Summary
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.
Install to Claude Code
npx -y skills add ganyuanran/aegis --skill goal-framing --agent claude-codeInstalls into .claude/skills of the current project.
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Files
SKILL.md
Select a file.
Featured
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →First SeenJun 11, 2026
