<< All versions

Skill v1.0.1

currentAutomated scan100/100
mylukin/agent-foreman/feature-next

3 files

──Details
PublishedSeptember 30, 2026 at 10:57 AM
Content Hashsha256:da63559c07ddde6a...
Git SHA2763f83578d6
Bump Typepatch
Compare with v1.0.0
──Files
Files (1 file, 3.7 KB)
SKILL.md3.7 KBactive
SKILL.md · 133 lines · 3.7 KB

version: "1.0.1" name: feature-next description: Implements a single task following the next → implement → check → done workflow with TDD support. Use when working on one specific task, implementing a single feature from the backlog, or following TDD red-green-refactor cycle. Triggers on 'next task', 'next feature', 'implement feature', 'work on feature', 'single task mode', 'what should I work on'. allowed-tools: [Bash, Read, Glob, Grep, Write, Edit] user-invocable: true


Task Next

One command: agent-foreman next

⚠️ STRICT WORKFLOW - NO IMPROVISATION

You MUST follow this exact sequence. Do NOT skip or reorder steps.

next → implement → check → done
❌ FORBIDDEN✅ REQUIRED
Skip check stepRun agent-foreman check before done
Go straight to implementationRun agent-foreman next first
Invent extra stepsUse only the 4 steps above

⛔ CLI-ONLY ENFORCEMENT

NEVER bypass CLI for workflow decisions:

❌ FORBIDDEN✅ REQUIRED
Read ai/tasks/index.json to select taskUse agent-foreman next
Read index.json to check statusUse agent-foreman status
Read index.json for TDD modeCheck CLI output for !!! TDD ENFORCEMENT ACTIVE !!!
Edit task files to change statusUse agent-foreman done/fail

Allowed: Reading task .md files for acceptance criteria AFTER running agent-foreman next.


Quick Start

bash
agent-foreman next # Auto-select next priority
agent-foreman next auth.login # Specific task

Workflow

next → implement → check → done
bash
agent-foreman next # 1. Get task + acceptance criteria
# ... implement the task ... # 2. Write code
agent-foreman check <id> # 3. Verify implementation
agent-foreman done <id> # 4. Mark complete + commit

Check TDD Mode First

Look for "!!! TDD ENFORCEMENT ACTIVE !!!" in agent-foreman next output.

TDD Workflow (when strict mode active)

bash
# STEP 1: Get task + TDD guidance
agent-foreman next <task_id>
# STEP 2: RED - Write failing tests FIRST
# Create test file at suggested path
# Run tests: <your-test-command>
# Verify tests FAIL (confirms tests are valid)
# STEP 3: GREEN - Implement minimum code
# Write minimum code to pass tests
# Run tests: <your-test-command>
# Verify tests PASS
# STEP 4: REFACTOR - Clean up
# Clean up code while keeping tests passing
# STEP 5: Verify + Complete
agent-foreman check <task_id>
agent-foreman done <task_id>

CRITICAL: DO NOT write implementation code before tests exist in strict TDD mode!

Priority Order

  1. needs_review → may be broken
  2. failing → not implemented
  3. Lower priority number → higher priority (0 is highest)

⚠️ BREAKDOWN → VALIDATE → IMPLEMENT Workflow

When `next` shows "VALIDATION PHASE REMINDER":

bash
# All BREAKDOWNs complete → Run validation FIRST
agent-foreman validate
# Then proceed with implementation
agent-foreman next

ALWAYS run `done` after completing each task (including BREAKDOWN tasks).

Options

FlagEffect
--checkRun tests before showing task
--dry-runPreview without changes
--jsonOutput as JSON for scripting
--quietSuppress decorative output
--allow-dirtyAllow with uncommitted changes
--refresh-guidanceForce regenerate TDD guidance

Complete Options

bash
agent-foreman done <id> # Mark complete + commit
agent-foreman done <id> --full # Run all tests
agent-foreman done <id> --skip-e2e # Skip E2E tests
agent-foreman done <id> --no-commit # Manual commit
← v1.0.0All versions