AgentOps 3.3: The Cathedral Cut

AgentOps 3.2 tried to make validation inescapable by owning the path around it. That turned a useful trust boundary into a control plane: retries, queues, work claims, Git admission, landing, closure, budgets, and delivery accumulated around one fresh-context review. The result was correct-looking gridlock. Validation often took longer than implementation, and moving main repeatedly invalidated expensive proof.

Version 3.3 removes that control plane.

RPI -> Plan -> Implement -> fresh Validate -> report and stop

What AgentOps owns

• one behavior with explicit normal and edge acceptance;
• one bounded implementation experiment;
• deterministic identity for the exact candidate content;
• one independent semantic judgment from fresh context;
• one durable, content-addressed verdict with checked and unchecked scope.

What the caller owns

The caller decides whether to revise, retry, re-plan, schedule, assign, commit, push, merge, release, or abandon the candidate. Existing repository Git and CI policy remains authoritative. Optional councils, genies, NTM, Agent Mail, Gas City, and swarm adapters may help, but none can change the core sequence or strengthen a verdict.

Skills

The load-bearing core is rpi, plan, implement, and validate. learn is an optional later analysis of verdict collections. Discovery, behavior-first planning, and goal design were folded into Plan. Crank and controller/delivery skills were removed. Canonical mortem names are premortem and postmortem.

The corpus is 48 metadata-owned skills; beyond the core and learn, the rest are specialist strategies and optional adapters. Their metadata is the source for the generated registry, router, graph, counts, and runtime projections. The release audit reads every canonical SKILL.md and runs the strict deep auditor over the entire corpus.

CLI

The retained ao CLI supplies ordinary deterministic checks, inspection, generic provenance records, goal measurement, session handoff, and skill discovery/linking. Removed lifecycle commands have inert, non-mutating tombstones for this release. Semantic validation lives in the Validate skill; ao gate check proves deterministic repository facts only.

Installation

Three supported paths:

• npx skills add boshu2/agentops --all -g — universal; installs the skills into all your coding agents at once.
• Runtime plugins for Claude Code and Codex — managed bundles that update with the release.
• One canonical checkout plus ao skills link — source-tracked symlinks for users who edit skills or contribute. The command links that checkout into the portable skill root and every detected runtime without overwriting foreign skills.

The 3.x curl installer scripts are refusing tombstones. See Install and day-2 operations and the migration guide.