Agent-alchemy feature-dev
Feature development workflow with exploration, architecture, implementation, and review phases. Use for implementing new features or significant changes.
git clone https://github.com/sequenzia/agent-alchemy
T=$(mktemp -d) && git clone --depth=1 https://github.com/sequenzia/agent-alchemy "$T" && mkdir -p ~/.claude/skills && cp -r "$T/claude/dev-tools/skills/feature-dev" ~/.claude/skills/sequenzia-agent-alchemy-feature-dev && rm -rf "$T"
claude/dev-tools/skills/feature-dev/SKILL.mdFeature Development Workflow
Execute a structured 7-phase feature development workflow. This workflow guides you through understanding, exploring, designing, implementing, and reviewing a feature.
CRITICAL: Complete ALL 7 phases. The workflow is not complete until Phase 7: Summary is finished. After completing each phase, immediately proceed to the next phase without waiting for user prompts.
Phase Overview
Execute these phases in order, completing ALL of them:
- Discovery - Understand the feature requirements
- Codebase Exploration - Map relevant code areas
- Clarifying Questions - Resolve ambiguities
- Architecture Design - Design the implementation approach
- Implementation - Build the feature
- Quality Review - Review for issues
- Summary - Document accomplishments
Phase 1: Discovery
Goal: Understand what the user wants to build.
-
Analyze the feature description from
:$ARGUMENTS- What is the core functionality?
- What are the expected inputs and outputs?
- Are there any constraints mentioned?
- What success criteria can you infer?
-
Summarize your understanding to the user. Use AskUserQuestion to confirm if your understanding is correct before proceeding.
Phase 2: Codebase Exploration
Goal: Understand the relevant parts of the codebase.
-
Run deep-analysis workflow:
- Read
and follow its workflow${CLAUDE_PLUGIN_ROOT}/../core-tools/skills/deep-analysis/SKILL.md - Pass the feature description from Phase 1 as the analysis context
- This handles reconnaissance, team planning, approval (auto-approved when skill-invoked), team creation, parallel exploration (code-explorer agents), and synthesis (code-synthesizer agent)
- Note: Deep-analysis may return cached results if a valid exploration cache exists. In skill-invoked mode, cache hits are auto-accepted — this is expected behavior that avoids redundant exploration.
- Read
-
Present the synthesized analysis to the user.
Phase 3: Clarifying Questions
Goal: Resolve any ambiguities before designing.
-
Review the feature requirements and exploration findings.
-
Identify underspecified aspects:
- Edge cases not covered
- Technical decisions that could go multiple ways
- Integration points that need clarification
- Performance or scale requirements
-
Ask clarifying questions: Use AskUserQuestion to get answers for critical unknowns. Only ask questions that would significantly impact the implementation.
If no clarifying questions are needed, inform the user and proceed.
Phase 4: Architecture Design
Goal: Design the implementation approach.
-
Load skills for this phase:
- Read
and apply its guidance${CLAUDE_PLUGIN_ROOT}/skills/architecture-patterns/SKILL.md - Read
and apply its guidance${CLAUDE_PLUGIN_ROOT}/../core-tools/skills/language-patterns/SKILL.md - Read
and apply its styling rules for any Mermaid diagrams in architecture proposals${CLAUDE_PLUGIN_ROOT}/../core-tools/skills/technical-diagrams/SKILL.md
- Read
-
Launch code-architect agents:
Launch 2-3 code-architect agents (Opus) with different approaches:
Agent 1: Design a minimal, focused approach prioritizing simplicity Agent 2: Design a flexible, extensible approach prioritizing future changes Agent 3: Design an approach optimized for the project's existing patterns (if applicable)Use the Task tool with
:subagent_type: "agent-alchemy-core-tools:code-architect"Feature: [feature description] Design approach: [specific approach for this agent] Based on the codebase exploration: [Summary of relevant files and patterns] Design an implementation that: - Lists files to create/modify - Describes the changes needed in each file - Explains the data flow - Identifies risks and mitigations Return a detailed implementation blueprint. -
Present approaches:
- Summarize each approach
- Compare trade-offs (simplicity, flexibility, performance, maintainability)
- Make a recommendation with justification
-
User chooses approach: Use AskUserQuestion to let the user select an approach or request modifications.
-
Generate ADR artifact:
- Read the ADR template from
${CLAUDE_PLUGIN_ROOT}/skills/feature-dev/references/adr-template.md - Create an ADR documenting:
- Context: Why this feature is needed
- Decision: The chosen approach
- Consequences: Trade-offs and implications
- Alternatives: Other approaches considered
- Determine the next ADR number by checking existing files in
internal/docs/adr/ - Save to
(createinternal/docs/adr/NNNN-[feature-slug].md
if needed)internal/docs/adr/ - Inform the user of the saved ADR location
- Read the ADR template from
Phase 5: Implementation
Goal: Build the feature.
-
Require explicit approval: Ask the user: "Ready to begin implementation of [feature] using [chosen approach]?" Wait for confirmation before proceeding.
-
Read all relevant files: Before making any changes, read the complete content of every file you'll modify.
-
Implement the feature:
- Follow the chosen architecture design
- Match existing code patterns and conventions
- Create new files as needed
- Update existing files using Edit tool
- Add appropriate error handling
- Include inline comments only where logic isn't obvious
-
Test if applicable:
- If the project has tests, add tests for the new functionality
- Run existing tests to ensure nothing broke
-
IMPORTANT: Proceed immediately to Phase 6. Do NOT stop here. Do NOT wait for user input. Implementation is complete, but the workflow requires Quality Review and Summary phases. Continue directly to Phase 6 now.
Phase 6: Quality Review
Goal: Review the implementation for issues.
-
Load skills for this phase:
- Read
and apply its guidance${CLAUDE_PLUGIN_ROOT}/skills/code-quality/SKILL.md
- Read
-
Launch code-reviewer agents:
Launch 3 code-reviewer agents (Opus) with different focuses:
Agent 1: Review for correctness and edge cases Agent 2: Review for security and error handling Agent 3: Review for maintainability and code qualityUse the Task tool with
:subagent_type: "code-reviewer"Review focus: [specific focus for this agent] Files to review: [List of files modified/created] Review the implementation and report: - Issues found with confidence scores (0-100) - Suggestions for improvement - Positive observations Only report issues with confidence >= 80. -
Aggregate findings:
- Collect results from all reviewers
- Deduplicate similar issues
- Prioritize by severity and confidence
-
Present findings: Show the user:
- Critical issues (must fix)
- Moderate issues (should fix)
- Minor suggestions (nice to have)
-
User decides: Use AskUserQuestion:
- "Fix all issues now"
- "Fix critical issues only"
- "Proceed without fixes"
- "I'll fix manually later"
-
If fixing: make the changes and re-review if needed.
-
IMPORTANT: Proceed immediately to Phase 7. Do NOT stop here. The workflow requires a Summary phase to document accomplishments and update the CHANGELOG. Continue directly to Phase 7 now.
Phase 7: Summary
Goal: Document and celebrate accomplishments.
-
Summarize accomplishments: Present to the user:
- What was built
- Key files created/modified
- Architecture decisions made
- Architecture diagram (Mermaid flowchart showing the implemented structure)
- Any known limitations or future work
-
Update CHANGELOG.md:
- Read the entry template from
${CLAUDE_PLUGIN_ROOT}/skills/feature-dev/references/changelog-entry-template.md - Load the
skill for Keep a Changelog guidelineschangelog-format - Create an entry under the
section with:[Unreleased]- Appropriate category (Added, Changed, Fixed, etc.)
- Concise description of the feature
- If
doesn't exist, create it with proper headerCHANGELOG.md - Add the entry to the appropriate section under
[Unreleased] - Inform the user of the update
- Read the entry template from
-
Final message: Congratulate the user and offer next steps:
- Commit the changes
- Create a PR
- Additional testing suggestions
Error Handling
If any phase fails:
- Explain what went wrong
- Ask the user how to proceed:
- Retry the phase
- Skip to next phase
- Abort the workflow
Agent Coordination
Exploration and synthesis agent coordination is handled by the
deep-analysis skill in Phase 2, which uses Agent Teams with hub-and-spoke coordination. Deep-analysis performs reconnaissance, composes a team plan (auto-approved when invoked by another skill), assembles the team, and manages the exploration/synthesis lifecycle. See that skill for team setup, approval flow, agent model tiers, and failure handling details.
When launching other parallel agents (code-architect from core-tools, code-reviewer):
- Give each agent a distinct focus area
- Wait for all agents to complete before proceeding
- Handle agent failures gracefully (continue with partial results)
When calling Task tool for agents:
- Use
(cross-plugin, from core-tools)subagent_type: "agent-alchemy-core-tools:code-architect" - Use
for review agents (same plugin)subagent_type: "code-reviewer" - Code-explorer and code-synthesizer models are managed by deep-analysis
Additional Resources
- For ADR template, see references/adr-template.md
- For changelog entry format, see references/changelog-entry-template.md