tokenlean

Add new functionality by understanding existing patterns and dependencies before writing code. Locates where the feature belongs, studies conventions, implements following precedent, then verifies integration. Use when asked to add a feature, flag, endpoint, component, or module.

Thorough code review using token-efficient context gathering. Analyzes PRs, diffs, or staged changes by checking blast radius, complexity, and dependencies before reviewing the actual code. Use when asked to review a PR, review changes, or do a code review.

Systematically investigate and fix bugs using token-efficient context gathering. Reproduces the issue first, localizes with blame and history, traces the call path, then verifies the fix. Use when asked to fix a bug, investigate an error, or debug unexpected behavior.

Diagnose and fix performance issues by measuring before optimizing. Establishes baselines, identifies bottlenecks through call graphs and complexity analysis, then confirms improvements with numbers. Use when asked to optimize, speed up, reduce memory usage, or fix slowness.

Efficiently explore and understand an unfamiliar codebase using token-lean context gathering. Maps project structure, identifies key files, and builds understanding progressively without reading everything. Use when onboarding to a new project, asked to understand a codebase, or starting work in unfamiliar code.

Migrate frameworks, APIs, or language versions incrementally with verification at each step. Surveys the migration surface, batches work by dependency order, and commits after each verified batch. Use when asked to migrate between frameworks, upgrade major versions, or adapt to new API versions.

Refactor code safely by analyzing blast radius and dependencies before making changes. Covers renaming, moving, extracting, and restructuring code with verification at each step. Use when refactoring, renaming symbols, extracting functions, moving files, or restructuring code.

Upgrade dependencies safely by auditing usage, researching breaking changes, and verifying after upgrade. Scales effort to version jump size — light check for patches, full audit for majors. Use when asked to upgrade, bump, or update a dependency or package.

Write effective tests by studying existing test patterns and understanding the code under test before writing assertions. Discovers test conventions, prioritizes public API coverage, and validates results. Use when asked to write tests, add test coverage, or create test files.

Add new functionality in Codex by mapping existing architecture first, then implementing the smallest compatible change and verifying behavior with focused checks.

Review changes in Codex with a risk-first workflow: establish scope, inspect high-impact files first, identify regressions/security issues, and report findings by severity.

Fix bugs in Codex by enforcing reproduction first, tracing the failing path with minimal reads, applying the smallest safe fix, and re-running the repro and relevant tests.

Improve performance in Codex by measuring baseline behavior, isolating hot paths, implementing focused optimizations, and confirming wins with before/after numbers.

Explore unfamiliar repositories in Codex by building a quick structural map, identifying execution entry points, and drilling into only the highest-value files.

Execute framework or API migrations in Codex through dependency-ordered batches, validating each batch before moving on to keep the codebase continuously working.

Refactor safely in Codex by mapping dependents before edits, making structural changes in small increments, and validating imports, exports, and tests after each change.

Upgrade dependencies in Codex with version-jump-aware rigor: audit usage, read changelogs, apply minimal bumps, and verify behavior through targeted and full tests.

Write high-value tests in Codex by matching repository test conventions, prioritizing public behavior, and validating coverage gains without overfitting implementation details.