Agent
Investigator role — diagnoses a failing CI run end-to-end and returns a classified failure report with a concrete fix list; never edits code, never re-runs workflows. Fetches run/job logs via gh CLI, classifies each failure as test / lint / build / flake / infra / environment-drift, and emits fix items orc-code-fixer…
Agent
Executor role — applies a defined list of code changes, runs the project's test suite, and reports a diff. Used by /orc:address to execute reviewer-requested fixes, or any context where a list of changes is already decided and just needs to be made cleanly.
Agent
Investigator role — long-running root-cause investigation for hard bugs and unexpected behavior. Use when a bug needs disciplined isolation — reproduction, hypothesis, instrumentation, regression-testing — before any fix is attempted. Maintains an isolated context and returns a written diagnosis the implementing…
Agent
Executor role — provisions a fast, reproducible dev environment for QA or standalone use — detects existing Docker setup (compose > devcontainer > Dockerfile), generates a minimal compose when none exists (hybrid by default: services in containers, app on host), boots with healthcheck-gated readiness, and writes…
Agent
Executor role — senior-developer agent that implements a defined slice list from a plan + failing test(s). Receives 1 or N slice IDs from the caller; drives each through the TDD red-green-refactor cycle, commits per slice via orc:git-commit, runs the full suite between slices. Default executor in /orc:flow Phase 5…
Agent
Investigator role — drafts a complete Jira backlog hierarchy (Epic micro-PRD, Stories, concurrency-sliced Tasks/Sub-tasks/Bugs) per the orc:jira-hierarchy contract and returns it as structured JSON; never creates tickets, never mutates Jira. Dispatched by /orc:jira-breakdown, and by /orc:flow or /orc:plan when a plan…
Agent
Investigator role — reviews someone else's open GitHub PR end-to-end and returns structured findings per the orc:review-contract schema; never posts, never edits. Fetches diff via gh CLI, walks every changed file. Dispatched by /orc:code-review (the posting layer converts findings into inline GitHub PR comments) and…
Agent
Investigator role — analyzes incoming PRDs / specs / feature briefs — extracts structured requirements, identifies ambiguities, surfaces missing edge cases, and generates clarifying questions for the PM or stakeholder. Produces a structured analysis report; the engineer decides how to act on the gaps. Dispatched by…
Agent
Executor role — drives a real browser via the agent-browser CLI (vercel-labs/agent-browser) to QA a running web application — golden path + edge cases — and writes an evidence packet (criterion-anchored annotated screenshots, a WebM recording, accessibility snapshots, browser console, network HAR, narrated steps…
Agent
Investigator role — deep codebase scan to surface refactor opportunities — coupling that hurts testability, duplicated decisions, leaky abstractions, drift from documented architecture (ADRs, CONTEXT.md). Dispatched by /orc:plan when the input is refactor-shaped (mentions refactor, architecture, tech debt, cleanup)…
Agent
Investigator role — drafts replies to PR review comments given the comment text, the relevant code, and what was (or wasn't) changed in response; drafts text only, never edits files. Used by /orc:address. Returns one short reply per comment, ready to post via gh CLI.
Agent
Investigator role — reviews PR diffs (or any code change) for security vulnerabilities and threat-modeling gaps, returning structured findings per the orc:review-contract schema with a concrete exploit scenario per finding; never edits code. Focuses on injection (SQL/command/template), auth/authz bypass, secret…
Agent
Investigator role — analyzes a too-big branch's diff and proposes how to split it into a stack of smaller, logically-coherent PRs, emitting a JSON plan (slices + non-interactive rebase plan) for the orchestrator to execute. Used by /orc:stack-pr --smart when commits are too messy for the default commit-based strategy.…
Agent
Executor role — authors comprehensive test suites for new or changed behavior — picks edge cases, error paths, and fixture design — given a function signature, behavior description, or failing requirement. Different from orc-code-fixer (which APPLIES pre-decided changes); this agent DESIGNS the tests. Used by…