20 tagged actual budget, measured the same way as everything else here.
Browse within: ai-assistant 18api-server 18budget-management 18budget-tracking 18conversation-ai 18
Agent Claude Code
Generates and runs comprehensive, non-destructive security tests for the actual-mcp-server MCP transport covering OWASP API Top 10, JSON-RPC injection, auth bypass (OIDC + static bearer), per-user budget ACL (IDOR), ActualQL/SQL injection, malformed input, and error-leakage. Use when writing security tests, expanding…
Agent Claude Code
Elite code review expert for security vulnerabilities, correctness bugs, performance, and maintainability. Runs the project's static analysis, security scanning, and tests as part of the review. Use PROACTIVELY for code quality assurance.
Agent Claude Code
Ticket readiness gate for actual-mcp-server (forge-kit ticket-gate v6). Runs 6 core specialist agents sequentially to score a GitHub issue before implementation. Each agent scores 1-10; ALL must score 10 to pass. An agent whose domain the ticket does not touch auto-scores 10 (N/A). Extra specialists are added by…
Agent Claude Code
Extracts a Maven dependency's JAR (or sources JAR) into the project build dir so you can browse its classes and source. Use when you need to explore the API or internals of a library. Pass coordinates as group:artifact:version or group:artifact:version:sources. Omit version to have it looked up from…
Agent Claude Code
Runs Gradle commands with filtered output to keep the parent context window clean. Use for any ./gradlew or gradle invocation — compilation, tests, formatting checks.