opencode-onboardv1.6.0

Agents and skills

The line between how to work (agents) and what to know (skills).

opencode-onboard draws a hard line between two concepts.

Agents: universal behaviors

Agents define how to work. They are universal personas, with the same behavior across projects and stacks.

lead                   lead/orchestrator, planning, pull request lifecycle
fullstack-engineer     primary planning agent, accumulates all skills (user-facing, not spawned)
*-engineer             user-created specialists, spawned by the lead for parallel implementation

fullstack-engineer is mode: primary. It is the user's planning session agent, not a spawned worker. Project-specific specialization comes from user-created custom engineers via /make-engineer. During /plan-apply the lead inspects the engineers that actually exist in .opencode/agents/ and spawns matching specialists. fullstack-engineer is never assigned to tasks; if no specialist matches, create one.

Skills: platform knowledge

Skills define what to know. They provide project rules, platform behavior and task-specific execution guidance. Agents auto-detect and load relevant skills: you do not manually choose skills per prompt.

  • ob-guardrails-generic is the mandatory baseline for every agent (git, secrets, quality rules, plus the engineer workflow)
  • Baseline context rules and token-optimization guidance live in AGENTS.md (always in context), not in a skill

Default fullstack-engineer abilities:

## Abilities
- Guardrails: @ob-guardrails-generic, @ob-guardrails-project

Users are expected to create additional skills and map them into abilities over time. Skills live in .agents/skills/, and any SKILL.md file in a subdirectory is automatically discoverable.

Built-in skills

SkillPurpose
ob-guardrails-genericFoundation for user guardrails skills
ob-guardrails-projectProject-specific guardrails, populated by /make-guardrails
ob-userstory-ghParse a GitHub Issue URL into a structured work item
ob-userstory-azParse an Azure DevOps work item URL
ob-userstory-jiraParse a Jira issue URL via the acli CLI
ob-userstory-browserParse a work item from any URL via browser automation
browser-automationBrowser control via @different-ai/opencode-browser
ob-plan-exploreRead-only exploration procedure behind /plan-explore
ob-plan-proposeProposal and task-enrichment procedure behind /plan-propose
ob-plan-applyWave-implementation procedure behind /plan-apply
ob-plan-archiveArchive procedure behind /plan-archive
ob-plan-goalAutonomous full-lifecycle pipeline behind /plan-goal
ob-plan-quickQuick task checklist behind /plan-quick
ob-ops-shipPR-creation procedure behind /ops-ship
ob-ops-evidenceEvidence of a change, plus an idempotent verified issue/PR comment
ob-make-architectureARCHITECTURE.md generation behind /make-architecture
ob-make-designDESIGN.md generation behind /make-design
ob-make-guardrailsGuardrails generation behind /make-guardrails
ob-make-engineerCustom engineer creation behind /make-engineer
ob-make-evidence-scaffoldVisual-evidence harness scaffold behind /make-evidence-scaffold
ob-make-user-modelTier model configuration behind /make-user-model
ob-repo-auditRead-only health audit across configured source roots
ob-repo-verifyCurrent-branch verification and repair gate
ob-repo-initializeProject initialization behind /repo-initialize
ob-repo-onboardGuided project tour behind /repo-onboard
ob-repo-helpThe command reference displayed by /repo-help

Platform operations are injected during onboarding: pull request creation into ob-ops-ship, the archive PR flow into ob-plan-archive, issue and work-item evidence comments into ob-ops-evidence, and pull request review plus issue creation directly into the /ops-review and /ops-backlog command files.

Platform skills ship as suffixed variants (ob-userstory-gh, ob-userstory-az, ob-userstory-jira, ob-userstory-browser) and the installer copies only the matching one, renamed to its generic name.