Help us improve
Share bugs, ideas, or general feedback.
From arn-code
Executes full structured project plans by dispatching parallel executor-reviewer agent cycles on all tasks, handling dependencies and review gates.
npx claudepluginhub appsvortex/arness --plugin arn-codeHow this skill is triggered — by the user, by Claude, or both
Slash command
/arn-code:arn-code-execute-planThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Execute a structured project plan by dispatching parallel batches of `arn-code-task-executor` agents and validating each completed task through a `arn-code-task-reviewer` agent before marking it done. Independent tasks run concurrently; dependent tasks wait for their blockers to clear. Each task goes through an execute-review-gate cycle: the executor implements and tests, the reviewer validates...
Executes multi-phase implementation plans by dispatching tasks to sub-agents, tracking progress per-task in plan.json, and coordinating sequential phases.
Executes a single task from the Arness task list by spawning a task executor agent, with optional reviewer for validation. For re-running failed tasks, isolated testing, or independent implementation.
Executes implementation plans from plan.md files via Superpower Loop phases: task creation, batch execution with verification, git commits. Use after plan ready or on 'execute the plan'.
Share bugs, ideas, or general feedback.
Execute a structured project plan by dispatching parallel batches of arn-code-task-executor agents and validating each completed task through a arn-code-task-reviewer agent before marking it done. Independent tasks run concurrently; dependent tasks wait for their blockers to clear. Each task goes through an execute-review-gate cycle: the executor implements and tests, the reviewer validates against patterns and acceptance criteria, and the orchestrator (this skill) decides whether to pass, retry, or escalate.
Key architectural constraint: Subagents cannot spawn other subagents. The dispatch loop MUST stay in the main session (this skill).
Pipeline position:
arn-code-init -> arn-code-feature-spec / arn-code-bug-spec -> arn-code-plan -> arn-code-save-plan -> arn-code-review-plan -> arn-code-taskify -> **arn-code-execute-plan** (dispatch -> execute -> review -> gate) -> arn-code-review-implementation -> arn-code-document-project -> arn-code-ship
If no ## Arness section exists in the project's CLAUDE.md, inform the user: "Arness is not configured for this project yet. Run /arn-implementing to get started — it will set everything up automatically." Do not proceed without it.
Read the project's CLAUDE.md and extract the ## Arness section to find:
ask, auto, or manual (if present)Template version check: If Template version and Template updates fields are present, run the template version check procedure documented in arn-code-save-plan Step 1 (Template Version Check) before proceeding. If ## Arness does not contain these fields, treat as legacy and skip.
Ask the user for PROJECT_NAME if not provided in the trigger message
Verify the project directory exists and contains the required structure:
<plans-dir>/<PROJECT_NAME>/
├── INTRODUCTION.md
├── TASKS.md
├── PROGRESS_TRACKER.json
├── plans/PHASE_*.md
└── reports/
If the project directory is missing, suggest running /arn-code-save-plan first
If INTRODUCTION.md or phase plans are missing, suggest running /arn-code-save-plan first
If PROGRESS_TRACKER.json is missing, warn that progress tracking will not be available. Execution can still proceed.
If ### Visual Testing is configured in CLAUDE.md, note the presence of visual testing. Per-task execution uses Layer 1 config only (top-level fields). Multi-layer visual validation is handled by /arn-code-review-implementation after plan execution completes.
Detect sketch artifacts -- Read <project-folder>/INTRODUCTION.md and check for a ### Sketch Artifacts section. If found, extract the sketch manifest path listed there (typically a relative path to sketch-manifest.json). Resolve it to an absolute path relative to the project directory. Also resolve the sketch directory path (the parent directory of the manifest). If no Sketch Artifacts section is found, check for manifests by scanning arness-sketches/ in the project's source directory for any sketch-manifest.json matching PROJECT_NAME. Store the resolved manifest path and sketch directory path for use in the dispatch loop (Step 4). If no manifest is found from either source, proceed normally -- the dispatch loop will not pass sketch context to executors.
Deferred Task List Setup:
Check for Task list ID in ## Arness config. If absent:
Ask (using AskUserQuestion):
"Persistent task lists are not configured. Would you like to enable them? (Recommended — tasks survive across sessions)"
If Yes: derive ID (slugify project directory name or use custom ID), write to .claude/settings.json (create if needed, preserve existing env vars), add Task list ID to ## Arness config. Inform: "Persistent task list configured."
If No: proceed without persistence. Inform (once): "Tasks will be session-scoped. Enable persistence anytime with /arn-code-taskify."
TaskList to check for existing tasksTask list ID is configured in ## Arness: tasks should have persisted — suggest: "No tasks found despite persistent task lists being configured. The task list may have been cleared. Run /arn-code-taskify to recreate tasks."Task list ID is NOT configured: "No tasks found. Tasks may have been lost when the previous session ended (session-scoped storage). Run /arn-code-taskify to recreate them. To enable persistent task lists for future sessions, run /arn-code-taskify which will offer to configure persistence."Show the current state (how many pending, in_progress, completed)
Ask (using AskUserQuestion):
"Tasks already exist with progress. How would you like to proceed?"
Options:
Ask (using AskUserQuestion):
"How should Arness handle critical review findings?"
Options:
Store the chosen mode for the duration of this execution session. This choice applies to all tasks; the user is not asked again unless execution is restarted.
The dispatch loop identifies batches of unblocked pending tasks, spawns parallel executor agents, then spawns parallel reviewer agents for each completed executor. Review verdicts determine whether a task is marked complete, retried with feedback, or escalated to the user. The loop repeats until all tasks are completed or blocked.
Read
${CLAUDE_PLUGIN_ROOT}/skills/arn-code-execute-plan/references/dispatch-loop.mdfor the full dispatch algorithm.
When all tasks are completed (or skipped/aborted by user), present a summary:
<plans-dir>/<PROJECT_NAME>/PROGRESS_TRACKER.jsonIf visual testing is configured, include in the completion summary:
/arn-spark-visual-readiness to check activation status, then /arn-code-review-implementation for full multi-layer review.Offer next steps:
/arn-code-simplify to review the implementation for reuse opportunities, quality issues, and efficiency improvements."/arn-code-review-implementation to validate the full implementation against the plan and stored patterns."/arn-code-document-project to generate developer documentation."/arn-code-ship to commit and create a pull request."After reporting completion, refresh stored pattern documentation to capture any new patterns introduced during implementation.
Read
${CLAUDE_PLUGIN_ROOT}/skills/arn-code-execute-plan/references/pattern-refresh.mdand follow the pattern refresh procedure.
This step is automatic and non-blocking. If the refresh fails, execution is still considered successful.
## Arness config missing in CLAUDE.md -- suggest running /arn-implementing to get started/arn-code-save-plan to create the project structure/arn-code-taskify to convert TASKS.md into tasksarn-code-review-plan; show the dependency graph (task IDs, names, and what each is blocked by) and ask the user to manually resolve by removing or reordering dependencies