From copilot-cli-toolkit
Plans complex tasks into milestones with specs and reviews them, then executes approved plans by delegating to agents. Use for multi-step projects with dependencies and architectural needs.
npx claudepluginhub rjmurillo/ai-agentsThis skill uses the workspace's default tool permissions.
Two workflows for complex tasks:
references/DEVELOPMENT.mdreferences/agent-architecture-patterns.mdreferences/design-pit-of-success.mdreferences/explainers-and-intents.mdreferences/hybrid-memory-architecture.mdreferences/mental-models-galls-law.mdreferences/strategy-ooda-loop.mdresources/default-conventions.mdresources/diff-format.mdresources/plan-format.mdresources/temporal-contamination.mdscripts/executor.pyscripts/planner.pyBreaks down complex tasks into milestone plans with specs and dependencies, reviews them, then executes via delegation to agents. For multi-step projects, architectures, or migrations.
Orchestrates execution of implementation plans with independent tasks by dispatching implementers and reviewers, tracking granular progress per task and phase.
Executes written implementation plans: loads and critically reviews them, runs tasks in dependency order with parallel dispatch, separate worker-validator subagents, and verifies completion.
Share bugs, ideas, or general feedback.
Two workflows for complex tasks:
Invoke planner.py when user asks to:
Invoke executor.py when user asks to:
Use the planner skill when the task has:
Skip the planner skill when the task is:
| Script | Purpose |
|---|---|
scripts/planner.py | Planning and review workflow with step-based state management |
scripts/executor.py | Execution workflow for approved plans with milestone delegation |
| Trigger Phrase | Operation |
|---|---|
plan this feature | planner.py (planning phase) |
create implementation plan | planner.py (planning phase) |
review the plan and pick up next item | executor.py (execution phase) |
execute the plan at plans/X.md | executor.py (execution phase) |
resume execution | executor.py (continue from last step) |
| Avoid | Why | Instead |
|---|---|---|
| Skipping review phase after planning | Misses quality/temporal issues | Always run review steps 1-2 before execution |
| Starting execution without /clear | Context pollution from planning | User should /clear before execution workflow |
| Manually following workflow steps | Script manages state and transitions | Run the script and follow its output |
| Planning single-step tasks | Overhead exceeds benefit | Implement directly without planner |
| Editing plan during execution | Creates drift between plan and actions | Return to planning phase for changes |
After planning:
After execution:
PLANNING PHASE (steps 1-N)
|
v
Write plan to file
|
v
REVIEW PHASE (steps 1-2)
|-- Step 1: @agent-technical-writer (plan-annotation)
|-- Step 2: @agent-quality-reviewer (plan-review)
v
APPROVED --> Execution workflow
Before invoking step 1, you MUST have:
python3 scripts/planner.py \
--step-number 1 \
--total-steps <estimated_steps> \
--thoughts "<your thinking about the problem>"
| Argument | Description |
|---|---|
--phase | Workflow phase: planning (default) or review |
--step-number | Current step (starts at 1) |
--total-steps | Estimated total steps for this phase |
--thoughts | Your thinking, findings, and progress |
STATUS: phase_completeWhen planning phase completes, the script outputs an explicit ACTION REQUIRED
marker:
============================================
>>> ACTION REQUIRED: INVOKE REVIEW PHASE <<<
============================================
You MUST invoke the review phase before proceeding to execution.
The review phase ensures:
After writing the plan file, transition to review phase:
python3 scripts/planner.py \
--phase review \
--step-number 1 \
--total-steps 2 \
--thoughts "Plan written to [path/to/plan.md]"
Delegate to @agent-technical-writer with mode: plan-annotation
Delegate to @agent-quality-reviewer with mode: plan-review
Step 1: Execution Planning
|
v
Step 2: Reconciliation (conditional, if prior work signaled)
|
v
Step 3: Milestone Execution (repeat until all complete)
|
v
Step 4: Post-Implementation QR
|
v
QR issues? --YES--> Step 5: Issue Resolution --> delegate fixes --> Step 4
|
NO
v
Step 6: Documentation
|
v
Step 7: Retrospective
Before invoking step 1, you MUST have:
python3 scripts/executor.py \
--plan-file PATH \
--step-number 1 \
--total-steps 7 \
--thoughts "<user's request and context>"
| Argument | Description |
|---|---|
--plan-file | Path to the approved plan file |
--step-number | Current step (1-7) |
--total-steps | Always 7 for executor |
--thoughts | Your current thinking and status |
| Step | Name | Purpose |
|---|---|---|
| 1 | Execution Planning | Analyze plan, detect reconciliation, strategy |
| 2 | Reconciliation | (conditional) Validate existing code vs plan |
| 3 | Milestone Execution | Delegate to agents, run tests (repeat) |
| 4 | Post-Implementation QR | Quality review of implemented code |
| 5 | Issue Resolution | (conditional) Present issues, collect fixes |
| 6 | Documentation | TW pass for CLAUDE.md, README.md |
| 7 | Retrospective | Present execution summary |
Note: Step 3 may be re-invoked multiple times until all milestones complete. Step 4 may loop back through step 5 until QR passes.
| Resource | Purpose |
|---|---|
resources/plan-format.md | Plan template (injected at planning completion) |
resources/diff-format.md | Authoritative specification for code change format |
resources/temporal-contamination.md | Detecting/fixing temporally contaminated comments |
resources/default-conventions.md | Default conventions when project docs are silent |
Note: Execution guidance is embedded directly in scripts/executor.py (not in
separate resource files) since it's only used by that script.
| Reference | Purpose |
|---|---|
references/strategy-ooda-loop.md | Map planning and execution phases to OODA stages |
references/design-pit-of-success.md | Design milestones so the obvious path produces correct results |
references/mental-models-galls-law.md | Validate milestone decomposition against incremental complexity |
.claude/skills/analyze/references/engineering-complexity-tiers.md | Classify tasks by tier (single source of truth in analyze skill) |
references/explainers-and-intents.md | Write explainers before work, use intents as permission gates |
references/agent-architecture-patterns.md | Skill budget rule, 3-file planning pattern, milestone decomposition for agent systems |
references/hybrid-memory-architecture.md | Hybrid retrieval cascade, memory decay tiers, decision extraction for planning memory systems |
# === PLANNING WORKFLOW ===
# Start planning
python3 scripts/planner.py --step-number 1 --total-steps 4 --thoughts "..."
# Continue planning
python3 scripts/planner.py --step-number 2 --total-steps 4 --thoughts "..."
# Start review (after plan written)
python3 scripts/planner.py --phase review --step-number 1 --total-steps 2 \
--thoughts "Plan at plans/feature.md"
# Continue review
python3 scripts/planner.py --phase review --step-number 2 --total-steps 2 \
--thoughts "TW done, ready for QR"
# === EXECUTION WORKFLOW ===
# Start execution
python3 scripts/executor.py --plan-file plans/feature.md --step-number 1 \
--total-steps 7 --thoughts "Execute the feature plan"
# Continue milestone execution
python3 scripts/executor.py --plan-file plans/feature.md --step-number 3 \
--total-steps 7 --thoughts "Completed M1, M2. Executing M3..."
# After QR passes
python3 scripts/executor.py --plan-file plans/feature.md --step-number 6 \
--total-steps 7 --thoughts "QR passed. Running documentation."
# Generate retrospective
python3 scripts/executor.py --plan-file plans/feature.md --step-number 7 \
--total-steps 7 --thoughts "Execution complete. Generating retrospective."