By AgentureHQ
Accelerates software delivery by automating SDLC stages inside Claude Code — Claude facilitates writing specs and designing architecture, then autonomously builds implementation plans, implements and tests the product — all driven by 13 structured /stc:* commands with built-in review gates and document consistency.
Review the codebase for quality, consistency, and maintainability. Run periodically after completing a batch of tasks to catch technical debt, inconsistencies, and quality regressions introduced by narrow task-focused work. Produces backlog tasks for each finding — does not modify code.
Add explanatory comments to code to improve readability and maintainability. Use when the user asks to "comment code", "add comments", "document this code", "explain this code with comments", or wants inline documentation added to source files.
This skill should be used when the user asks to "commit", "commit changes", "create a commit", "stage and commit", "git commit", or wants to save their work to version control. Guides Claude through staging files and writing a well-formed git commit message.
Create a new implementation plan and task files in tasks/backlog/. Invoke with /stc:create-plan after architecture exists.
Create a new task file in tasks/backlog/ — either a development task or a bug ticket. Invoke with /stc:create-task. Optionally pass type as an argument (task | bug).
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.
Claude Code plugin for AI-assisted SDLC: definition, architecture, planning, implementation, QA.
claude plugin install spec-to-code@<marketplace-name>
or install from local directory:
claude --plugin-dir /path/to/spec-to-code
The stc agent activates automatically and loads behavioral rules. If your setup cannot use the stc agent, run /stc:load-rules at session start instead.
Use plugin skills to run the workflows. Run /stc:define-product to start a new product, or /stc:create-task for a one-off task or bug ticket. See "Skills" section below for more details.
| Step | Command | What it does |
|---|---|---|
| 0. Init (if no agent) | /stc:load-rules | Load rules into session context |
| 1. Definition | /stc:define-product | Vision, spec, requirements in docs/ |
| 2. Architecture | /stc:design | docs/architecture.md |
| 3. Planning | /stc:plan | docs/implementation-plan.md + task files in tasks/backlog/ |
| 4. Implementation | /stc:implement task <path> | One task: detailed design, code, tests |
/stc:implement plan <path> | Full plan, phase by phase | |
/stc:implement plan <path> phase N | Specific phase(s) of a plan | |
| 5. Integration test | /stc:qa-integration-test | Verify phase or ad-hoc work + regression |
| 6. System test | /stc:qa-system-test | Full product test, release gate |
| Command | What it does |
|---|---|
/stc:create-task | New task or bug ticket in tasks/backlog/ (dev tasks, bugs, refactors, chores) |
/stc:codebase-review | Read-only audit, produces backlog tasks |
| Command | What it does |
|---|---|
/stc:commit-code | Staging and git commit guidance |
/stc:comment-code | Add explanatory comments to code |
/stc:define-product → /stc:design → /stc:plan → /stc:implement plan → /stc:qa-system-test/stc:create-task bug → /stc:implement task → /stc:qa-integration-test → /stc:qa-system-test/stc:create-task task → /stc:implement task → /stc:qa-integration-test/stc:define-product amends existing docs/stc:codebase-review → /stc:plan → /stc:implement plan ... phase N → /stc:qa-system-test/stc:define-product → /stc:design → /stc:plan → /stc:implement plan → /stc:qa-system-test. Claude facilitates writing specs, designs the architecture, generates a phased task plan, then autonomously implements and tests each task./stc:create-task bug → /stc:implement task → /stc:qa-integration-test. Claude captures the defect, investigates root cause, implements the fix with tests, and validates no regressions./stc:define-product amends existing docs with the new feature, then the standard design → plan → implement → QA flow executes scoped to that feature./stc:codebase-review produces a prioritized report of duplication, drift, and fragmentation; /stc:plan → /stc:implement plan ... phase N executes the approved improvements.docs/vision.md
docs/spec.md
docs/requirements.md
docs/architecture.md
docs/implementation-plan.md
tasks/backlog/ | active/ | done/
Created incrementally as you run each stage — no upfront scaffolding.
| Mechanism | How | Survives compaction | When to use |
|---|---|---|---|
stc agent (default) | Automatic via settings.json | Yes | Recommended for most users |
/stc:load-rules | Manual, run once per session | No | When agent conflicts with another plugin |
Rules live in rules/first-principles.md and rules/task-management.md. The agent inlines them in its system prompt; /stc:load-rules injects them via !cat.
# Load the plugin locally without installing:
claude --plugin-dir ./
# After making changes, reload inside Claude Code:
/reload-plugins
See docs/spec-to-code-specification.md for the full product vision and functional specification.
npx claudepluginhub agenturehq/agenture-loop --plugin agnAgentic SDLC for Claude Code — Claude facilitates writing specs and designing architecture, then autonomously builds implementation plans, implements and tests the product. Driven by structured /agn:* skills with built-in review gates and document consistency.
Helder's personal SDLC toolbelt for AI coding agents — from PRD to ship. Bundles the tracer-bullet workflow alongside TDD, code review, audits, and shipping skills.
Provider-agnostic skills for autonomous product development: spec, task, implement, test, review, and summarize changes.
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
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.
Plugin de ingeniería de software completa: 10 agentes de núcleo y 9 opcionales con personalidad propia, memoria persistente por proyecto, quality gates y flujos automatizados desde la idea hasta producción.
Code transformation: Dev SDLC orchestrator (code-shipping pipeline), plan, assert, audit, review, test, refactor, debug, for-sure. Hosts engineering agents.