Skip to content

Bundled Roles Reference

58 roles ship with agents-fleet. A role is an agent persona — it defines the system prompt, agent type, and permissions for a spawned worker. Roles live in src/skills/bundled/roles/ and are always loaded (bundled tier); override any role with a same-named .role.md in .fleet/roles/ (project) or ~/.fleet/roles/ (user). List them at runtime with /skills or list_features --kind role.

See also: Bundled Skills, Crews, Security Autopilots.

Generated for agents-fleet v0.52.0 · 58 bundled roles.


Default Agent Roles

RoleAgent TypeDescription
default-codercoderDefault system prompt for coder worker agents
default-coordinatorcoordinatorDefault coordinator system prompt for fleet orchestration
default-explorerexplorerDefault system prompt for explorer worker agents
default-general-purposegeneral-purposeDefault system prompt for general-purpose worker agents
default-researcherresearcherDefault system prompt for researcher worker agents
default-reviewerreviewerDefault system prompt for reviewer worker agents
default-testertesterDefault system prompt for tester worker agents

Fleet-Specialized Roles

RoleAgent TypeDescription
fleet-architectreviewerArchitecture reviewer specialized for agents-fleet coordinator-worker patterns
fleet-ci-engineercoderInfrastructure/CI engineer — builds & maintains CI pipelines (test, coverage, regression, build gates)
fleet-ci-reviewerreviewerCI/build-integrity reviewer — ensures tests, coverage, and green builds are always in place
fleet-codercoderCoder agent specialized for agents-fleet (TypeScript/ESM/Ink/Copilot SDK)
fleet-correctness-reviewerreviewerCorrectness reviewer specialized for agents-fleet type safety and async patterns
fleet-explorerexplorerRead-only explorer specialized for investigating the agents-fleet codebase
fleet-maintainability-reviewerreviewerMaintainability reviewer specialized for agents-fleet code hygiene and conventions
fleet-minimalism-reviewerreviewerMinimalism / over-engineering reviewer — finds what to delete, replace with stdlib/native, or shrink
fleet-performance-reviewerreviewerPerformance reviewer specialized for agents-fleet runtime efficiency and resource usage
fleet-report-writergeneral-purposeReport-writing specialist — produces polished, interactive HTML reports (agents-fleet light brand theme) with SVG/PNG/interactive diagrams and on-demand PDF export
fleet-researcherresearcherResearch and investigation agent with scoped write access for the agents-fleet codebase
fleet-security-reviewerreviewerSecurity reviewer specialized for agents-fleet threat model
fleet-testertesterTester agent specialized for agents-fleet (Vitest/better-sqlite3/real implementations)
fleet-workflow-architectcoderExpert workflow author — composes the workflow-authoring skill, always validates via /wf validate, discovers reusable components

Code Review Roles

RoleAgent TypeDescription
architecture-reviewerreviewerArchitecture and design pattern reviewer
correctness-reviewerreviewerLogic and correctness focused code reviewer
performance-reviewerreviewerPerformance and efficiency focused reviewer
security-reviewerreviewerOWASP-focused security audit reviewer
test-reviewerreviewerTest coverage and quality reviewer for agents-fleet (TypeScript/Vitest)

Investigation Roles (used by /init)

RoleAgent TypeDescription
init-api-explorercoderInvestigates API surface and contracts
init-arch-explorercoderInvestigates architecture and project structure
init-build-explorercoderInvestigates build system, test framework, and dev workflow
init-criticgeneral-purposeAdversarial critic that verifies investigation findings
init-decision-explorercoderInvestigates key design decisions and rationale
init-dep-explorercoderInvestigates dependencies and external services
init-pattern-explorercoderInvestigates coding patterns and conventions
init-security-explorercoderInvestigates security model and authentication
init-synthesizergeneral-purposeSynthesis writer that produces the final /init completion artifacts

Research, Brainstorm & Planning

RoleAgent TypeDescription
context-researcherexplorerContext and dependencies researcher - investigates surrounding context and historical background
counter-researcherexplorerCounter-arguments and alternatives researcher - investigates downsides and alternative approaches
edge-case-researcherexplorerEdge cases and failure modes researcher - investigates what could go wrong
inquisitor-edge-casesexplorerAdversarial edge-cases-angle inquisitor that grills the user with questions about failure modes, security, malformed input, and adversarial scenarios before a feature is built. Spawned by /brainstorm in round 1 alongside inquisitor-ux and inquisitor-technical.
inquisitor-technicalexplorerAdversarial technical/integration-angle inquisitor that grills the user with questions about architecture, integration points, data shapes, and operational concerns before a feature is built. Spawned by /brainstorm in round 1 alongside inquisitor-ux and inquisitor-edge-cases.
inquisitor-uxexplorerAdversarial UX-angle inquisitor that grills the user with questions about intent, workflows, success criteria, and user experience before a feature is built. Spawned by /brainstorm in round 1 alongside inquisitor-technical and inquisitor-edge-cases.
planning-coordinatorcoordinatorCoordinator specialized for planning workflows - brainstorming, requirements, and design
ponytail-codercoderMinimalist coder — a lazy senior developer who writes the least code that works
primary-researcherexplorerPrimary research perspective - direct investigation of facts, code, documentation, examples
research-coordinatorcoordinatorCoordinator specialized for parallel research and investigation workflows
research-criticreviewerAdversarial critic that cross-references and verifies research findings

Security Roles

RoleAgent TypeDescription
sec-binary-analystgeneral-purposeStatic reverse engineer for a target binary — triages the file, maps parsing/decoder attack surface, patch-diffs patched-vs-unpatched builds, and produces an RE findings artifact plus a ranked list of fuzz targets
sec-crash-triage-analystgeneral-purposeTriages fuzzing crashers and assesses realistic exploitability — reproduces, classifies (!exploitable / !analyze / ASan), determines the memory-safety primitive, weighs mitigations, writes the minimal impact-proving PoC (never weaponized), and produces a triage/exploitability artifact
sec-exploit-poc-engineercoderWrites a local, sandboxed failing test that proves a vulnerability in the operator's own code
sec-fixercoderImplements the minimal, correct security fix for a finding while preserving behavior
sec-fuzzing-engineergeneral-purposeBuilds and runs a coverage-guided fuzz harness for ONE target routine inside an isolated, disposable Azure VM — assembles seeds + dictionaries, fuzzes under sanitizers, measures coverage, minimizes crashers, and produces a fuzzing artifact
sec-msrc-reportergeneral-purposeProduces the MSRC coordinated-disclosure report from a validated finding plus isolated-VM evidence, using the sec-msrc-report format; WRITES the report artifact
sec-recon-mappergeneral-purposeMaps a codebase's attack surface and writes a structured recon artifact
sec-reportergeneral-purposeWrites the final security report with per-finding detail and an executive summary
sec-triage-analystgeneral-purposeDedupes and prioritizes hunter findings and writes a triage summary + fix-target list
sec-verifiertesterRe-runs the PoC and relevant suites to confirm a fix resolves the finding with no regressions
sec-vm-validatorgeneral-purposeOwns the Azure isolated-VM lifecycle — provision an isolated disposable VM, detonate the PoC, capture + hash evidence, assert the security impact, and ALWAYS tear down; uses az + powershell under hard isolation guardrails
sec-vuln-hunterreviewerSenior appsec auditor that hunts one vulnerability class and returns evidence-backed findings