AgentOps

Plugin agentops in ConcertoNotes/codex-plugins. Commands read from the repo's manifest — 1 month ago.

Skills (74)

• account-rotation

  Switch coding-agent accounts on a usage/rate limit or to spread swarm lanes. Routes by host+agent: macOS+Claude via claude-acct; Codex/Gemini and Linux/WSL via caam. Triggers: "account-rotation", "account rotation", "switch coding-agent accounts on a".

• acfs

  Use when operating ACFS flywheel health checks, init, and agent loop tooling from ~/acfs/bin/acfs.

• agent-mail

  Use when coordinating agents with Agent Mail locks, inboxes, threads, and conflict-prevention handoffs. Triggers: "agent-mail", "agent mail", "use when coordinating agents with".

• agent-native

  Make an out-of-session agent AgentOps-native with skills, the ao CLI, local cockpit proof, and CI backstop telemetry instead of runtime hooks. Triggers: "agent-native", "agent native", "make an out-of-session agent agentops-native".

• agy-headless-evidence

  Run AGY headlessly via scheduled ticks or `agy -p`, capture agentapi JSONL evidence, and validate automated AGY loops or event streams.

• agy-native

  Drive AgentOps in AGY: loop, plugins, memory, evidence, scoped worktrees.

• autodev

  Manage the PROGRAM.md/AUTODEV.md contract consumed by evolve/factory ticks. Use for loop rules, boundaries, or PROGRAM.md repair. Triggers: "manage PROGRAM.md/AUTODEV.md", "autodev loop rules", "evolve/factory tick boundaries".

• automation-shape-routing

  Front door for agent automation — decide the SHAPE (Workflow vs ATM vs skill), then hand off. Triggers: "build automation", "convert skills to workflows", "which shape".

• beads-br

  Local-first issue tracker (beads_rust) for AI agents. Use when tracking tasks, managing dependencies, finding ready work, or syncing issues to git via JSONL. Triggers: "beads-br", "beads br", "local-first issue tracker beads rust".

• beads-bv

  Graph-aware task triage with bv and br. Use when prioritizing work, finding bottlenecks, tracking dependencies, or managing local issues across projects. Triggers: "beads-bv", "beads bv", "graph-aware task triage with bv".

• beads-workflow

  Use when converting markdown plans into br beads with dependencies for implementation or swarm execution. Triggers: "beads-workflow", "beads workflow", "use when converting markdown plans".

• behavior-first-planning

  Behavior-first planning discipline — intent → Gherkin behaviors → EXECUTED-red acceptance tests → spec → acceptance-gated bead DAG. No runnable acceptance test, no bead. Triggers: "plan behavior-first", "acceptance-first planning", "give these beads runnable done-criteria".

• bootstrap

  Initialize AgentOps project files. Triggers: "initialize AgentOps", "bootstrap project files", "set up .agents scaffolding".

• cass

  Mine past agent sessions for working prompts, decisions, and patterns. Use when "what did I ask?", "find that prompt", session archaeology, or agent history. Triggers: "cass", "mine past agent sessions for", "cass skill".

• cc-hooks

  Configure Claude Code hooks (PreToolUse, PostToolUse, Stop, Notification). Fold target for the cc-* loop, subagent, and worktree-isolation skills. Triggers: "cc-hooks", "cc hooks", "configure claude code hooks pretooluse".

• codex-approval

  Use when Codex needs Fable approval through an ATM/NTM validator pane.

• codex-exec

  Use when running Codex workers or validators non-interactively through codex exec with evidence.

• compile

  Compile .agents knowledge wiki. Triggers: "compile the knowledge wiki", "build the LLM wiki", "compile .agents into the wiki".

• continuity-loop

  Own the unattended renewal spine: renewal ticks, the two-tick stall rule, escalation for NTM panes over MCP Agent Mail. Use when wiring or tuning a loop''s continuity step.

• converge

  Drive a fix→re-run-judge-panel loop to terminal agreement or a 3-consecutive-fail BLOCK via the Go `ao converge` command. Thin memo over the CLI — loop and gates live in Go. Triggers: "converge", "drive a fix re-run-judge-panel loop", "converge skill".

• converter

  Convert AgentOps skill formats. Triggers: "converter", "convert agentops skill formats.", "converter skill".

• council

  Run council.

• crank

  Run crank.

• curate

  Mine transcripts, .agents, bd, and git for skill diffs, bd updates, or rare wiki entries. Triggers: "curate skills from sessions", "mine transcripts for skill diffs", "what should be a skill".

• dcg

  Handle blocked destructive commands. Use when dcg blocks rm -rf, git reset --hard, DROP DATABASE, kubectl delete, or when configuring agent safety guardrails. Triggers: "dcg", "handle blocked destructive commands. use", "dcg skill".

• discovery

  Create dense execution packets. Fold target for brainstorm + design (goal clarification, product-fit pressure testing). Triggers: "run discovery", "shape intent as BDD", "scope a feature into an execution packet".

• doc

  Run doc.

• domain

  Canonical vocabulary for human-AI software work. Use when naming concepts, resolving terminology disputes, or establishing shared domain language across agents and docs. Triggers: "domain", "canonical vocabulary for human-ai software", "domain skill".

• dual-pane-atm

  Repeatable mixed-model ATM duel — Opus (Claude) + Codex (+AGY) panes, or an in-session variant for a one-shot one-way-door decision. Triggers: "dual pane", "Opus and Codex together", "CEP duel/build", "two-pane ATM", "collaborative ATM", "mixed-model duel", "fan out competing theses / duel it out".

• eval-outcomes

  Grade agent or model output against Outcomes for holdout-safe evals and runtime comparisons. Fold target for scenario. Triggers: "eval-outcomes", "eval outcomes", "grade agent or model output".

• evolve

  Run evolve.

• flywheel

  Check knowledge flywheel health. Triggers: "flywheel", "check knowledge flywheel health.", "flywheel skill".

• forge

  Mine transcripts into learnings. Triggers: "forge", "mine transcripts into learnings.", "forge skill".

• goals

  Run goals.

• handoff

  Run handoff.

• heal-skill

  Repair skill hygiene. Triggers: "heal-skill", "heal skill", "repair skill hygiene.".

• implement

  Run implement.

• inject

  Load relevant .agents context. Triggers: "inject context", "load .agents context", "pull decay-ranked prior knowledge".

• ntm

  Orchestrates NTM tmux agent swarms and robot APIs. Use when spawning/sending panes, reading robot state, triaging work, locks/mail, safety, pipelines, serve, or NTM errors. Triggers: "ntm", "orchestrates ntm tmux agent swarms", "ntm skill".

• operationalize

  Distill context (research, recon, learnings) into evidence-anchored rules routed to automation shapes. Use when a finished artifact should become skills, gates, or beads.

• orchestrate

  Out-of-session orchestration instrument lane: route, preflight, verify before human atm/am procedure. Triggers: "orchestrate out-of-session", "route + preflight + verify a run", "orchestration preflight".

• perf

  Profile and optimize hotspots. Triggers: "perf", "profile and optimize hotspots.", "perf skill".

• plan

  Run plan.

• post-mortem

  Run post mortem.

• pr-prep

  Run pr prep.

• pre-land-refuters

  Dispatch fresh-context refuters (model-agnostic; multi-model opt-in) to attack a completion claim at the shared-trunk pawl before landing. Triggers: pre-land validation, refute.

• pre-mortem

  Run pre mortem.

• product

  Create or refine PRODUCT.md. Triggers: "product", "create or refine product.md.", "product skill".

• push

  Run push.

• rch

  Use when offloading slow builds to remote workers or recovering RCH worker, hook, SSH, sync, or disk issues. Triggers: "rch", "use when offloading slow builds", "rch skill".

• reality-check

  Mid-epic drift audit: code is ground truth; README/PRODUCT/plan are the measuring stick. Use when a wave boundary lands and bead counts look healthy but value feels absent.

• recover

  Run recover.

• red-team

  Probe docs and skills. Use when: adversarially probing a doc, skill, plan, or claim for weaknesses, gaps, or unstated assumptions before it ships.

• refactor

  Execute safe refactors. Triggers: "refactor", "execute safe refactors.", "refactor skill".

• release

  Run release.

• research

  Run research.

• reverse-engineer

  Reverse-engineer an external system you own or are authorized to analyze — repo, binary, or product — into a mechanically-verifiable feature inventory + spec set, then a steal-map (have/gap/steal/park/reject) onto our own surfaces. Use when evaluating a competitor, upstream, fork, or reference tool

• review

  Review diffs for risk, find mocks, scan for bugs, audit codebases. Fold target for bug-hunt, codebase-audit, and ubs. Triggers: "review", "review diffs for risk find", "review skill".

• rpi

  Run RPI.

• sbh

  Disk-pressure defense for AI coding workloads. Use when: disk full, low space, ballast, cleanup, scan artifacts, emergency, sbh daemon, sbh status.

• scaffold

  Create project, component, or boilerplate scaffolds. Use when starting a new project, module, or component, generating boilerplate, or stamping a repeatable file structure. Triggers: "scaffold", "create project component or boilerplate", "scaffold skill".

• scope

  Hard-block edits outside declared frozen directories and protect paths during risky changes. Triggers: "scope", "hard-block edits outside declared frozen", "scope skill".

• security

  Run security.

• shared

  Shared AgentOps skill contracts. Triggers: "shared", "shared agentops skill contracts.", "shared skill".

• skill-auditor

  Audit SKILL.md files against the AgentOps template and readiness checks. Use for quality reviews or template compliance.

• skill-builder

  Scaffold or absorb new SKILL.md files against the unified AgentOps template. Triggers: "create a skill", "scaffold skill", "absorb external skill", "new skill".

• standards

  Provide repo coding standards. Triggers: "standards", "provide repo coding standards.", "standards skill".

• status

  Run status.

• swarm

  Run swarm.

• toil-mining

  Mine usage history (cass, rtk, shell) for repeated toil, score frequency x pain, emit ranked candidates for automation-shape-routing. Use when rituals repeat by hand.

• using-atm

  Use ATM as the out-of-session substrate: spawn Claude/Codex panes running /rpi and /evolve over a bead queue, then tend the swarm to convergence. Triggers: "use ATM as the out-of-session substrate", "spawn atm panes over a bead queue", "tend an unattended swarm".

• validate

  Produce PASS/WARN/FAIL verdicts for artifacts, plans, code, PRs, or gates — including quick readiness/sanity checks before commit (absorbs vibe) and completion audits. Triggers: "validate an artifact", "PASS/WARN/FAIL verdict", "readiness / completion audit".

• vibing-with-ntm

  Use when tending NTM agent swarms, unsticking panes, handling rate limits, or coordinating convergence.

• workflow-builder

  Scaffold a new Claude Workflow script — deterministic multi-agent orchestration. Triggers: "build a workflow", "create a workflow", "scaffold workflow", "author a workflow".

Similar plugins