Agent Claude Code
Validates updated project instructions against project templates and propagates changes.
Replace chaotic AI code generation with a disciplined, spec-driven workflow. SDD Pilot enforces structured development phases and quality gates, leveraging AI agents to conduct online research for best practices and plan your architecture before a single line of code is written.
This repository also configures its own agents. See what sdd-pilot tells them →
Agent Claude Code
Validates updated project instructions against project templates and propagates changes.
Agent Claude Code
Detects the current feature branch, derives the feature directory, validates prerequisites, and returns structured context for other SDD Pilot agents.
Agent Claude Code
Generates the data model document and Entity-Relationship diagram for a feature.
Agent Claude Code
Implements a specific task from the task list, validating via compilation/linting and tests.
Agent Claude Code
Scores a feature implementation plan against phase-boundary criteria and returns a structured pass/fail verdict with specific issues found.
Agent Claude Code
Validates project artifacts against non-negotiable project instructions and governance rules.
Agent Claude Code
QC sub-agent. Executes tests, static analysis, and security tools. Asks user for permission before installing missing dependencies.
Agent Claude Code
Scans a feature specification for ambiguities and generates a prioritized queue of clarification questions.
Agent Claude Code
Scores a feature specification against quality criteria and returns a structured pass/fail verdict with specific issues found.
Agent Claude Code
QC sub-agent. Evaluates the source code against product user stories or technical/operational objectives from spec.md to ensure all requirements are fully implemented.
Agent Claude Code
Reads, parses, and returns the list of tasks from tasks.md in a structured format.
Agent Claude Code
Scores a generated tasks.md against phase-boundary criteria and returns a structured pass/fail verdict with specific issues found.
Agent Claude Code
Research authoritative external evidence and return concise, source-linked decision support to the calling agent.
Agent Claude Code
Evaluates checklist items against feature artifacts, auto-checks satisfied items, auto-resolves gaps by amending docs, and asks the user only when ambiguous.
Agent Claude Code
Generates a requirements quality checklist for a specific domain based on feature artifacts.
Agent Claude Code
Generates, validates, and writes the tasks.md file based on project design artifacts.
Agent Claude Code
Identify underspecified areas in the current feature spec and resolve them through targeted clarification questions.
Agent Claude Code
Perform non-destructive cross-artifact consistency and quality analysis across spec, plan, and tasks.
Agent Claude Code
Create/refine a project-level Deployment & Operations Document and register it as canonical deployment and operations context.
Agent Claude Code
Guides a developer through full local development environment setup — runtime tools, services, configuration, test toolchain, and verification.
Agent Claude Code
Create a feature specification from a natural language feature description.
Agent Claude Code
Create or safely refine the canonical project PRD through quick clarification or resumable product discovery.
Agent Claude Code
Propagate a project-level bootstrap change across canonical artifacts and the project plan by analyzing impact and executing the owning bootstrap workflows inline.
Agent Claude Code
Initialize a new project with non-negotiable principles and governance rules, or amend existing ones.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: