Prompt Preflight Starter
Generic bounded-prompt protocol with score gate and operator controls. Reference implementation for the APAI prompt-preflight pattern.
About
Wraps any user request in a bounded prompt template, scores it for risk, applies 1/3/0 operator controls (continue/revise/stop), and writes a transcript receipt. Independent of any specific upstream product; meant as a copy-and-modify starting point for teams who want a basic preflight layer before sending a request to a paid LLM.
Native install
For environments with file or shell access (Codex, Claude Code, Gemini CLI, Cursor, local CLI). v0.1: the apai CLI is a scaffold; real install behavior lands in Phase 1.
The apai CLI is a TypeScript scaffold at v0.1. See /honest-status for the full shipped vs stubbed list.
Prompt install
Hosted chat apps (ChatGPT, Claude, Gemini, Grok) cannot silently install software. Paste the snippet below into the chat to load the package protocol for the current conversation only.
Paste this into any LLM that does not have shell access to your machine - chatgpt.com, claude.ai, gemini.google.com, grok.com - and the model will load the Capability Passport and apply the package protocol. If you are using Claude Code, Codex, Cursor, Gemini CLI, or another tool-enabled agent, use apai install instead - it produces a durable install receipt.
Install https://apai.run/packages/prompt-preflight-starter for this chat. Load the capability passport, apply the prompt-preflight protocol, and report what changed. Do not call paid APIs, request secrets, or perform destructive actions without explicit approval.
Install card source: https://apai.run/packages/prompt-preflight-starter/llms.txt
Capability Passport
Reads
- ·Current user prompt or supplied task only
Writes
- ·Optional local transcript or generated bounded prompt
Accesses
- ·No secrets required
- ·No paid API required
Spends
- ·No direct spend by default
Exposes
- ·No prompt collection by default
Approvals required
- ·Human approval required before destructive actions, external sends, purchases, deploys, or credential use
Rollback
Remove installed adapter files or stop using the prompt protocol in hosted chat. No persistent state.
Scanner
heuristic-stub-v0 means the v0.1 scanner (13 suspicious-pattern regex checks + Unicode format-character detection) found nothing. It does NOT mean the package is certified safe. Real prompt-injection, OAuth-scope, and dependency scanning lands in Phase 5. See honest status.