agentops instructions

AgentOps-AI/agentops

Cursor rule Cursor

All tasks related to updating frontend components, CSS, and general styling.

AgentOps-AI/agentops

Cursor rule Cursor

No need to run the app. It's already up. i.e. no bun dev or bun run build.

slaveOftime/open-relay

Skill Claude CodeCodex

Use when building a web app/api to present rich output or interactive experiences to users.

slaveOftime/open-relay

Skill Claude CodeCodex

Use when starting a long-running or interactive CLI command with oly, especially when it may need later input, should be detachable, or should keep durable logs for supervision and resume.

vpeetla-ai/aegisai-enterprise-agent-platform

Skill Claude CodeCodexCursor

Integrate AegisAI gateway before tool side effects (notify, publish, deploy). Use when adding Slack/Telegram/WhatsApp notify, content publish, or any irreversible external action in VAP, AegisLoop, or ai-content-factory.

vpeetla-ai/aegisai-enterprise-agent-platform

Skill Claude CodeCodexCursor

Apply Karpathy agentic engineering discipline: think before coding, minimal diffs, surgical changes, test-verified completion. Use for any implementation task in vpeetla-ai repos when quality bar matters.

vpeetla-ai/aegisai-enterprise-agent-platform

Skill Claude CodeCodexCursor

Build or modify LangGraph StateGraph agents in vpeetla-ai repos: typed state, nodes, conditional edges, MemorySaver, interruptbefore HITL. Use when adding orchestrators, coding loops, or multi-agent graphs.

vpeetla-ai/aegisai-enterprise-agent-platform

Instructions file CodexOpenCode

AGENTS.md instructions for vpeetla-ai/aegisai-enterprise-agent-platform, covering agent instructions — vpeetla-ai org, agentic engineering (karpathy), stack awareness, repo conventions and skills repo.

MLOps-Courses/agentops-open-course

Instructions file CodexOpenCode

Instructions for MLOps-Courses/agentops-open-course, covering agents.md, repository purpose, course invariants, open-source boundary and pinned contracts.

MLOps-Courses/agentops-open-course

Skill Claude CodeCodex

Build offline checks and model-backed evidence for an LLM agent — trajectory scoring, groundedness/citation coverage, a run-over-run token drift warning, and side-by-side prompt A/B. Use when a prompt or model change might silently regress behavior, cost, or grounding, or when "it looked fine" is your only test.

MLOps-Courses/agentops-open-course

Skill Claude CodeCodex

Add layered safety to an LLM agent — PII redaction, prompt-injection spotlighting, human approval on state-changing tools, and a configuration-controlled write kill-switch. Use when an agent can take consequential actions, when tool output could carry injected instructions, or when user data must be redacted before it…

MLOps-Courses/agentops-open-course

Skill Claude CodeCodex

Index of the AgentOps patterns for operating LLM agents in production — telemetry, guardrails, resilience, evaluation, token budgets, least privilege, and incident response — with a pointer to the full open-source course. Use when you want an overview of how the AgentOps skills fit together, or where to start…

jtprogru/bear-skills

Plugin Claude Code

A plugin collection containing rules, skills, and agents for several areas, including Obsidian note-taking, Git workflows, site reliability, Kubernetes, content production, and agent operations. A plugin is a package that adds capabilities to a coding agent.

jtprogru/bear-skills

Instructions file CodexOpenCode

Repository instructions explaining bear-skills, a collection of Claude Code rules, skills, and agents organized into separate domains.

jtprogru/bear-skills

Agent

A specialised agent for keeping a personal knowledge base in Obsidian, a note-taking application. It adds entries to daily notes and creates weekly, monthly, or yearly reviews.

jtprogru/bear-skills

Agent

An Obsidian knowledge-base maintenance agent focused on keeping linked notes and maps of content organised. Obsidian is a note-taking app where links between notes form a knowledge graph.

jtprogru/bear-skills

Agent

A specialized agent for reviewing and enriching one Obsidian note at a time. Obsidian is a note-taking app that stores linked Markdown files; this agent checks note metadata, contradictions, weak reasoning, and missing links or context.

jtprogru/bear-skills

Command

A diagnostic command for checking why a bear-skills add-on is not being triggered. It examines domain requirements, broken links, installation channels, name conflicts, and overlapping triggers.

jtprogru/bear-skills

Command

A command that shows which bear-skills add-ons have been triggered and which have not. It can limit the report to a chosen time period.

jtprogru/bear-skills

Command

A command that reports the current state of the bear-skills collection, including its domains, skills, installation status, and requirements. A domain groups related skills.

jtprogru/bear-skills

Skill Claude CodeCodex

A writing skill for making Russian text sound more natural and less like it was generated by an AI system.

jtprogru/bear-skills

Skill Claude CodeCodex

A tool for creating a postmortem, a written review of what happened during an incident and how to prevent a repeat. It uses the srekit command-line tool to create sections such as impact, timeline, root cause, and action items from the current conversation.

jtprogru/bear-skills

Skill Claude CodeCodex

A workflow for creating operational runbooks with the srekit tool. A runbook is a step-by-step guide for handling a known alert or service failure, with sections for symptoms, diagnosis, mitigation, and verification.

jtprogru/bear-skills

Hook

Runs when a session starts, executing bear-activate.js via node. From jtprogru/bear-skills.