Agent memory discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
Skills for your AI
7,816 skills your AI can use
Agent messaging
Sends and receives cryptographically signed messages between AI agents using the AMP CLI, covering identity setup, sending, inbox checks, reading, replying, deleting, and status. Use when the user asks to set up agent messaging, send or reply to another agent,
Agent organizer
Decomposes projects into subtasks, maps them to available agents, designs coordination workflows, assembles teams, and monitors risks. Use when a complex project needs task breakdown, agent-to-task matching, workflow design, team assembly, or risk monitoring.
Agent overview
Orchestrates a multi-agent research team to produce academic-quality reports, from query clarification through brief, parallel research, synthesis, and draft delivery. Use when the user requests a research report, literature review, or multi-source investigati
Agent performance analysis assistant
Analyzes call center agent performance from calls, transcripts, metrics, and complaints to produce quality reviews, performance reports, coaching plans, and root cause analyses. Use when a supervisor provides call recordings, transcripts, metrics, complaint da
Agent protocol
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with mu
Agent retention strategy planner
Designs call center agent retention programs covering training, recognition, work-life balance, career growth, feedback, team building, performance improvement, surveys, mentorship, and well-being. Use when a supervisor needs a retention plan, program, survey,
Agent team builder
Designs production-ready multi-agent team configurations from business process discovery, covering team architecture, per-agent specs, YAML config files, and pilot validation. Use when a user wants to automate a business process with a multi-agent team, needs
Agent workflow designer
Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs mu
Agenthub
Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple appro
Agentic identity trust
Use when Codex should act as the Agentic Identity & Trust Architect specialist from Agency Agents. Designs identity, authentication, and trust verification systems for autonomous AI agents operating in multi-agent environments. Ensures agents can prove who the
Agents autogpt
Guides users through building, triggering, monitoring, and deploying autonomous agents on the AutoGPT platform using its visual builder, Forge toolkit, and APIs. Use when someone asks how to create an agent, set up triggers, configure blocks or credentials, ru
Agents crewai
Orchestrates teams of specialized AI agents with roles, tasks, tools, and process types to collaborate on complex tasks. Use when defining agents, sequencing tasks, running a crew, generating YAML configs, assigning tools, or choosing sequential vs hierarchica
Agents langchain
Guides building LLM applications with LangChain, covering model setup, chains, ReAct agents, memory, RAG pipelines, structured output, and parallel/streaming execution. Use when a user wants to initialize a model or switch providers, build a chain, create a to
Agents llamaindex
Builds and queries a RAG application over private documents using LlamaIndex, covering ingestion from 300+ connectors, persistent vector indices, RAG query answering, metadata filtering, conversational chat, and agent tool use. Use when the user wants to load
Agents orchestrator
Use when Codex should act as the Agents Orchestrator specialist from Agency Agents. Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.
Agile product owner
Agile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking. Use when writing user stories, creating acceptance criteria, planning sprints, estimating story points,
Agile product owner
Generates INVEST-compliant user stories with acceptance criteria from epics, plans sprints against capacity or stored velocity, tracks velocity, and prioritizes backlogs. Use when the user provides an epic, a sprint capacity, completed sprint points, or asks t
Agile project management guide
Provides practical Agile guidance for IT project managers on Scrum, backlog management, sprint planning, metrics, tools, scaling, and transformation. Use when the user asks about Agile principles, ceremonies, prioritization, estimation, retrospectives, velocit
Agile project manager advisor
Provides practical Agile guidance on principles, frameworks, planning, tracking, collaboration, releases, risk, quality, scaling, retrospectives, coaching, tools, and transformation. Use when a project manager asks about Agile practices, needs a plan, or wants
Agile testing assistant
Helps QA managers plan, execute, and report agile testing work across automation, BDD, TDD, exploratory testing, ATDD, shift-left, test data, environments, metrics, pair testing, and risk-based testing. Use when planning tests, writing scenarios or test cases,
Agirails agent payments
Generates USDC payment code and onboarding steps for AI agents earning or paying on Base L2 via the AGIRAILS network. Use when a user wants to set up AGIRAILS, integrate agent payments, build an agent that earns or pays, try a mock demo, or understand ACTP vs
Ai act readiness
/cs:ai-act-readiness <system> — EU AI Act 6-question forcing interrogation. Use during AI-system intake, before EU deployment, or during annual compliance refresh as Article 113 obligations phase in (2025-02-02 / 2025-08-02 / 2026-08-02 / 2027-08-02).
Ai agent audit specialist
Designs tamper-evident audit trails for AI coding agents in regulated environments, mapping agent events to control IDs and producing auditor-facing evidence. Use when mapping agent events to frameworks, designing hash-chained capture, running integrity verifi