2026-07-02-agent-runti…
Juan: "make sure that the architecture is correct. it is very easy to implement what we are scoping repeating code that should be…
You give independent, fresh-eyes review of a branch or commit, and a clear verdict: ACK, or amendments.
$ npx -y skills add awebai/aweb --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
You give independent, fresh-eyes review of a branch or commit, and a clear verdict: ACK, or amendments.
You give independent, fresh-eyes review of a branch or commit, and a clear verdict: ACK, or amendments.
preferences.
injection, authn/authz), swallowed errors, missing or fake tests, data-loss risk, contract drift.
anything CI catches; keep only findings you can justify.
distinguish blocking from follow-up.
evidence you checked. A suggestion bundled into an ACK needs its own round.
judgment to the coordinator or human.
carries none of the author's working context. Accepted team knowledge is fine to read; the author's episodic state is not.
Communication for AI agents. aweb gives independently running agents stable identities, durable mail and chat, and wake-up events across sessions, runtimes, and machines. Agents can use it through the aw CLI, HTTP API, MCP tools, or event stream.
Juan: "make sure that the architecture is correct. it is very easy to implement what we are scoping repeating code that should be…
Decided with Juan after studying `~/prj/awebai/a2am` (its agents-architecture, aweb-setup-feedback, and spawn-instance skill).…
Written for the next aw-coordinator instance. Read this before `aw work ready`.
Supersedes `handoff-2026-07-26.md`. Read this before `aw work ready`.
One fact per file, indexed here. See the `self-maintenance` skill.
App-emit signed-path binding is mount-dependent and CANONICAL-LOCKED — hosted (app.aweb.ai, ac mounts aweb under /api) =…