# Plan Mode

> Clarify requirements and produce an implementation plan before changing

- **Type:** Skill
- **Install:** `agentstack add skill-raidriar7170-hermes-skilleval-plan-mode`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Raidriar7170](https://agentstack.voostack.com/s/raidriar7170)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Raidriar7170](https://github.com/Raidriar7170)
- **Source:** https://github.com/Raidriar7170/hermes-skilleval/tree/main/benchmarks/migrated-skills/claude-code/plan-mode

## Install

```sh
agentstack add skill-raidriar7170-hermes-skilleval-plan-mode
```

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

## About

# Plan Mode

Use when a task is broad, ambiguous, or risky enough to need a written plan before edits. Gather context, state assumptions, identify files and validation, and wait for approval when required.

## Evidence

- Task understanding.
- Step plan with validation.
- Open questions or approval checkpoint.

## Source Snapshot

Source: Hermes Claude Code orchestration guide, plan mode controls

Short excerpt used for provenance, not a full source copy.

````text
`--permission-mode ` supports `default`, `acceptEdits`, `plan`, `auto`,
`dontAsk`, and `bypassPermissions`. `/plan [description]` enters Plan mode with
auto-start for task planning. Shift+Tab cycles permission modes, including Plan, when
running interactively.
````

## Source & license

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

- **Author:** [Raidriar7170](https://github.com/Raidriar7170)
- **Source:** [Raidriar7170/hermes-skilleval](https://github.com/Raidriar7170/hermes-skilleval)
- **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-raidriar7170-hermes-skilleval-plan-mode
- Seller: https://agentstack.voostack.com/s/raidriar7170
- 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%.