By opscompanion
OpsCompanion tools for Claude Code — persistent team memory, org context, session history
Load org, user, integration, and workspace context to ground the conversation. Use at session start or when the user asks about their org/team/environment context.
Set up OpsCompanion with your API key and org configuration. Use when the user says "set up opscompanion", "configure opscompanion", or when any other opscompanion skill reports it's not configured.
Search logs and traces, or run a live tail, when the user asks about current system behavior, incidents, errors, or recent runtime activity.
Store new decisions, discoveries, or knowledge for future recall. Use when the user asks to remember something or when significant decisions emerge during a conversation.
Search stored organization knowledge or user memory. Use when the user asks "what did we decide about...", "do you remember...", or needs to look up a past decision.
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Agent-agnostic skills for OpsCompanion — persistent team memory across agent sessions.
Install the CLI, then install for your agent:
brew install opscompanion/opc/opc
# For Claude Code
opc install --agent claude
# For Codex
opc install --agent codex
opc install handles everything: downloads skills, registers plugins/hooks, and creates a mock config if none exists so you can demo immediately.
| Skill | Trigger | What it does |
|---|---|---|
opscompanion-init | "set up opscompanion" | Configure API key, install hooks |
opscompanion-context | "show my org context" | Load org/user/integration context |
opscompanion-search | "what did we decide about..." | Search organization knowledge and user memory |
opscompanion-observability | "what errors are we seeing?" | Search logs, traces, and run live tails |
opscompanion-remember | "remember this decision" | Save decisions for future search |
--agent ContractEvery opc command accepts --agent <name> to normalize behavior across runtimes:
opc --agent claude search "auth migration" # from Claude Code
opc --agent codex search "auth migration" # from Codex
opc search "auth migration" # human mode (auto-detect)
The --agent flag controls:
CLAUDE_SESSION_ID, CODEX_SESSION_ID, etc.).claude/settings.local.json vs .codex/hooks.json)Skills and hooks generated by opc install automatically include the correct --agent flag.
Set api_key to mock-key in ~/.config/opscompanion/config.json (or set OPSCOMPANION_MOCK=true) to use realistic mock responses without a backend. opc install does this automatically if no config exists.
opscompanion-skills/
├── .claude-plugin/
│ └── marketplace.json # Plugin registry
├── plugins/opscompanion/ # Claude Code plugin
│ ├── .claude-plugin/
│ │ └── plugin.json # Plugin metadata
│ ├── hooks/
│ │ ├── hooks.json # Auto-approve opc commands
│ │ └── auto-approve-opc.sh # Hook script
│ └── skills/
│ ├── opscompanion-init/ # Setup skill
│ ├── opscompanion-context/ # Org context skill
│ ├── opscompanion-search/ # Knowledge search skill
│ ├── opscompanion-observability/ # Logs, traces, and live tail skill
│ └── opscompanion-remember/# Memory save skill
├── agents/skills/ # Codex agent skills
│ ├── opscompanion-init/
│ ├── opscompanion-context/
│ ├── opscompanion-search/
│ ├── opscompanion-observability/
│ └── opscompanion-remember/
└── README.md
npx claudepluginhub opscompanion/opscompanion-skills --plugin opscompanionThe operational layer for coding agents. Bookkeeping, validation, and flows that compound knowledge between sessions.
Persistent memory across sessions. Learns preferences, conventions, and corrections automatically.
Structured operational documentation and runbook patterns for human operators. Helps create clear, actionable runbooks for troubleshooting, incident response, and maintenance.
Plugin-first Claude Code workflows with planning, CI/CD debugging, reusable agents, TODOs, and MCP safety policies.
Claude Copilot — a framework of specialized agents, skills, commands, and hooks that give Claude persistent memory, expert methodology, and task tracking. Agents cover architecture (ta), engineering (me), QA (qa), service design (sd), DevOps (do), documentation (doc), and knowledge onboarding (kc).
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer