Writing Plans

changelog: Enhanced with ClawHub metadata, expanded examples, and rationalization prevention

Install

openclaw skills install @pmuhammadagus-byte/writing-plans

writing-plans — X∞ Compliance Layer

1. IDENTITY

Skill milik user: writing-plans. Mengikuti Skill Architecture Standard X∞ (wajib).

2. PURPOSE

Menyediakan kemampuan writing-plans kepada agent saat relevan.

3. METADATA

name: writing-plans
version: 1.0.0
standard: Skill Architecture Standard X∞ (21-node)
scope: lihat body domain
depends_on: tidak ada (mandiri)

4. TRIGGER ENGINE

Aktif ketika user meminta hal yang cocok dengan deskripsi di atas. Negative trigger: di luar scope deskripsi.

5. CONTEXT ENGINE

Baca OS/ARCH/runtime sebelum bertindak. Termux Android ARM64 ≠ Ubuntu x86_64.

6. DECISION POLICY

IF uncertainty → VERIFY IF high risk → ASK/STOP IF tool unavailable → ALTERNATIVE IF action fails → RECOVER

7. REASONING POLICY

Evidence-first. Bedakan FAKTA vs HIPOTESIS. Confidence: CONFIRMED/LIKELY/POSSIBLE/UNKNOWN.

8. EXECUTION POLICY

Ambil tindakan relevan, lalu VERIFY. Jangan klaim sukses sebelum diverifikasi.

9. TOOL POLICY

Pilih tool berdasar kebutuhan+konteks. Jangan asal panggil semua tool.

10. MEMORY POLICY

Ingat hal relevan; abaikan noise. Retrieve saat dibutuhkan, update bila berubah.

11. VERIFICATION ENGINE

ACTION → VERIFY → SUCCESS? Jika tidak: DIAGNOSE → RETRY/CHANGE STRATEGY.

12. ERROR RECOVERY

transient→retry; timeout→backoff; auth→credential check; dependency→diagnosis; unknown→investigate.

13. SECURITY GUARDRAILS

NEVER log secret. REDACT API KEY/TOKEN/PASSWORD/SECRET sebelum simpan. PII: MINIMIZE→REDACT→HASH.

14. EVALUATION

Self-eval: capai goal? terverifikasi? ada asumsi? ada gagal? Kirim ke Agent Evaluation Engine.

15. OBSERVABILITY

Emit: START/PROGRESS/TOOL CALL/ERROR/RETRY/SUCCESS/FAILURE + TRACE_ID (tanpa secret).

16. PERFORMANCE OPTIMIZATION

FULL→OPTIMIZED→LOW RESOURCE mode bila terbatas. Prioritas: TASK>SAFETY>RELIABILITY.

17. SELF-IMPROVEMENT

USE→OBSERVE→EVALUATE→FIND WEAKNESS→IMPROVE→TEST→NEW VERSION (via evaluasi+regresi).

18. VERSIONING

Semver. Perubahan struktur = MAJOR. CHANGELOG wajib. CHANGELOG

1.0.0 — Light upgrade: frontmatter description rusak (berisi teks changelog) diganti deskripsi trigger; Node 2 (PURPOSE) & Node 3 (METADATA) diisi; metadata.openclaw.version diset 1.0.0. Body domain dipertahankan.

19. COMPATIBILITY

Tahu OS/ARCH/RUNTIME/versi/tool/API tersedia.

20. KNOWLEDGE SOURCES

Trust hierarchy: OFFICIAL>PRIMARY>REPUTABLE>COMMUNITY>UNKNOWN. Tandai VERIFIED/LIKELY/UNCERTAIN/OUTDATED/CONFLICTING.

21. EXIT CONDITIONS

Berhenti pada: SUCCESS/FAILURE/BLOCKED/NEED USER/NEED CREDENTIAL/NEED TOOL/NEED VERIFICATION.

Writing Plans

Overview

Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.

Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.

Announce at start: "I'm using the writing-plans skill to create the implementation plan."

Context: If working in an isolated worktree, it should have been created via the superpowers:using-git-worktrees skill at execution time.

Save plans to: docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md

(User preferences for plan location override this default)

When to Use

dot

digraph when_to_use {
    "Have spec/requirements?" [shape=diamond];
    "Multi-step task?" [shape=diamond];
    "Before touching code?" [shape=diamond];
    "writing-plans" [shape=box];
    "Skip planning" [shape=box];

    "Have spec/requirements?" -> "Multi-step task?" [label="yes"];
    "Have spec/requirements?" -> "Skip planning" [label="no - simple"];
    "Multi-step task?" -> "Before touching code?" [label="yes"];
    "Multi-step task?" -> "Skip planning" [label="no - already coding"];
    "Before touching code?" -> "writing-plans" [label="yes"];
    "Before touching code?" -> "Skip planning" [label="no - too late"];
}

Use when:

You have a spec or requirements document
Task involves multiple steps
Before writing any code

Don't use when:

Simple single-step task
Already started coding
No clear requirements

Scope Check

If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.

File Structure

Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.

Design units with clear boundaries and well-defined interfaces. Each file should have one clear responsibility.
You reason best about code you can hold in context at once, and your edits are more reliable when files are focused. Prefer smaller, focused files over large ones that do too much.
Files that change together should live together. Split by responsibility, not by technical layer.
In existing codebases, follow established patterns. If the codebase uses large files, don't unilaterally restructure - but if a file you're modifying has grown unwieldy, including a split in the plan is reasonable.

This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.

Task Right-Sizing

A task is the smallest unit that carries its own test cycle and is worth a fresh reviewer's gate. When drawing task boundaries: fold setup, configuration, scaffolding, and documentation steps into the task whose deliverable needs them; split only where a reviewer could meaningfully reject one task while approving its neighbor. Each task ends with an independently testable deliverable.

Bite-Sized Task Granularity

Each step is one action (2-5 minutes):

"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

Plan Document Header

Every plan MUST start with this header:

markdown

# [Feature Name] Implementation Plan

> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.

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

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

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

## Global Constraints

[The spec's project-wide requirements — version floors, dependency limits,
naming and copy rules, platform requirements — one line each, with exact
values copied verbatim from the spec. Every task's requirements implicitly
include this section.]

---

Task Structure

markdown

### Task N: [Component Name]

**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`

**Interfaces:**
- Consumes: [what this task uses from earlier tasks — exact signatures]
- Produces: [what later tasks rely on — exact function names, parameter
  and return types. A task's implementer sees only their own task; this
  block is how they learn the names and types neighboring tasks use.]

- [ ] **Step 1: Write the failing test**

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

- [ ] **Step 2: Run test to verify it fails**

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

- [ ] **Step 3: Write minimal implementation**

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

- [ ] **Step 4: Run test to verify it passes**

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

- [ ] **Step 5: Commit**

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

No Placeholders

Every step must contain the actual content an engineer needs. These are plan failures — never write them:

"TBD", "TODO", "implement later", "fill in details"
"Add appropriate error handling" / "add validation" / "handle edge cases"
"Write tests for the above" (without actual test code)
"Similar to Task N" (repeat the code — the engineer may be reading tasks out of order)
Steps that describe what to do without showing how (code blocks required for code steps)
References to types, functions, or methods not defined in any task

Common Rationalizations

Excuse	Reality
"I'll add placeholders and fill them later"	You won't. Write complete steps now.
"This step is obvious, no need for code"	Write the code. Obvious ≠ documented.
"The engineer can figure it out"	They shouldn't have to. Plan everything.
"I'll just describe what to do"	Show code blocks. Description ≠ implementation.
"The plan is getting too long"	Better long and complete than short and ambiguous.
"I know what this means"	You do. The engineer reading this might not.

Self-Review

After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.

1. Spec coverage: Skim each section/requirement in the spec. Can you point to a task that implements it? List any gaps.

2. Placeholder scan: Search your plan for red flags — any of the patterns from the "No Placeholders" section above. Fix them.

3. Type consistency: Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called clearLayers() in Task 3 but clearFullLayers() in Task 7 is a bug.

If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.

Execution Handoff

After saving the plan, offer execution choice:

"Plan complete and saved to docs/superpowers/plans/<filename>.md. Two execution options:

1. Subagent-Driven (recommended) - I dispatch a fresh subagent per task, review between tasks, fast iteration

2. Inline Execution - Execute tasks in this session using executing-plans, batch execution with checkpoints

Which approach?"

If Subagent-Driven chosen:

REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development
Fresh subagent per task + two-stage review

If Inline Execution chosen:

REQUIRED SUB-SKILL: Use superpowers:executing-plans
Batch execution with checkpoints for review

Quick Reference

Situation	Action
Have spec	Write plan
Multi-step task	Write plan
Before coding	Write plan
Plan written	Self-review
Self-review done	Offer execution choice
User chooses subagent	Use subagent-driven-development
User chooses inline	Use executing-plans