Strategic planning agent that analyzes code changes to suggest optimal commit boundaries, PR splits, and review sequences for complex development workflows.
From newtnpx claudepluginhub liebies/newt --plugin newtManages AI Agent Skills on prompts.chat: search by keyword/tag, retrieve skills with files, create multi-file skills (SKILL.md required), add/update/remove files for Claude Code.
Manages AI prompt library on prompts.chat: search by keyword/tag/category, retrieve/fill variables, save with metadata, AI-improve for structure.
Triages messages across email, Slack, LINE, Messenger, and calendar into 4 tiers, generates tone-matched draft replies, cross-references events, and tracks follow-through. Delegate for multi-channel inbox workflows.
Provide intelligent strategic planning for code changes by analyzing dependencies, identifying logical boundaries, and recommending optimal PR structures to minimize risk and maximize review efficiency.
Input: Staged files, uncommitted changes, branch diff Process:
Input: Branch diff, commit history, change complexity Process:
pr_size_limits)Input: Code structure, import relationships, data flow Process:
Input: Change complexity, affected components, system criticality Process:
Input: Team capacity, dependency constraints, release schedules Process:
Commit Boundary Analysis:
- Suggested Commits: 3
Commit 1: Add user authentication interface
Files: src/auth/interface.ts, src/auth/types.ts
Reason: Self-contained interface definition
Risk: Low
Commit 2: Implement JWT service
Files: src/auth/jwt-service.ts, src/auth/token-validator.ts
Reason: Complete implementation of auth service
Risk: Medium
Commit 3: Update login controller
Files: src/controllers/login.ts, tests/auth.test.ts
Reason: Integration with existing controller
Risk: Medium
- Dependencies: Commit 2 → Commit 1, Commit 3 → Commit 2
PR Splitting Recommendations:
- Current Size: 85 commits, 12,000 lines added
- Recommendation: Split into 3 PRs
PR 1: Authentication foundation (25 commits)
Description: Core auth interfaces and services
Risk: Low-Medium
Reviewers: @security-team, @backend-team
PR 2: Login integration (35 commits)
Description: Login flow implementation
Risk: Medium
Reviewers: @frontend-team, @backend-team
PR 3: Authorization middleware (25 commits)
Description: Route protection and permissions
Risk: Medium-High
Reviewers: @security-team, @frontend-team
- Merge Sequence: PR 1 → PR 2 → PR 3
- Estimated Timeline: 2-3 weeks
Dependency Mapping:
- Critical Path: auth-interface → jwt-service → login-controller → middleware
- Parallel Opportunities: Tests can be developed alongside implementation
- Blocking Dependencies: None detected
- Risk Areas: JWT service changes affect multiple downstream components
Risk Assessment:
- Overall Risk: Medium
Security: Medium (authentication changes)
Performance: Low (minimal performance impact)
Stability: Medium (affects login flow)
- High-Risk Components:
- JWT token validation logic
- Session management changes
- Mitigation Strategies:
- Comprehensive security review
- Staged rollout with feature flags
- Automated security testing
Timeline Planning:
- Week 1: PR 1 (Authentication foundation)
- Development: 3 days
- Review: 2 days
- Merge: 1 day
- Week 2: PR 2 (Login integration)
- Development: 4 days
- Review: 2 days
- Merge: 1 day
- Week 3: PR 3 (Authorization middleware)
- Development: 3 days
- Review: 2 days
- Merge: 1 day
- Total Duration: 3 weeks
- Critical Path: Sequential PRs (no parallelization possible)
Controlled via config/default.yml:
review_policies.pr_size_limits - Thresholds for PR splittingreview_policies.reviewer_assignment - Expert team definitionsrisk_assessment.thresholds - Risk scoring parameterstimeline_planning.team_capacity - Team velocity settingslogs/errors/pr-planning-agent.log for debugging