using-rn-dev-agent

Using rn-dev-agent

The Codex rn-dev-agent surface provides an MCP tool suite, 17 explicit workflow skills, and 11 implicit domain skills—exactly 28 native Codex skills. The six packaged agent files are inline playbooks, not a native Codex subagent contract.

This skill is your front door. Before starting any RN work, use the decision tree below to route the user's intent to the right tool.

Codex surface map

Codex loads .codex-plugin/plugin.json, package-local codex-skills/, and stable MCP server key cdp from codex.mcp.json. No plugin hooks is expected. Packaged codex-commands/*.md are complete workflow playbooks reached through the seventeen native $rn-dev-agent:<workflow> skills; best-effort command migration is explicitly disabled, so source-command-* is not a supported vocabulary.

Workflow adapters are explicit-only. Domain skills remain implicit knowledge owners. Resolve every playbook/helper relative to the exact selected SKILL.md; never scan caches or use a launcher-only package-root variable. For action replay, prefer structured cdp_run_action after the preflights in the package-local run-action workflow.

Decision Tree

What is the user asking for?
│
├── INVENTORY of reusable actions ("what's already automated for this?")
│   └─► $rn-dev-agent:list-learned-actions [keyword]
│       (Scans feedback memories + .rn-agent/actions/ + .rn-agent/skeleton.yaml.
│        ALWAYS run this BEFORE any device_* sequence — replay an
│        existing flow instead of recomposing primitives manually.
│        See feedback_execute_artifacts_before_manual.md.)
│
├── REPLAY a learned action (Maestro flow)
│   └─► $rn-dev-agent:run-action <name> [-e KEY=VALUE …] [--platform ios|android]
│       (Counterpart to list-learned-actions: list discovers, run executes.
│        Pre-flights mutates flag, appId match, parameter coverage. Use to
│        skip a 7-min manual walk when a 23-sec flow already exists.)
│
├── CREATE a new reusable action ("save this flow", "make this replayable")
│   └─► Load the creating-actions skill
│       (Inventory-dedup first, ground selectors in evidence, ASCII flow
│        diagram, M7 header, validate, then replay to promote. Covers both
│        the recorder path and direct YAML authoring.)
│
├── BUILD a new feature / "add X to the app"
│   └─► $rn-dev-agent:rn-feature-dev <description>
│       (8-phase pipeline — see rn-feature-development skill)
│
├── TEST an existing feature
│   └─► $rn-dev-agent:test-feature <description>
│       (Runs rn-tester protocol INLINE in parent session — MCP tools required.
│        Step 0 is automatic artifact-first scan via list-learned-actions.)
│
├── QA a GitHub pull request on device
│   └─► $rn-dev-agent:qa-pr <PR URL or number> [ios|android|device|all]
│       (Runs rn-pr-qa protocol INLINE — pins the PR head, installs via
│        rn-dev-agent, exercises the change on simulator/emulator/device.)
│
├── BUILD + TEST (app not yet installed)
│   └─► $rn-dev-agent:build-and-test <description>
│       (Builds app via Expo/EAS, installs, starts Metro, then runs tester protocol inline)
│
├── Something is BROKEN on the current screen
│   └─► $rn-dev-agent:debug-screen
│       (Runs rn-debugger protocol INLINE in parent session — MCP tools required)
│
├── Plugin tools not working / environment broken
│   └─► $rn-dev-agent:setup
│       (passive package health first, then consented AGENTS.md/nav/store/scaffold setup)
│
├── DIAGNOSE the environment (read-only, no changes)
│   └─► $rn-dev-agent:doctor
│       (Passive checklist from rn-setup — reports, never modifies)
│
├── Need PROOF for a PR ("record a demo", "capture proof", "PR video")
│   └─► Load the capturing-proof skill (or run $rn-dev-agent:proof-capture <feature-slug>)
│       (Rehearsal-gated video + screenshots + generated PR body)
│
├── FREEZE a verified action into a locked regression test
│   └─► $rn-dev-agent:lock-e2e <action-name>
│       (Strict no-repair run via cdp_lock_e2e_test, freezes to .rn-agent/e2e/;
│        the frozen suite runs via cdp_run_e2e_suite. For login, this is the
│        formal PR proof on the exact candidate; cdp_login_prologue is not.)
│
├── Watch tool activity live in a browser ("observability UI")
│   └─► $rn-dev-agent:observe
│       (Shows the observe web UI URL; stop/restart the server)
│
├── Audit project rules sync (Vercel rules)
│   └─► $rn-dev-agent:check-vercel-rules
│
├── REPORT a plugin bug / send feedback
│   └─► $rn-dev-agent:send-feedback (routes to `sending-feedback`)
│       (Sanitized environment context → GitHub issue, user-confirmed)
│
├── Understand an existing feature (read, don't write)
│   └─► Spawn rn-code-explorer via Task tool (read-only, safe to spawn)
│       (Maps screens, state, navigation, testIDs, patterns)
│
├── Design architecture before implementing
│   └─► Spawn rn-code-architect via Task tool (read-only, safe to spawn)
│       (Fable-powered blueprint with testID placement + proof flow)
│
├── Review code before merging
│   └─► Spawn rn-code-reviewer via Task tool (read-only, safe to spawn)
│       (Confidence-filtered review, RN conventions + best practices)
│
├── About to start a real device journey (build / test / proof, end to end)
│   └─► $rn-dev-agent:run-workflow [journey-description]
│       (Loads the rn-workflow domain skill: declared package manager + deps,
│        read-only inventory, typed session recovery, one exclusive device,
│        managed integration/Metro, only the requested proof, reverse cleanup)
│
├── Just check if environment is ready
│   └─► $rn-dev-agent:check-env
│       (Quick cdp_status check, no setup attempt)
│
└── Extract the navigation graph
    └─► $rn-dev-agent:nav-graph
        (Maps all screens and navigators)