ed3dai/ed3d-plugins/executing-an-implementation-plan

Executing an Implementation Plan

Execute plan phase-by-phase, loading each phase just-in-time to minimize context usage.

Core principle: Read one phase → execute all tasks → review → move to next phase. Never load all phases upfront.

REQUIRED SKILL: requesting-code-review - The review loop (dispatch, fix, re-review until zero issues)

Overview

When NOT to use:

• No implementation plan exists yet (use writing-implementation-plans first)
• Plan needs revision (brainstorm first)

MANDATORY: Human Transparency

The human cannot see what subagents return. You are their window into the work.

Do not use nested subagents. This workflow may dispatch first-level task, review, bug-fix, and librarian subagents. Those subagents must not dispatch additional subagents; they must do their assigned work directly and report back to this caller.

After EVERY subagent completes (task-implementor, bug-fixer, code-reviewer), you MUST:

1. Print the subagent's full response to the user before taking any other action
2. Do not summarize or paraphrase - show them what the subagent actually said
3. Include all details: test counts, issue lists, commit hashes, error messages

Before dispatching any subagent:

• Briefly explain (2-3 sentences) what you're asking the agent to do
• State which phase this covers

Why this matters: When you silently process subagent output without showing the user, they lose visibility into their own codebase. They can't catch errors, learn from the process, or intervene when needed. Transparency is not optional.

Red flag: If you find yourself thinking "I'll just move on to the next step" without printing the subagent's response, STOP. Print it first.

REQUIRED: Implementation Plan Path

DO NOT GUESS. If the user has not provided a path to an implementation plan directory, you MUST ask for it.

Use AskUserQuestion:

Question: "Which implementation plan should I execute?"
Options:
  - [list any plan directories you find in docs/implementation-plans/]
  - "Let me provide the path"

If docs/implementation-plans/ doesn't exist or is empty, ask the user to provide the path directly.

Never assume, infer, or guess which plan to execute. The user must explicitly tell you.

The Process

1. Discover Phases

DO NOT read the full phase files yet. List them and read only the header and task markers.

# List phase files
ls [plan-directory]/phase_*.md
 
# For each file, get the header (first 10 lines include title and Goal)
head -10 [plan-directory]/phase_01.md
 
# Get task/subcomponent structure without reading full content
grep -E "START_TASK_|START_SUBCOMPONENT_" [plan-directory]/phase_01.md

The header includes the title (# [Phase Title]) and **Goal:** line. Extract the title for the task entry.

The grep output shows the task structure, e.g.:

<!-- START_TASK_1 -->
<!-- START_TASK_2 -->
<!-- START_SUBCOMPONENT_A (tasks 3-5) -->
<!-- START_TASK_3 -->
<!-- START_TASK_4 -->
<!-- START_TASK_5 -->

Examples of headers you might see:

• # Document Infrastructure Implementation Plan — Phase 1 implied
• # Phase 4: Link Resolution — Phase number explicit

Check for implementation guidance:

After discovering phases, check if .ed3d/implementation-plan-guidance.md exists in the project root:

# Check for implementation guidance (note the absolute path for later use)
ls [project-root]/.ed3d/implementation-plan-guidance.md

If the file exists, note its absolute path for use during code reviews. If it doesn't exist, proceed without it—do not pass a nonexistent path to reviewers.

Check for test requirements:

Check if test-requirements.md exists in the plan directory:

# Check for test requirements (note the absolute path for later use)
ls [plan-directory]/test-requirements.md

If the file exists, note its absolute path for use during final review. The test requirements document specifies what automated tests must exist for each acceptance criterion.

Create a session-isolated scratchpad directory:

# Extract slug from plan directory name (last path component, without trailing slash)
SLUG=$(basename "[plan-directory]")
# Generate unique session ID
SESSION_ID=$(printf '%04x%04x' $RANDOM $RANDOM)
# Create scratchpad path
SCRATCHPAD_DIR="/tmp/exec-${SLUG}-${SESSION_ID}"
mkdir -p "${SCRATCHPAD_DIR}"
echo "${SCRATCHPAD_DIR}"

This scratchpad ensures isolation when multiple execution sessions run in parallel. Pass it to code-reviewer invocations.

2. Create Phase-Level Task List

Use TaskCreate to create three task entries per phase (or TodoWrite in older Claude Code versions). Include the title from the header:

- [ ] Phase 1a: Read /absolute/path/to/phase_01.md — Document Infrastructure Implementation Plan
- [ ] Phase 1b: Execute tasks
- [ ] Phase 1c: Code review
- [ ] Phase 2a: Read /absolute/path/to/phase_02.md — API Integration
- [ ] Phase 2b: Execute tasks
- [ ] Phase 2c: Code review
...

Why absolute paths in task entries: After compaction, context may be summarized. The absolute path in the task entry ensures you always know exactly which file to read.

Why include the title: Gives visibility into what each phase covers without loading full content.

3. Execute Each Phase

For each phase, follow this cycle:

3a. Read Phase File (just-in-time)

Mark "Phase Na: Read [path]" as in_progress.

Read ONLY that phase file now. Extract:

• List of tasks in this phase
• Working directory
• Any phase-specific context

Mark "Phase Na: Read" as complete.

3b. Execute All Tasks

Mark "Phase Nb: Execute tasks" as in_progress.

Before dispatching, verify test coverage for functionality tasks:

If a functionality task (code that does something) has no tests specified:

1. Check if a subsequent task in the same phase provides tests
2. If no tests exist anywhere for this functionality → STOP
3. This is a plan gap. Surface to user: "Task N implements [functionality] but no corresponding tests exist in the plan. This needs tests before implementation."

Do NOT implement functionality without tests. Missing tests = plan gap, not something to skip.

Execute all tasks in sequence. For each task, dispatch task-implementor-fast with the phase file path:

<invoke name="Task">
<parameter name="subagent_type">ed3d-plan-and-execute:task-implementor-fast</parameter>
<parameter name="description">Implementing Phase X, Task Y: [description]</parameter>
<parameter name="prompt">
  Implement Task N from the phase file.
 
  Phase file: [absolute path to phase file]
  Task number: N
 
  Read the phase file and implement Task N (look for `<!-- START_TASK_N -->`).
 
  Your job is to:
  1. Read the phase file to understand context
  2. Apply all relevant skills, such as (if available) ed3d-house-style:coding-effectively
  3. Implement exactly what Task N specifies
  4. Verify with tests/build/lint
  5. Commit your work
  6. Report back with evidence
  7. Do not dispatch or invoke any subagents.
 
  Work from: [directory]
 
  Provide complete report per your agent instructions.
</parameter>
</invoke>

For subcomponents (grouped tasks), dispatch once for all tasks in the subcomponent:

<invoke name="Task">
<parameter name="subagent_type">ed3d-plan-and-execute:task-implementor-fast</parameter>
<parameter name="description">Implementing Phase X, Subcomponent A (Tasks 3-5): [description]</parameter>
<parameter name="prompt">
  Implement Subcomponent A (Tasks 3, 4, 5) from the phase file.
 
  Phase file: [absolute path to phase file]
  Tasks: 3, 4, 5 (look for `<!-- START_SUBCOMPONENT_A -->`)
 
  Read the phase file and implement all tasks in this subcomponent.
 
  Your job is to:
  1. Read the phase file to understand context
  2. Apply all relevant skills, such as (if available) ed3d-house-style:coding-effectively
  3. Implement all tasks in sequence
  4. Verify with tests/build/lint after completing all tasks
  5. Commit your work (one commit per task, or logical commits)
  6. Report back with evidence for each task
  7. Do not dispatch or invoke any subagents.
 
  Work from: [directory]
 
  Provide complete report covering all tasks.
</parameter>
</invoke>

Print each task-implementor's response before moving to the next task.

No code review between tasks. Execute all tasks in the phase first.

After all tasks complete, mark "Phase Nb: Execute tasks" as complete.

3c. Code Review for Phase

Mark "Phase Nc: Code review" as in_progress.

MANDATORY: Use the requesting-code-review skill for the review loop.

Context to provide:

• WHAT_WAS_IMPLEMENTED: Summary of all tasks in this phase
• PLAN_OR_REQUIREMENTS: All tasks from this phase
• BASE_SHA: commit before phase started
• HEAD_SHA: current commit
• IMPLEMENTATION_GUIDANCE: absolute path to .ed3d/implementation-plan-guidance.md (only if it exists—omit entirely if the file doesn't exist)
• SCRATCHPAD_DIR: session-isolated temp directory for code reviewer scratch files

The implementation guidance file contains project-specific coding standards, testing requirements, and review criteria. When provided, the code reviewer should read it and apply those standards during review.

Note: Test requirements validation happens at final review, not per-phase. Per-phase reviews focus on code quality and whether the phase includes tests for its functionality.

If code reviewer returns a context limit error:

The phase changed too much for a single review. Chunk the review:

1. Identify the midpoint of tasks in the phase
2. Run code review for first half of tasks (commits for tasks 1 through N/2)
3. Fix any issues found
4. Run code review for second half of tasks (commits for tasks N/2+1 through N)
5. Fix any issues found

When issues are found:

1. Create a task for EACH issue (survives compaction):

`` TaskCreate: "Phase N fix [Critical]: <VERBATIM issue description from reviewer>" TaskCreate: "Phase N fix [Important]: <VERBATIM issue description from reviewer>" TaskCreate: "Phase N fix [Minor]: <VERBATIM issue description from reviewer>" ...one task per issue... TaskCreate: "Phase N: Re-review after fixes" TaskUpdate: set "Re-review" blocked by all fix tasks ``

Copy issue descriptions VERBATIM, even if long. After compaction, the task description is all that remains — it must contain the full issue details for the bug-fixer to understand what to fix.

1. Dispatch `task-bug-fixer` with the phase file:

<invoke name="Task">
<parameter name="subagent_type">ed3d-plan-and-execute:task-bug-fixer</parameter>
<parameter name="description">Fixing review issues for Phase X</parameter>
<parameter name="prompt">
  Fix issues from code review for Phase X.
 
  Phase file: [absolute path to phase file]
 
  Code reviewer found these issues:
  [list all issues - Critical, Important, and Minor]
 
  Read the phase file to understand the tasks and context.
 
  Your job is to:
  1. Understand root cause of each issue
  2. Apply fixes systematically (Critical → Important → Minor)
  3. Verify with tests/build/lint
  4. Commit your fixes
  5. Report back with evidence
  6. Do not dispatch or invoke any subagents.
 
  Work from: [directory]
 
  Fix ALL issues — including every Minor issue. The goal is ZERO issues on re-review.
  Minor issues are not optional. Do not skip them.
</parameter>
</invoke>

1. Mark "Fix issues" complete, then re-review per the requesting-code-review skill.

1. If re-review finds more issues, create new fix/re-review tasks. Continue loop until zero issues.

1. Mark "Re-review" complete when zero issues.