agentops

AgentOps

AgentOps is the operating loop a coding agent follows: one intent, one bounded build, one fresh judge, one durable verdict. It also ships skills to orchestrate multi-agent systems. For contested calls, opt into council (independent judges) or idea-genie duel mode (sealed perspectives before Plan).

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

Quickstart

npx skills@latest add boshu2/agentops --all -g

One command, every coding agent — npx skills installs the corpus into all your agents at once. The loop runs as skills inside your coding agent (Claude Code, Codex, Cursor, …): type /rpi — or ask for plan, implement, validate, learn by name — in that agent's chat. No other runtime is required.

Plugins (Claude Code / Codex)

Prefer a managed bundle that updates with the release:

# Claude Code
claude plugin marketplace add boshu2/agentops
claude plugin install agentops@agentops-marketplace

# Codex
codex plugin marketplace add boshu2/agentops
codex plugin add agentops@agentops-marketplace

Three install paths:

• npx / skills.sh — universal; copies skills you can edit.
• Plugins — a read-only bundle that stays current with the repo.
• Checkout + ao skills link — source-tracked symlinks for contributors (see Install and day-2 operations).

Admission-control hooks (on by default)

AgentOps ships a PreToolUse policy dispatcher — deterministic guards that block a small set of known-destructive commands (staging the private bead ledger, hand-editing the hash-chained provenance ledger, overwriting installed skill copies) and route you to the correct tool instead. Silent on every clean call; every block is one line.

• Claude Code plugin installs: active automatically — nothing to run.
• npx / skills.sh copies: run ~/.claude/skills/cc-hooks/scripts/install-hooks.sh once.
• git clone / brew: run scripts/install-policy-dispatch.sh once.

Disable anytime (/plugin disable agentops, or remove the two PreToolUse matchers from settings). Policy list and design: skills/cc-hooks/SKILL.md.

Remove with your runtime's plugin uninstall, or delete the linked skill directories.

Intent lives in a bead

Beads is the preferred tracker (optional — brew install beads). Plan writes BDD acceptance and DDD ubiquitous language into the bead; Implement builds against it; Validate judges a hashed snapshot under .agents/ao/intents/sha256/. No beads? Plan shapes the caller's issue or chat text and the runtime snapshots those bytes the same way.

validate must run in a fresh context (not the author session). Same model or a different one — both are supported.

Multi-agent systems

The default loop is one agent, one writer. When you need a fleet, swarm, agent-native, ntm, and using-gc orchestrate multi-agent work. They dispatch; they do not own the verdict.

The Gas City pack (preview)

Gas City runs teams of coding agents as long-lived, supervised sessions. The pack in deploy/gc/ stands up a "city" that runs the AgentOps loop end to end: workers implement in isolated worktrees, a fresh agent validates, a refiner merges to your repo's main branch. The installer fetches official checksummed Gas City and Beads binaries; you build nothing.

You drive it by talking to one agent, the Mayor: attach to its session in your terminal, or let another agent steer it.

deploy/gc/invoke.sh --city <city> create "task title"       # define work
deploy/gc/invoke.sh --city <city> feed <bead-id>            # hand it to the city
deploy/gc/invoke.sh --city <city> mayor tell "dispatch <bead-id>"

The using-gc skill is the operating manual, including the four observability layers and what to do when they disagree. Preview: pinned to official Gas City v1.3.5, which carries three upstream defects we found and filed; the label comes off at the next official pin bump. Setup and details: deploy/gc/README.md and the v3.3.0 release notes.

AgentOps already borrows heavily from that ecosystem. Two stacks people run around the same loop:

• Gas City — orchestration-builder for multi-agent coding workflows
• Jeffrey Emanuel's Agentic Coding Flywheel — coordinated multi-agent tooling (mail, beads, NTM, and friends)

Optional: ao CLI