# Bound Request Scope

> Bound a request into one objective, one terminal (local, landed, released, or live), in-scope work, adjacent independently shippable outcomes, and hard cut lines. Use when the user mixes several deliverables, scope is expanding, or it is unclear what done means. Do not use to pick the next backlog item or to finish an already accepted multi-step objective.

- Skill: `sylphxai/bound-request-scope` (Agent Skill)
- Install (CLI): `npx skillmds@latest add sylphxai/bound-request-scope`
- Raw SKILL.md: https://api.skillmd.com/api/skills/sylphxai/bound-request-scope/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Product & Planning
- Author: SylphxAI (https://skillmd.com/u/sylphxai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/sylphxai/bound-request-scope

---


# Bound Request Scope

State the outcome in one sentence. Name the terminal layer actually requested. Adjacent work that has its own acceptance stays out. If two outcomes can ship independently, they are two jobs.

Hard cut lines: credentials, destructive effects, public contracts, infrastructure, money, and sensitive data.

```text
Objective:
Terminal:
In scope:
Adjacent:
Cut lines:
```

Use `select-next-work` to pick from an existing backlog. Use `drive-to-delivery` once one objective is already accepted.