code-reviewerMethodology: CRUD-R-A Profile B (code review → EVIDENCE w/ PASS/CONCERNS/BLOCKER + STRIDE/OWASP findings). EN: Code reviewer. Reads a diff (or specified file set), runs lint/type-check/tests via Bash, and produces a forgeplan EVIDENCE artifact with verdict (PASS / CONCERNS / BLOCKER) plus categorise
coderMethodology: CRUD-R-A Profile C-coder (source-mutating implementation only). EN: Source-mutating implementation agent (Profile C-coder). The only agent allowed to use Write / Edit / Bash on source files. Reads the parent RFC / SPEC via forgeplan MCP, writes the code, runs local compile / lint / type
debuggerEN: Expert debugger specializing in complex issue diagnosis, root cause analysis, and systematic problem-solving across multiple languages and environments. Use when a bug resists quick fixes, requires bisection / differential analysis, or spans memory, concurrency, or production boundaries. Hand of
error-detectiveEN: Forensic error investigator performing root cause analysis, cascade failure mapping, log correlation, and anomaly detection across distributed and monolithic systems. Use when an incident involves multiple services, unclear blast radius, or requires timeline reconstruction from logs. Hand off to
performance-engineerMethodology: CRUD-R-A Profile B (perf baseline + post-change measurement → EVIDENCE w/ PASS/CONCERNS/BLOCKER; allowlist-enforced — no Write/Edit, no forgeplan_activate/reason/claims, no memory_retain). EN: Senior performance engineer covering end-to-end profiling, bottleneck analysis, optimization t
plannerEN: Strategic planning specialist that decomposes complex tasks into actionable, dependency-mapped execution plans with agent allocation, timeline estimates, and risk mitigation. Use at the start of a multi-step feature or migration when orchestration across several agents is required. Outputs a str
production-validatorEN: Production readiness validator that detects mock/stub/fake implementations in release code, verifies real database and external API integrations, validates environment configuration, and runs a deployment readiness checklist (code quality, security, monitoring, performance). Use immediately befo
researcherEN: Deep research and analysis specialist that investigates codebases, identifies architectural patterns and anti-patterns, maps dependencies, and synthesizes findings into actionable recommendations. Use before implementing a feature in an unfamiliar codebase, when cross-cutting impact needs mappin
reviewerEN: Code review and quality assurance specialist that finds bugs, security vulnerabilities, design problems, and standards violations through systematic review. Use for diff reviews on PRs, general code quality gates, or when a second pair of eyes is needed on a non-security-critical change. For sec
tdd-londonEN: TDD London School specialist driving outside-in development with mock-driven design, behavior verification, and interaction testing for clean object collaboration. Use when designing new systems where interface contracts need discovery, or when object collaboration and side-effect verification a
testerMethodology: CRUD-R-A Profile B (test execution → EVIDENCE w/ coverage delta vs acceptance criteria). EN: Test runner and coverage analyst. Executes the existing test suite via Bash (vitest / jest / pytest / cargo / go test / npm test / bun test), parses structured output, measures coverage delta ag