/project-execution

name: project-execution
description: Executes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after planning is complete and tasks are ready to implement.
alwaysApply: false
# Custom metadata (not used by Claude for matching):
model: sonnet
tools_allowed: all
category: workflow
tags: [execution, implementation, progress-tracking, quality-gates, tdd]
complexity: intermediate
model_hint: standard
estimated_tokens: 2100
progressive_loading: true
references:
- references/mission-report.md
role: library

When To Use

• After planning phase completes
• Ready to implement tasks
• Need systematic execution with tracking
• Want checkpoint-based validation
• Executing task lists with dependencies
• Monitoring progress and velocity

When NOT To Use

• No implementation plan exists (use `Skill(attune:project-planning)` first)
• Still planning or designing (complete planning phase before execution)
• Single isolated task (execute directly without framework overhead)
• Exploratory coding or prototyping (use focused development instead)

Integration

**With superpowers**:

• Uses `Skill(superpowers:executing-plans)` for systematic execution
• Uses `Skill(superpowers:systematic-debugging)` for issue resolution
• Uses `Skill(superpowers:verification-before-completion)` for validation
• Uses `Skill(superpowers:test-driven-development)` for TDD workflow

**With imbue**:

• Uses `Skill(imbue:graduated-implementation)` at the ramp gate so

each increment's ambition is earned by demonstrated understanding of the prior one, not ramped on completion alone

**Without superpowers**:

• Standalone execution framework
• Built-in checkpoint validation
• Progress tracking patterns

Execution Framework

Pre-Execution Phase

**Actions**: 1. Load implementation plan 2. Validate project initialized 3. Check dependencies installed 4. Review task dependency graph 5. Identify starting tasks (no dependencies)

**Validation**:

• ✅ Plan file exists and is valid
• ✅ Project structure initialized
• ✅ Git repository configured
• ✅ Development environment ready

Task Execution Loop

**For each task in dependency order**:

1. PRE-TASK
   - Verify dependencies complete
   - Review acceptance criteria
   - Create feature branch (optional)
   - Set up task context

2. IMPLEMENT (TDD Cycle)
   - Write failing test (RED)
   - Implement minimal code (GREEN)
   - Refactor for quality (REFACTOR)
   - Repeat until all criteria met

3. VALIDATE
   - All tests passing?
   - All acceptance criteria met?
   - Code quality checks pass?
   - Documentation updated?

4. RAMP GATE (before the next, more ambitious task)
   - Invoke Skill(imbue:graduated-implementation)
   - Demonstrate understanding of THIS increment, sized to stakes:
     low-stakes on the evidence gate (green tests plus a recorded
     tradeoff), high-stakes on the human explaining the diff unaided
   - On a clean demonstration, record it in the ramp ledger and
     mark the rung widened; below the band, hold and split the next
     task smaller instead of ramping

5. CHECKPOINT
   - Mark task complete IMMEDIATELY (do NOT batch)
   - Update execution state
   - Report progress
   - Identify blockers

**Task Completion Discipline**: Always call `TaskUpdate(taskId: "X", status: "completed")` right after finishing each task. Never defer completions to end of session.

**Verification:** Run `pytest -v` to verify tests pass.

Post-Execution Phase

**Actions**: 1. Verify all tasks complete 2. Run full test suite 3. Check code quality metrics 4. Generate completion report 5. Prepare for deployment/release 6. Record lessons learned (see below)

Record Lessons Learned (decision journal)

Implementation is where the honest lessons appear: the approach that had to be reworked, the blocker that cost a day, the assumption from planning that did not hold. Capture these in `docs/lessons-learned.md` now, blamelessly, instead of letting them vanish into "done." Draft and confirm one entry per substantive lesson:

• If leyline is installed, invoke `Skill(leyline:decision-journal)` and follow

it to append a lesson entry: `what_happened`, `what_didnt_work`, `root_cause`, and a concrete `action`. Set `phase` to `execute`. Show the draft; append on confirmation (status starts `open`).

• Fallback (leyline absent): append to `docs/lessons-learned.md` by hand using

the in-file ENTRY TEMPLATE; assign the next `LL-NNN` id.

Trigger this whenever execution involved rework, a failed approach, or a blocker that exhausted the two-challenge / 3-attempt limit. A clean run with no surprises needs no entry.

Terminal Phase Notice

This is the **final phase** of the attune workflow. No auto-continuation occurs after execution completes. The workflow terminates here. Unlike brainstorming, specification, and planning phases, execution does NOT auto-invoke any subsequent phase.

Task Execution Pattern

Delegation Check (First, Per Task)

Before implementing a task, delegate it. `Skill(conjure:delegation-core)` is on by default, so the decision to make is whether a Keep Local clause holds, not whether to bother.

Keep the task local when it is design or trade-off work, when its context carries a secret, when it needs turn-by-turn iteration, or when its output cannot be validated afterward. Otherwise hand it to the delegator and validate what comes back through the same TDD workflow below. The tests are the validation: a delegated implementation that fails the RED test is rejected exactly like a local one.

If the result carries a `fallback_reason`, no external model ran. Report which providers were tried, then implement the task here. An exhausted chain is not a blocked task and does not belong in `docs/lessons-learned.md`.

TDD Workflow

**RED Phase**:

# Write test that fails
def test_user_authentication():
    user = authenticate("user@example.com", "password")
    assert user.is_authenticated