Yes| ImplPR([PR #2+: Implementation])
Verify -->|Drift detected| Evolve["/spex:evolve<br>Reconcile"]
Evolve -->|Update spec| ReviewSpec
Evolve -->|Fix code| Implement
Ship -->|Chains all stages| ImplPR