Your Codebase
Improves Itself
BlockSpool scouts improvements, executes them in parallel, and batches everything into clean milestone PRs — ready for your review.
Features
One Command.
Continuous Improvement.
Point it at your repo, set a timer, and walk away. BlockSpool scouts, builds, tests, and PRs—cycle after cycle.
Milestone Mode
Batches improvements into clean PRs instead of 50 tiny ones.
Parallel Execution
Runs multiple improvements at once in isolated branches with conflict-aware wave scheduling.
Deep Mode
Finds structural problems, not just lint fixes. Principal-engineer-level architectural review.
Impact Scoring
Proposals ranked by impact x confidence. Quality gating filters out low-value changes automatically.
Adversarial Review
Devil's advocate scoring challenges every proposal before approval — only high-value work gets through.
Cross-Run Learnings
Remembers what failed and what worked across sessions. Avoids repeating mistakes, confirms successful patterns.
Spindle Detection
Catches runaway agents — QA ping-pong, command failure loops, and file churn — before they waste tokens.
Smart Deduplication
Never proposes the same fix twice. Each cycle sees all previous work.
Trust Ladder
Starts safe with refactoring, tests, and docs. Unlock more when you're ready.
Formulas
One flag for a security audit, test coverage boost, or type cleanup. Write your own in YAML.
Project Detection
Auto-detects your test runner, framework, linter, and language across 10+ ecosystems for correct CLI syntax.
Guidelines Context
Loads your CLAUDE.md or AGENTS.md into every prompt so agents follow your conventions automatically.
Let Your Codebase
Improve Itself
Free and open source. Run it, review the PRs when you're ready.