Goal Framing

Before Claude starts work, this drops a thin boundary frame: what you're asking for, what success looks like, where to stop, and what's out of scope. You trigger it with /aegis-goal or "Aegis goal:" when you want that explicit contract up front. It's not for tiny edits or quick questions. It's for the moment you realize you need a stop condition before Claude rewrites your entire auth system to fix one refresh bug. The frame is compact, routes you to the right workflow (TDD, debugging, planning), then execution continues in the same turn unless you asked to pause. It's opt-in guardrails, not ceremony.

GitHub stars: 492
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add ganyuanran/aegis --skill goal-framing --agent claude-code

Installs into .claude/skills of the current project.

Files

Aegis Goal Framing

Use this skill to create a thin goal frame before execution. It is opt-in and boundary-setting only.

Do not use it for tiny edits, one-command checks, or ordinary fast-path Q&A unless the user explicitly asks for /aegis-goal or Aegis goal:.

Authority Boundary

Current owner:

Method Pack task framing

Not owned here:

authoritative GateDecision
final evidence sufficiency
final completion authority is not owned here
host daemon / automatic stop enforcement

Input Forms

Treat these as equivalent:

/aegis-goal <task description>
Aegis goal: <task description>
"Define the goal / stop condition before we start"

Slash commands are optional host shortcuts. The natural-language form is the portable fallback.

Example:

Aegis goal: Fix the auth refresh bug without rewriting the auth system.

Output

Produce the smallest useful frame, then continue into the routed workflow in the same turn.

TaskIntentDraft:
- Requested outcome:
- Goal:
- Success evidence:
- Stop condition:
- Non-goals:
- Constraints:
- Scope:
- Risk hints:
- Aegis Visibility:
- Route:
- Next:

Default behavior:

SKILL.md on GitHub