# Plan

> Create implementation plans. Use for feature planning, system design, architecture, roadmaps.

- **Type:** Skill
- **Install:** `agentstack add skill-namtroi-agentic-base-plan`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [namtroi](https://agentstack.voostack.com/s/namtroi)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [namtroi](https://github.com/namtroi)
- **Source:** https://github.com/namtroi/agentic-base/tree/main/template/.claude/skills/plan

## Install

```sh
agentstack add skill-namtroi-agentic-base-plan
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Planning Skill

Create technical implementation plans through research, codebase analysis, and solution design.

## Workflow

1. **Research** — Understand requirements, read relevant docs/code
2. **Analyze** — Identify constraints, patterns, dependencies
3. **Design** — Propose solution with clear phases
4. **Document** — Write plan.md with frontmatter + phases

## Modes

| Flag | Mode | Description |
|------|------|-------------|
| `--auto` | Auto-detect | Analyze complexity, pick mode (default) |
| `--fast` | Fast | Skip research, minimal plan |
| `--hard` | Hard | Deep research, thorough analysis |

## Plan File Format

Every plan.md starts with YAML frontmatter:

```yaml
---
title: "{title}"
status: pending
priority: P2
effort: "{estimate}"
created: {YYYY-MM-DD}
---
```

## Phase Structure

Break plan into numbered phases:
- Each phase has clear objective, deliverables, effort estimate
- Phases are sequential with dependencies noted
- Include code snippets/pseudocode when helpful

## Rules

- DO NOT implement code — only plan
- Be concise. Sacrifice grammar for brevity.
- YAGNI, KISS, DRY always
- **Every plan MUST include:** `## Docs Impact`, `## Test Strategy`, `## Observability` sections
- List unresolved questions at end
- Output plan file path + summary when done

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [namtroi](https://github.com/namtroi)
- **Source:** [namtroi/agentic-base](https://github.com/namtroi/agentic-base)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-namtroi-agentic-base-plan
- Seller: https://agentstack.voostack.com/s/namtroi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.