agent-native

name	agent-native
description	Make an out-of-session Claude (Managed Agent or Agent SDK loop) AgentOps-native — via skills + the ao CLI + CI, not hooks.
skill_api_version	1
practices	["continuous-delivery","ddd"]
hexagonal_role	supporting
consumes	["standards","converter","validation"]
produces	["docs/contracts/agent-runtime-profile.md"]
context	{"window":"fork","intent":{"mode":"task"},"sections":{"exclude":["HISTORY"]},"intel_scope":"topic"}
metadata	{"tier":"meta","dependencies":["standards","converter"],"stability":"experimental"}
output_contract	An AgentOps-native Agent definition (skills + ao tool surface) graded by the same CI gate as interactive work

/agent-native — Make Out-of-Session Agents AgentOps-Native (Hookless)

Run a Claude loop outside an interactive Claude Code / Codex session — an Anthropic Managed Agent, an Agent SDK loop, or a self-hosted sandbox job — and keep it under the same AgentOps guardrails. The old reflex ("port the ~50 marketplace hooks into the new runtime") is wrong for AgentOps 3.0. This skill is the hookless reframe.

Overview

AgentOps 3.0 is hookless. Guardrails come from three things, never hooks:

1. Skills — skills/<name>/SKILL.md progressive-disclosure contracts (standards, behavioral-discipline, council, validation, trace, provenance).
2. The ao CLI — the deterministic tool surface (ao session bootstrap, ao inject, ao corpus inject --query, ao validate, ao goals measure) plus the standards skill loaded into the agent's instructions.
3. CI as the authoritative gate — .github/workflows/validate.yml runs the standards/scenario checks as CI jobs, NOT as a PreToolUse hook.

So an out-of-session agent becomes AgentOps-native by: (a) loading AgentOps skills into the Agent definition, (b) exposing the ao CLI as a callable tool (MCP or shell-tool) so the agent can ao session bootstrap / ao inject / ao validate itself, and (c) running the same CI-style validation gate on its outputs before the work is accepted. The Agent SDK's own hooks become an optional thin adapter for teams wanting in-loop interception — never the primary mechanism.

Mechanism status (planned, not yet shipped). This skill is the doctrine layer and lands first; the two concrete commands it names — ao agent bundle (ag-jspr) and ao mcp serve (ag-higd) — are open, ready beads under epic ag-7s9fo, not yet in the live CLI. The ao session bootstrap / ao inject / ao corpus inject / ao validate / ao goals measure commands the bundled agent calls are real today. When ag-jspr and ag-higd land, remove this skill's entry from scripts/skill-body-refs-allowlist.txt.