Agent Claude Code
Detects inconsistencies between backend API definitions and frontend API consumption. Flags endpoint mismatches, type drift between Pydantic models and TypeScript interfaces, request/response shape divergence, auth contract gaps, and error-handling format mismatches. Use after API or web client changes.
Agent Claude Code
Reviews async Python code for concurrency bugs, race conditions, resource leaks, deadlocks, blocking calls in async context, cancellation safety, and TaskGroup misuse. Use for changes involving asyncio, concurrency primitives, or long-running async workflows.
Agent Claude Code
Reviews code for FUNCTIONAL CORRECTNESS bugs (logic errors, null/None handling, control-flow, edge cases). The general logic-bug lens in a multi-agent roster; defers conventions/security/logging/async/persistence to the specialist reviewers. By default reviews unstaged git diff. Reports only issues with confidence >=…
Agent Claude Code
Refines recently modified code for clarity, consistency, and maintainability while preserving exact functionality. Prefers explicit/readable over compact; never changes behaviour. Applies CLAUDE.md project standards scoped per language (Python core + React dashboard). Operates on recently touched code unless told…
Agent Claude Code
Reviews code comments for accuracy, completeness, and long-term maintainability. Verifies factual claims against actual code, flags misleading examples / outdated TODOs, suggests removals for comments that restate obvious code. Output: Critical Issues (factually wrong) / Improvement Opportunities / Recommended…
Agent Claude Code
Hunts forensic narrative in code, comments, docstrings, log strings, and identifiers: reviewer citations, in-code issue/PR back-references, audit-run callouts, taxonomy shorthand without rationale, and migration framing. Runs on every PR alongside docs-consistency.
Agent Claude Code
Enforces SynthOrg-specific Python conventions beyond standard style: immutability patterns, vendor-name policy, Python 3.14 / PEP 758, Pydantic configs, code structure limits, observability-logger imports, and error-handling discipline. Use for changes under src/synthorg/ and tests/.
Agent Claude Code
Checks that changed code conforms to its governing docs/design/ page, treating the spec as authoritative and the code as the thing to fix. Discovers the relevant page from the diff rather than working a fixed list. Complements docs-consistency, which runs the opposite direction (doc-describes-code). Use on any PR…
Agent Claude Code
Audits web dashboard files for design token violations in animation (Motion transitions) and density/spacing (card padding, section gaps, grid gaps, banner padding).
Agent Claude Code
Validates Mermaid and D2 diagram syntax in documentation files, checking for syntax errors, consistent styling, and correct fence types.
Agent Claude Code
Checks documentation accurately reflects current codebase. Reads CLAUDE.md, README.md, and docs/design/ pages; compares against the diff and actual current state. Flags drift in code conventions, design-spec pages, logging rules, package structure, and getting-started instructions. Runs on every PR.
Agent Claude Code
Reviews the SynthOrg React 19 web dashboard for code quality, accessibility, and framework best practices. Covers React 19 patterns, component design, Zustand state management, TypeScript safety, accessibility, performance, and shadcn/ui usage. Use for changes under web/.
Agent Claude Code
Enforces SynthOrg-specific Go conventions for the CLI binary in cli/. Covers error wrapping, code structure, Cobra CLI patterns, Docker operation safety, table-driven tests, naming, and module hygiene. Use for changes under cli/.
Agent Claude Code
Expert Go code reviewer for the SynthOrg CLI binary. Specializes in idiomatic Go, concurrency patterns, error handling, and Docker-orchestrator scope. Use for all Go code changes under cli/. MUST BE USED for cli/ changes. Output findings only; do not edit files.
Agent Claude Code
Reviews Go code in cli/ for security vulnerabilities specific to Go and Docker CLI operations: command injection, path traversal, secrets in logs, TLS/network safety, container hardening, crypto usage, and input validation. Use for changes under cli/.
Agent Claude Code
Reviews infrastructure files for security, correctness, and best practices: Dockerfiles, Docker Compose, GitHub Actions workflows, pre-commit config, .dockerignore, Trivy/Grype scan configs. Use for changes under .github/, Dockerfile, docker-compose.yml, .pre-commit-config.yaml.
Agent Claude Code
Verifies a PR fully resolves the acceptance criteria of its linked GitHub issue(s). Fetches issues via gh CLI, extracts criteria, checks each against the diff. NOTRESOLVED items always surface as CRITICAL regardless of confidence. Use during PR review.
Agent Claude Code
Audits logging practices against SynthOrg logging conventions: logger setup, event constants, structured kwargs, log levels, secret redaction, and logging-coverage suggestions for error paths and state transitions. Use for changes in src/synthorg/.
Agent Claude Code
SynthOrg persistence-layer specialist for SQLite + Postgres parity, query optimization, schema design, security, and yoyo migrations. Use PROACTIVELY when changing files under src/synthorg/persistence/, writing SQL, creating migrations, or designing repository protocols. Output findings only; do not edit files.
Agent Claude Code
Reviews PR test coverage for behavioural completeness, not line coverage. Identifies critical gaps (untested error paths, missing edge cases, absent negative tests, missing async coverage), evaluates test resilience to refactoring. Rates each suggestion 1-10 by criticality (10 = data loss / security; 7-8 = user-facing…
Agent Claude Code
Audits untrusted-content fencing and governance at LLM and tool boundaries for semantic correctness, not just call presence. Covers SEC-1 wrapuntrusted tagging, chat-inbound fencing, credentialed-MCP governance, gateway binding, agent-MCP visibility scoping, and forge repo-scoping. Use on changes touching prompt…
Agent Claude Code
Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance for the SynthOrg codebase. Use for all Python code changes. MUST BE USED for Python changes in src/synthorg/ and tests/.
Agent Claude Code
Audits resilience patterns: retry/backoff in correct layer (BaseCompletionProvider only), rate-limit handling, error hierarchy correctness, circuit breaking, timeout propagation. Flags manual retry loops anywhere in code. Use for changes touching provider/, retry handling, or external service integration.
Agent Claude Code
Security vulnerability detection specialist for the SynthOrg codebase. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, LLM prompts, secret backends, or persistence-layer changes. Flags secrets, SSRF, injection, unsafe crypto, prompt-injection sinks, and OWASP Top 10…