Claude Code: AI Agent Workflow Collection

Analyze code to identify explicit contracts, implicit usage patterns, and realistic boundary conditions. Contains concrete formulas for calculating input realism limits. Use before generating adversarial tests.

Library of realistic adversarial attack vectors and anti-patterns to avoid. Contains examples of valid attacks and subtle gaming patterns to reject.

For cross-cutting concerns: add behavior without modifying functions, caching, timing, logging, validation wrappers.

For performance work: measure before changing, profile to find bottlenecks, compare before and after.

For symbolic computation: ASTs, mathematical expressions, code that manipulates code structure, expression transformations.

For ordered processing: A search, Dijkstra, event simulation, task scheduling. Efficient min/max extraction with heap-based queue.

For dynamic programming: overlapping subproblems, recursive solutions with repeated computations, memoization to avoid redundant work.

For persistent state: closures capture outer variables, alternative to classes for simple state, factory functions that remember context.

For flexible parsing: try multiple type conversions in order, graceful fallback from specific to general types.

For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.

For hot loop optimization: repeated formula evaluation, regex patterns, expression compilation. Transform string to callable once, call many times.

For complex behavior: build from tiny functions, chain transformations, make code read like a pipeline of operations.

For probability and counting: permutations, combinations, sample spaces, Monte Carlo simulation, brute-force enumeration, card/dice problems.

For new modules: define type aliases as vocabulary, make code self-documenting, create domain-specific language feel.

For heterogeneous data: pattern matching on type/structure, interpreter eval loops, handling different expression types.

For 2D debugging: visualize grid/board state, show puzzle progress, make algorithm behavior visible.

Provides heuristics for identifying incomplete or broken documentation. Use when validating README setup instructions, testing onboarding flows, or auditing documentation quality. Triggers: docs, readme, onboarding, setup validation, documentation audit.

Principles and patterns for writing error messages that help users recover. Use when auditing, writing, or improving error messages in code. Triggers: error messages, user experience, error handling, exception messages, validation errors.

For cross-version support: try/except imports, optional dependencies, graceful degradation across Python versions.

For computational geometry: convex hull, point enclosure, polygon operations. Uses monotone chain algorithm with stack-based turn detection.

For pathfinding and search: shortest path, maze solving, game AI, route planning, graph traversal, BFS/DFS, Dijkstra, A problems.

For result reporting: tabular output, aligned columns, statistics summaries, human-readable reports.

For graph exploration: frontier collection with configurable pop order, BFS/DFS/random via strategy change.

For tree/maze generation: spanning trees, random mazes, graph coverage. Uses frontier-based exploration with configurable traversal order.