Plugin Claude Code
Plugin marketplace listing 1 plugin: agentops.
Plugin Claude Code
Plugin marketplace listing 1 plugin: agentops.
Plugin Claude Code
The operations layer for agentic engineering: portable skills and evidence contracts connecting intent, coding agents, software factories, and independent judgment.
Instructions file CodexOpenCode
Instructions for boshu2/agentops, covering agentops operating contract, repository map and mechanics, authority and trust, honest work and anti-ceremony and runtime floor.
Instructions file
Instructions for boshu2/agentops, a project described as: The operations layer for agentic engineering — portable skills and contracts connecting intent, agents, software factories, and independent judgment.
Agent
Expert code review specialist. Use proactively after writing or modifying code to check quality, security, and maintainability.
Agent
Deep codebase exploration and analysis. Use for understanding code architecture, finding patterns, and gathering context before making changes.
Hook
Runs before the agent uses a tool for Bash, Edit and Write tool calls, executing policy-dispatch.sh (2 commands). From boshu2/agentops.
Agent
Verify a worker's evidence from a separate AGY context. Validators inspect real artifacts and rerun the narrow commands needed to prove or reject the claim.
Agent
Use the AgentOps loop contracts to claim ready work, make scoped changes, and produce durable evidence. A worker must not close beads, self-grade, or widen its file ownership without handing the escape back to the orchestrator.
Skill Claude CodeCodex
Switch a caller-selected coding-agent account and report the observed identity. Triggers: "switch account", "rotate coding-agent account".
Skill Claude CodeCodex
Use Agent Mail as an optional messaging and file-reservation adapter for explicitly coordinated writers. Triggers: "coordinate writers", "reserve files".
Skill Claude CodeCodex
Operate explicit orchestrator, implementer, validator, and scribe roles through a caller-selected agent runtime. Triggers: "agent-native factory", "role-shaped agent panes", "persistent workers".
Skill Claude CodeCodex
Use an explicitly selected AGY runtime for one provided packet or fresh validator context. Triggers: "agy", "antigravity", "AGY evidence".
Skill Claude CodeCodex
Guard outcome work against process overhead. Triggers: RPI pre-Plan guard; explicit "full anti-ceremony audit" requests.
Skill Claude CodeCodex
Front door for agent automation: choose inline, bounded fanout, reusable skill/workflow/gate, persistent agent-native workers, or explicit Gas City. Triggers: "build automation", "which orchestration shape", "should this use NTM".
Skill Claude CodeCodex
Initialize explicitly requested, missing AgentOps documentation and optional verdict storage without taking over repository workflow. Triggers: "bootstrap AgentOps", "initialize AgentOps docs".
Skill Claude CodeCodex
Mine past agent sessions for working prompts, decisions, and patterns (session archaeology). Triggers: "cass", "mine past agent sessions for", "cass skill".
Skill Claude CodeCodex
Configure default Claude Code enforcement hooks and opt-in guard recipes. Triggers: "cc-hooks", "configure Claude Code hooks", "install hooks".
Skill Claude CodeCodex
Reconstruct a repository as cited entry-to-test flows and bounded claims. Triggers: "codebase recon", "trace this codebase", "repository audit", "refresh the prior recon".
Skill Claude CodeCodex
Run one caller-supplied Codex command non-interactively and capture evidence. Triggers: "run Codex headless", "capture Codex evidence".
Skill Claude CodeCodex
Convert AgentOps skill formats. Triggers: "converter", "convert agentops skill formats.", "converter skill".
Skill Claude CodeCodex
Collect independent perspectives for an explicitly high-stakes or contested judgment. Triggers: "council", "multi-judge review", "independent perspectives".
Skill Claude CodeCodex
Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments toward one larger outcome. Triggers: "craft a goal prompt", "mayor goal", "goal-runner prompt", "lint this goal", "is this goal safe". (Shaping one experiment's intent routes to plan.).
Skill Claude CodeCodex
Handle blocked destructive commands and configure agent safety guardrails. Triggers: "dcg", "handle a DCG block", "configure agent safety guardrails".