# Do Subtasks

> Executes exactly one approved subtask at a time, then returns a conventional commit message suggestion for human review and commit. Use when the user wants strict one-task-at-a-time implementation with manual commit control and explicit "next task" prompts.

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

## Install

```sh
agentstack add skill-rediche-skills-do-subtasks
```

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

## About

# Do Subtasks

## Workflow

1. Implement exactly one subtask at a time.
2. Do not begin additional subtasks in the same response.
3. When that subtask is complete, stop implementation and return only a conventional commit message suggestion.
4. The commit message must have no scope and no body.
5. The human reviews and commits; do not commit automatically.
6. Wait for the human to tell you to move to the next task.

## Next-task behavior

- When the human tells you to continue, begin work immediately.
- Do not ask for confirmation.
- Do not restate or confirm which task you are starting.
- If the human asks for the next subtask and there are no remaining agreed-upon subtasks, do not implement anything.
- In that case, tell the human that all agreed-upon subtasks have already been implemented.

## Output Rules

- At subtask completion, output a single-line conventional commit message only.
- Allowed format: `: `
- No scope section like `feat(api): ...`
- No body text, bullets, or extra commentary.

## Source & license

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

- **Author:** [rediche](https://github.com/rediche)
- **Source:** [rediche/skills](https://github.com/rediche/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-rediche-skills-do-subtasks
- Seller: https://agentstack.voostack.com/s/rediche
- 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%.