# Plan Compass

> >-

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

## Install

```sh
agentstack add skill-softcane-human-state-skills-plan-compass
```

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

## About

# Plan Compass

Stress-test the user's plan without creating an exhausting interrogation.

## Core Loop

Ask exactly one question at a time.

Each question must include:

1. The progress label.
2. The question.
3. Why this matters in one sentence.
4. Your recommended answer.
5. Two or three concrete answer choices.
6. A suggested default if the user is unsure.

Use this shape:

```text
Decision 2 of 6: Data ownership

Question: Who owns the saved draft?

Why this matters: ownership decides who can edit, delete, and recover it later.

Recommended answer: The user owns the draft.

Choices:
- A: User owns it.
- B: Team owns it.
- C: Project owns it.

Default: A.
```

## Interaction Rules

- Do not call the process "grilling" unless the user uses that word first.
- Keep questions short and specific.
- Do not ask broad open-ended questions unless unavoidable.
- Do not ask multiple questions in one response.
- Do not require the user to hold previous answers in memory.
- Restate only the current decision and the immediate consequence.
- Prefer examples over abstract categories.
- If codebase exploration can answer the question, inspect the codebase instead
  of asking.
- If the user seems stuck, narrow the decision instead of explaining more.
- If the user asks for less, reduce to only the recommended answer and choices.

## Progress Format

Use this format:

```text
Decision 2 of 6: Data ownership
```

Choose the total decision count conservatively. Prefer 4 to 6 decisions for a
normal plan. Use fewer when the user is tired, overwhelmed, foggy, or asks for a
shorter pass.

## Stop Conditions

Pause the decision walkthrough when:

- The next decision depends on missing information.
- The user has answered enough to produce a useful plan.
- The user says they are overwhelmed, tired, foggy, or done.

When pausing, summarize only:

- Decisions made.
- Open decisions.
- Next useful action.

## Source & license

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

- **Author:** [softcane](https://github.com/softcane)
- **Source:** [softcane/human-state-skills](https://github.com/softcane/human-state-skills)
- **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-softcane-human-state-skills-plan-compass
- Seller: https://agentstack.voostack.com/s/softcane
- 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%.