/arn-implementing

name: arn-implementing
description: >-
  This skill should be used when the user says "implementing", "arness implementing",
  "start implementing", "execute the plan", "build it", "implement this",
  "run the tasks", "execute", "start building", "implement the feature",
  "implement the fix", "quick change", "swift", "swift mode", "quick implementation",
  "standard", "standard mode", "standard implementation",
  "start execution", "build the feature", "arn-implementing",
  or wants to execute an implementation plan, run a quick implementation,
  a standard-tier implementation, or manage the build-simplify-review cycle.
  Chains to arn-shipping at completion.
version: 1.1.0

Arness Implementing

Execute an implementation plan, run a quick implementation (swift), run a standard-tier implementation, or manage the build-simplify-review cycle. This is a first-citizen entry point that orchestrates `arn-code-execute-plan`, `arn-code-swift`, `arn-code-standard`, `arn-code-simplify`, `arn-code-review-implementation`, and related execution skills. Chains from `arn-planning` and chains to `arn-shipping` or `arn-assessing` at completion.

This skill is a **sequencer and decision-gate handler**. It MUST NOT duplicate sub-skill logic. All implementation work is done by the invoked skills. Arness-implementing handles: input routing, state detection, execution mode selection, the simplify/review cycle, and chaining.

Step 0: Ensure Configuration

Read `${CLAUDE_PLUGIN_ROOT}/skills/arn-code-ensure-config/references/step-0-fast-path.md` and follow its instructions. This guarantees a user profile exists and `## Arness` is configured with Arness Code fields before proceeding.

After Step 0 completes, extract the following from `## Arness`:

• **Plans directory** — for detecting structured plans and project folders
• **Code patterns** — path to stored pattern documentation
• **Template path** — path to report templates

Workflow

Step 0.5: Input Routing

Check the trigger message for swift or standard intent:

• **"swift: [description]"**, **"quick: [description]"**, **"quick change: [description]"**, or **"quick implementation: [description]"** detected:

→ Route directly to the Swift Path (Step S1). Skip all state detection.

• **"standard: [description]"** or **"standard mode: [description]"** detected:

→ Route directly to the Standard Path (Step ST1). Skip all state detection.

• **No swift or standard intent** detected:

→ Proceed to Step 1 (State Detection).

---

Step 1: State Detection

Check which artifacts exist on disk to determine the entry point. Check from most advanced to least advanced — first match wins:

| Artifact | Detected State | Resume Point | |----------|---------------|--------------| | `SIMPLIFICATION_REPORT.json` in `<plans-dir>/<project>/reports/` | Simplification done | G4 (Review implementation) | | Any `IMPLEMENTATION_REPORT_*.json` or `TESTING_REPORT_*.json` in `<plans-dir>/<project>/reports/` (no SIMPLIFICATION_REPORT) | Execution complete | G3 (Simplify?) | | `TASKS.md` in `<plans-dir>/<project>/` with parseable task entries | Tasks exist | G2 (Execution mode) | | `INTRODUCTION.md` in `<plans-dir>/<project>/` but no `TASKS.md` | Plan saved, not taskified | Auto-taskify, then G2 | | `SWIFT_REPORT.json` in `<plans-dir>/SWIFT_<name>/` | Swift complete | G5 (Completion handoff) | | `<plans-dir>/SWIFT_<name>/SWIFT_<name>.md` but no report | Swift plan exists, not executed | Resume swift execution | | `STANDARD_REPORT.json` in `<plans-dir>/STANDARD_<name>/` | Standard complete | G5 (Completion handoff) | | `<plans-dir>/STANDARD_<name>/STANDARD_<name>.md` but no report | Standard in progress | Resume standard execution | | None of the above | No plan found | G0 (No plan fallback) |

**If multiple projects detected** (more than one subdirectory in plans-dir with artifacts): list them with their states and ask the user which to implement.

**If artifacts detected for a single project:** ask: "Resume [project-name] at [detected stage], or start fresh?"

• **Resume** → skip to the detected gate
• **Start fresh** → begin at G0/G2 (do not delete existing artifacts)

---

Step 2: Gate G0 — No Plan Fallback

Only reached when no structured plan or swift artifacts are found.

Show progress:

Implementing: [no plan detected]

Ask (using `AskUserQuestion`):

**"No implementation plan found. What would you like to do?"**

Options: 1. **Quick implementation** — Describe a small change for swift mode 2. **Go to planning first** — Run `/arn-planning` to create a spec and plan

If **Quick implementation**: Ask for a description, then route to Swift Path (Step S1). If **Go to planning first**: `Skill: arn-code:arn-planning`. After planning completes and chains back, re-run state detection (Step 1). If the scope router assigned `standard` tier, route to Standard Path (Step ST1) instead of full execution.

---

Step 3: Auto — Taskify (conditional)

If state detection found `INTRODUCTION.md` but no `TASKS.md`, run taskify automatically:

Inform: "Creating task list from plan..."

> `Skill: arn-code:arn-code-taskify`

After taskify completes, proceed to G2.

---

Step 4: Gate G2 — Execution Mode

Show progress:

Implementing: EXECUTE -> simplify -> review-impl -> [ship]
              ^^^^^^^

Ask (using `AskUserQuestion`):

**"How should the tasks be executed?"**

Options: 1. **Sequential with review gates** (Recommended) — Each task is executed and reviewed before the next 2. **Parallel with Agent Teams** — Tasks run in parallel using Agent Teams (higher token cost) 3. **One task at a time** — Execute tasks manually, one at a time

Based on choice:

• **Sequential** → `Skill: arn-code:arn-code-execute-plan`
• **Agent Teams** → `Skill: arn-code:arn-code-execute-plan-teams`
• If Agent Teams is not available (environment variable not set), inform the user and suggest sequential instead.
• **One at a time** → `Skill: arn-code:arn-code-execute-task`