hermes-skills/writing-plans/SKILL.md

name, description, version, author, license, platforms, metadata

name	description	version	author	license	platforms	metadata
writing-plans	Write implementation plans: bite-sized tasks, paths, code.	1.1.0	Hermes Agent (adapted from obra/superpowers)	MIT	linux macos windows	hermes tags related_skills planning design implementation workflow documentation subagent-driven-development test-driven-development requesting-code-review

Writing Implementation Plans

Overview

Write comprehensive implementation plans assuming the implementer has zero context for the codebase and questionable taste. Document everything they need: which files to touch, complete code, testing commands, docs to check, how to verify. Give them bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.

Assume the implementer is a skilled developer but knows almost nothing about the toolset or problem domain. Assume they don't know good test design very well.

Core principle: A good plan makes implementation obvious. If someone has to guess, the plan is incomplete.

When to Use

Always use before:

• Implementing multi-step features
• Breaking down complex requirements
• Delegating to subagents via subagent-driven-development

Don't skip when:

• Feature seems simple (assumptions cause bugs)
• You plan to implement it yourself (future you needs guidance)
• Working alone (documentation matters)

Bite-Sized Task Granularity

Each task = 2-5 minutes of focused work.

Every step is one action:

• "Write the failing test" — step
• "Run it to make sure it fails" — step
• "Implement the minimal code to make the test pass" — step
• "Run the tests and make sure they pass" — step
• "Commit" — step

Too big:

### Task 1: Build authentication system
[50 lines of code across 5 files]

Right size:

### Task 1: Create User model with email field
[10 lines, 1 file]

### Task 2: Add password hash field to User
[8 lines, 1 file]

### Task 3: Create password hashing utility
[15 lines, 1 file]

Plan Document Structure

Header (Required)

Every plan MUST start with:

# [Feature Name] Implementation Plan

> **For Hermes:** Use subagent-driven-development skill to implement this plan task-by-task.

**Goal:** [One sentence describing what this builds]

**Architecture:** [2-3 sentences about approach]

**Tech Stack:** [Key technologies/libraries]

---

Task Structure

Each task follows this format:

### Task N: [Descriptive Name]

**Objective:** What this task accomplishes (one sentence)

**Files:**
- Create: `exact/path/to/new_file.py`
- Modify: `exact/path/to/existing.py:45-67` (line numbers if known)
- Test: `tests/path/to/test_file.py`

**Step 1: Write failing test**

```python
def test_specific_behavior():
    result = function(input)
    assert result == expected
```

**Step 2: Run test to verify failure**

Run: `pytest tests/path/test.py::test_specific_behavior -v`
Expected: FAIL — "function not defined"

**Step 3: Write minimal implementation**

```python
def function(input):
    return expected
```

**Step 4: Run test to verify pass**

Run: `pytest tests/path/test.py::test_specific_behavior -v`
Expected: PASS

**Step 5: Commit**

```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```

Writing Process

Step 1: Understand Requirements

Read and understand:

• Feature requirements
• Design documents or user description
• Acceptance criteria
• Constraints

Step 2: Explore the Codebase

Use Hermes tools to understand the project:

# Understand project structure
search_files("*.py", target="files", path="src/")

# Look at similar features
search_files("similar_pattern", path="src/", file_glob="*.py")

# Check existing tests
search_files("*.py", target="files", path="tests/")

# Read key files
read_file("src/app.py")

Step 3: Design Approach

Decide:

• Architecture pattern
• File organization
• Dependencies needed
• Testing strategy

Step 4: Write Tasks

Create tasks in order:

1. Setup/infrastructure
2. Core functionality (TDD for each)
3. Edge cases
4. Integration
5. Cleanup/documentation

Step 5: Add Complete Details

For each task, include:

• Exact file paths (not "the config file" but src/config/settings.py)
• Complete code examples (not "add validation" but the actual code)
• Exact commands with expected output
• Verification steps that prove the task works

Step 6: Review the Plan

Check:

• Tasks are sequential and logical
• Each task is bite-sized (2-5 min)
• File paths are exact
• Code examples are complete (copy-pasteable)
• Commands are exact with expected output
• No missing context
• DRY, YAGNI, TDD principles applied

Step 7: Save the Plan

mkdir -p docs/plans
# Save plan to docs/plans/YYYY-MM-DD-feature-name.md
git add docs/plans/
git commit -m "docs: add implementation plan for [feature]"

Principles

DRY (Don't Repeat Yourself)

Bad: Copy-paste validation in 3 places Good: Extract validation function, use everywhere

YAGNI (You Aren't Gonna Need It)

Bad: Add "flexibility" for future requirements Good: Implement only what's needed now

# Bad — YAGNI violation
class User:
    def __init__(self, name, email):
        self.name = name
        self.email = email
        self.preferences = {}  # Not needed yet!
        self.metadata = {}     # Not needed yet!

# Good — YAGNI
class User:
    def __init__(self, name, email):
        self.name = name
        self.email = email

TDD (Test-Driven Development)

Every task that produces code should include the full TDD cycle:

1. Write failing test
2. Run to verify failure
3. Write minimal code
4. Run to verify pass

See test-driven-development skill for details.

Frequent Commits

Commit after every task:

git add [files]
git commit -m "type: description"

Common Mistakes

Gathering Technical Details During Plan Writing

Bad: When asked to write a plan, start running terminal commands to verify model availability, check API endpoints, test connectivity, or gather live data. The user asked for a plan document, not execution.

Good: Write the plan from known information. List verification steps as tasks (e.g., "Phase 0: verify SearXNG JSON endpoint works"). Do not execute them during plan creation. The plan is a specification — it can note unknowns and flag what needs verification before implementation begins.

Why this matters: The user explicitly corrected this: "YOu are supposed to ONLY be writing the plan md file!!" Plan mode means plan mode. Don't explore, don't verify, don't probe — just write the plan.

Jumping to Execution During Plan Discussion

Bad: User asks for a plan. You write it. Then the user asks clarifying questions about the plan (e.g., "which quant?", "replace or coexist?"). You interpret this as a signal to start deploying/building. You SSH into servers, run docker compose, download models.

Good: User asks for a plan. You write it. User asks questions about the plan — you answer them in text. You stay in plan mode. You do NOT execute anything until the user explicitly says "build it," "deploy it," "go ahead," or similar.

Why this matters: The user explicitly corrected this: "you are supposed to be building a text md plan... What are you doing?" Plan-discussion questions are about refining the plan, not a green light to start building. The boundary is: plan mode ends ONLY when the user gives an explicit execution command. Questions about the plan are still plan mode.

Vague Tasks

Bad: "Add authentication" Good: "Create User model with email and password_hash fields"

Incomplete Code

Bad: "Step 1: Add validation function" Good: "Step 1: Add validation function" followed by the complete function code

Missing Verification

Bad: "Step 3: Test it works" Good: "Step 3: Run pytest tests/test_auth.py -v, expected: 3 passed"

Missing File Paths

Bad: "Create the model file" Good: "Create: src/models/user.py"

Plan Mode (No-Execution)

When the user invokes plan mode (/plan in chat, "plan this" etc.), write a markdown plan to .hermes/plans/YYYY-MM-DD_HHMMSS-<slug>.md without executing any code, editing project files, or running mutating commands. This was previously the plan skill (v1.0.0), absorbed here as plan mode is just the trigger; the methodology is writing-plans.

Core behavior in plan mode:

• Do not implement code, edit project files, commit, push, or perform external actions.
• You may read files, search the codebase, or run read-only commands for context.
• Your deliverable is a markdown plan saved under .hermes/plans/.
• If the request is clear, write the plan directly. If underspecified, ask a brief clarifying question.
• After saving, reply with what you planned and the path.

Execution Handoff

After saving the plan, offer the execution approach:

"Plan complete and saved. Ready to execute using subagent-driven-development — I'll dispatch a fresh subagent per task with two-stage review (spec compliance then code quality). Shall I proceed?"

When executing, use the subagent-driven-development skill:

• Fresh delegate_task per task with full context
• Spec compliance review after each task
• Code quality review after spec passes
• Proceed only when both reviews approve

Remember

Bite-sized tasks (2-5 min each)
Exact file paths
Complete code (copy-pasteable)
Exact commands with expected output
Verification steps
DRY, YAGNI, TDD
Frequent commits

A good plan makes implementation obvious.