Agent Claude Code
Use this agent to guarantee code meets strict quality, security, testing, and maintainability standards. It enforces linting (ruff), types (pyright), security (bandit), tests (pytest/coverage), dead-code removal (vulture), duplication/centralization (jscpd + radon + import-graph checks), and test-name⇄target mapping.
Agent Claude Code
Audits test code for quality, structure, and patterns. Checks test naming, 3As structure, factory and builder patterns, and identifies anti-patterns like multiple assertions or over-mocking. Based on real codebase with 63 factories and 12 builders.
Agent Claude Code
Advisor role in HydraFlow's self-repairing review pipeline. Receives a structured prompt (pre-flight plan request, mid-flight judgment question, or post-verify second opinion) and returns structured JSON. Routes to Opus by default per the advisor pattern. Read-only by intent: the executor handles writes.
Command Claude Code
Capture an architectural decision as a draft ADR issue routed into HydraFlow.
Command Claude Code
Run a comprehensive code quality audit across the entire repo. Dynamically analyzes source code for dead code, complexity, duplication, error handling gaps, type safety issues, class cohesion, and method size. Creates GitHub issues for findings so HydraFlow can process them.
Command Claude Code
Audit all Claude Code hooks (.claude/settings.json and .claude/hooks/.sh) for correctness, efficiency, and gating opportunities. Launch a single agent that reads everything and reports findings.
Command Claude Code
Run a comprehensive integration test audit across the entire repo. Dynamically discovers external dependencies in source code, inventories existing integration tests, identifies coverage gaps, flags ugly/outdated tests, and creates GitHub issues for findings.
Command Claude Code
Run a comprehensive test quality audit across the entire repo. Analyzes test naming, structure, hygiene, factory usage, fluent builder patterns, anti-patterns, coverage gaps, and flaky patterns. Creates GitHub issues for findings so HydraFlow can process them.
Command Claude Code
Review the current branch diff for common implementation mistakes before committing. This is a read-only check — it does not modify files.
Command Claude Code
Take a rough description from the user, research the relevant codebase, and create a well-structured GitHub issue with full context, file references, and acceptance criteria.
Command Claude Code
Scan the current conversation for architectural decisions, bug root causes, configuration choices, codebase patterns, and workflow preferences. Write each as a memory item to the local JSONL store for ingestion by the memory sync worker.
Command Claude Code
Run a comprehensive quality check before declaring work complete or committing. This catches lint errors, type issues, and test failures BEFORE they accumulate.
Command Claude Code
Assess whether changed production code has adequate test coverage. This is a read-only assessment — it does not modify files.
Hook Claude Code
Runs before the agent uses a tool for Bash, Write and Edit tool calls, executing hf.block-destructive-git.sh, hf.scan-secrets-before-commit.sh, hf.validate-tests-before-commit.sh, hf.validate-functional-areas.sh, hf.enforce-plan-and-explore.sh, hf.check-test-counterpart.sh, hf.enforce-migrations.sh and…
Hook Claude Code
Runs after a tool call finishes for Read, Grep, Glob, cclsp, TaskCreate, Write and Edit tool calls, executing hf.track-exploration.sh, hf.track-planning.sh, hf.warn-new-file-creation.sh, hf.track-code-changes.sh, hf.auto-lint-after-edit.sh and hf.mirror-feedback-memory.sh (11 commands). From T-rav/hydraflow.
Hook Claude Code
Runs when the agent finishes a response, executing hf.cleanup-code-change-marker.sh. From T-rav/hydraflow.
Settings file Claude Code
Agent settings declaring 3 hook events (PreToolUse, PostToolUse, Stop).
Skill Claude CodeCodex
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Agent Codex
Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency.
Skill Claude CodeCodex
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.
Skill Claude CodeCodex
Create a draft ADR issue for HydraFlow processing.
Skill Claude CodeCodex
Run a comprehensive code quality audit across the entire repo. Dynamically analyzes source code for dead code, complexity, duplication, error handling gaps, type safety issues, and architectural problems. Creates GitHub issues for findings so HydraFlow can process them.
Skill Claude CodeCodex
Audit all Claude Code hooks (.claude/settings.json and .claude/hooks/.sh) for correctness, efficiency, and gating opportunities. Launch a single agent that reads everything and reports findings.
Skill Claude CodeCodex
Run a comprehensive integration test audit across the entire repo. Dynamically discovers external dependencies in source code, inventories existing integration tests, identifies coverage gaps, flags ugly/outdated tests, and creates GitHub issues for findings.