Research before you build
Gather documentation, understand requirements, and build context before writing a single line of code.
Agent: grit-pact-preparer
Design before you implement
Create detailed architectural plans, identify edge cases, and define the implementation approach.
Agent: grit-pact-architect
Build with confidence
Implement the architecture with specialized agents, pre-implementation checklists, and recovery tracking.
Agent: grit-pact-coder
Validate before you ship
Comprehensive testing with the Test Companion, automated QA loops, and human validation.
Agent: grit-pact-test-engineer
PACT's power comes from its modular architecture. Each module solves a specific problem and can be combined as needed.
| Module | Phase | Purpose |
|---|---|---|
| deep-investigation | Prepare | Mandatory codebase analysis with parallel agents |
| context7-integration | All | Library documentation lookup for any technology |
| session-memory | All | Persist discoveries across sessions |
| subtask-planning | Architect | Break work into verifiable units |
| spec-critique | Architect | Extended thinking validation before coding |
| pre-implementation-checklist | Code | Predictive bug prevention |
| self-critique | Code | Quality gate before completion |
| recovery-tracking | Code | Prevent circular fixes across sessions |
| qa-fix-loop | Test | 5-iteration structured fix cycle |
| validation-patterns | Test | API, Browser, Database verification |
Unlike traditional AI workflows where context is lost, PACT maintains session memory that compounds your learning over time.
.gritflow/
├── patterns.md # Discovered patterns (reused across sessions)
├── gotchas.md # Known issues and pitfalls
├── codebase_map.json # Project structure
├── attempt_history.json # What's been tried
└── session_insights/ # Per-session learnings
├── 2025-01-15.json
├── 2025-01-16.json
└── 2025-01-17.jsonStart with the getting started guide to install GritFlow, then run your first PACT workflow.