Skip to content
Agentmart
Submit a tool

planning

Decompose specs into executable task sequences.

Skill by renathoaz

IndexedMIT★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/renathoaz-planning

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Decompose specs into executable task sequences.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/planning

What's inside

Skill name
planning
Description
Decompose specs into executable task sequences.
License
MIT
Instructions
127 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • plan-document-reviewer-prompt.md · references/

SKILL.md (first lines)

# Planning

Transform an approved spec into a step-by-step implementation plan that an engineer with zero project context can follow.

**Announce at start:** "Generating implementation plan using arsyn:planning."

**Save to:** `docs/arsyn/plans/YYYY-MM-DD-<feature-name>.md` (user preference overrides)

## Scope Gate

If the spec covers multiple independent subsystems, it should have been split during ideation. If it was not, recommend separate plans — one per subsystem. Each plan must produce working, testable software on its own.

## File Map

Before defining tasks, enumerate every file that will be created or modified and its responsibility. This locks in decomposition decisions.

- One clear responsibility per file. Prefer focused files over large ones.
- Files that change together live together. Split by responsibility, not by layer.
- Follow existing codebase patterns. If a file you are modifying has grown unwieldy, include a split in the plan.

## Task Granularity

Each step is a single action (2-5 minutes):

| Step | Example |
|------|---------|
| Write failing test | `test_user_creates_account` |
| Run test, confirm failure | `pytest ... -v` -> FAIL |
| Implement minimal code | function body |
| Run test, confirm pass | `pytest ... -v` -> PASS |
| Commit | `git commit -m "feat: ..."` |

## Plan Header

Every plan starts with:

```markdown
# [Feature] Implementation Plan

> **For agents:** Use arsyn:orchestrating (preferred) or arsyn:executing to run this plan. Steps use `- [ ]` checkboxes.

**Goal:** [One sentence]

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

**Tech Stack:** [Key technologies]

---
```

## Task Format

````markdown
### Task N: [Name] `[CONFIDENCE: HIGH|MEDIUM|LOW]`

**Files:**
- Create: `src/exact/path.py`
- Modify: `src/existing/file.py:40-55`
- Test: `tests/exact/test_path.py`

- [ ] **N.1 Write failing test**

```python
def test_behavior():
    assert function(input) == expected
```

- [ ] **N.2 Confirm failure**

Run: `pytest tests/path/test.py::test_behavior -v`
Expect: FAIL — `NameError: function not defined`

- [ ] **N.3 Implement**

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

- [ ] **N.4 Confirm pass**

Run: `pytest tests/path/test.py::test_behavior -v`
Expect: PASS

- [ ] **N.5 Commit**

```bash
git add src/exact/path.py tests/exact/test_path.py
git commit -m "feat: add behavior"
```
````

## Review Loop

1. Dispatch plan-document-reviewer subagent (see `references/plan-document-reviewer-prompt.md`) with crafted context — never raw session history. Provide plan path and spec path.
2. Issues found: fix and re-dispatch.
3. Approved: proceed to handoff.
4. If loop exceeds 3 iterations, surface to user.

Reviewers are advisory. Explain disagreements if you believe feedback is wrong.

## Execution Handoff

After saving and committing the plan:

> "Plan saved to `docs/arsyn/plans/<filename>.md`. Two execution modes:
>
> **1. Orchestrated (recommended)** — Fresh subagent per task with review between tasks.
>
> **2. Inline** — Execute tasks sequentially in this session with checkpoint reviews.
>
> Which approach?"

- Orchestrated: invoke arsyn:orchestrating
- Inline: invoke arsyn:executing

## Gotchas

- **Vague steps** — "Add validation" is not a step. Every step contains complete, copy-pasteable code or an exact command with expected output.

From renathoaz/arsyn, MIT.

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Mar 24, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from renathoaz

Cite this page

planning skill. Agent Mart. https://agentmart.dev/skills/renathoaz-planning (last updated 2026-10-24)