Quality

Test-Driven Development enforces the red-green-refactor loop for new features, bugfixes, and new production code. Write a failing test first, then minimal code to pass, and refactor only after green.

Absolute Audit scans a repository for dependency CVEs and risky code patterns, then triages and fixes the issues worth addressing. Use it to harden your own codebase after a disclosure or as part of routine security hygiene.

Absolute Debt clears pre-existing lint, type, and suppression debt across a repo on green main. Use it to burn down warnings, errors, and ignores in safe waves, one rule at a time, with tests passing after each wave.

Absolute Deflake finds nondeterministic tests, diagnoses the root cause, and fixes the source of flakiness. Use it when CI is flaky or a test fails intermittently, then verify the fix with repeated randomized runs.

Absolute Prune removes dead code, unused dependencies, unreferenced exports, unreachable branches, and orphaned files from the whole repo. It is used on green main and verifies each removal with tool evidence and tests before deleting anything.

Absolute Simplify cleans up staged, unstaged, or targeted code changes without changing behavior. It reduces complexity, removes redundancy, flattens nesting, and runs tests to confirm the edits still work.

Audit Fixture Tool Error invokes an always-failing tool once, then returns a fixed JSON response. Use it to verify tool_call_error event handling in end-to-end tests.

Auto Test Execution runs relevant tests after code-generating agents modify source files. It is used to enforce an execute-before-return workflow and retry when tests fail.

Code Review analyzes code for bugs, security issues, and code smells, then returns a structured set of findings and a quality score. Use it when you need an audit or actionable improvements.

Debug Memory queries and manages executable feedback session history. Use it to find past failures, inspect learned patterns, review stats, or archive the memory store.

Execute Feedback runs tests on generated code, analyzes failures, applies targeted fixes, and retries until the code passes or max attempts are reached. Use it after code generation or edits to verify behavior.

Flow Syntax validates YAML flow syntax against the pinned reference parser. Use it when you need to check whether input is accepted by that parser.