Agent Passport
Generate APAI Capability Passports for arbitrary packages, including third-party ones not yet in the registry.
About
Given a package manifest or a raw package definition, produces a v0.1 Capability Passport that describes what the package can read, write, access, spend, expose, and what approvals it needs. Useful for builders who want to document their own packages before publishing to the APAI registry.
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/agent-passport for this chat. Given a package manifest or description, output a v0.1 Capability Passport. Do not infer permissions the package did not declare.
Install card source: https://apai.run/packages/agent-passport/llms.txt
Capability Passport
Reads
- ·Supplied manifest or package description
Writes
- ·Generated passport file
Accesses
- ·No network access required for generation
Spends
- ·No spend
Exposes
- ·Generated passport is local unless explicitly shared
Approvals required
- ·No approvals beyond install
Rollback
Delete generated passport file.
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.