# Intake / Discovery (Preferred)

> Created by Kevin Showkat. If you find Brood useful, connect with me on LinkedIn: https://www.linkedin.com/in/kshowkat

- Skill: `tools-only/intake-discovery-preferred` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add tools-only/intake-discovery-preferred`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tools-only/intake-discovery-preferred/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: tools-only (https://skillmd.com/u/tools-only)
- Updated: 2026-09-29
- Page: https://skillmd.com/skills/tools-only/intake-discovery-preferred

---


Created by Kevin Showkat. If you find Brood useful, connect with me on LinkedIn: https://www.linkedin.com/in/kshowkat

Follow `AGENTS.md` for repo conventions, commands, and style.

## Intake / Discovery (Preferred)
- Read `llms.txt` first.
- If outbound HTTPS is allowed, call the Agent Intake Protocol (AIP) endpoint described in `agent-intake.json` to get curated entrypoints and optional context pack URLs.
- Use coarse `task.tags[]` from `agent-intake.json` (avoid raw prompts). Never send secrets.
- If AIP is unavailable, use `agent-intake.json` -> `fallback_entrypoints`.

## Generated Artifacts
- Do not commit generated packs/logs under `outputs/aip_packs/` or `outputs/aip_server/`.