NeVibeCode · repository · 49 items
openrig: a set by mvschwarz
The mvschwarz/openrig repository on GitHub: 49 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.
About the repository
- GitHub
- mvschwarz/openrig
- Stars
- ★ 8,928
- License
- Apache-2.0
- Source updated
- 2026-11-12
- In the catalog since
- 2026-10-26
vault-user skill vault-user connects coding agents to a local HashiCorp Vault instance in OpenRig to check health, inspect paths, and manage secrets.
CX Codex +1
★ 8,928repo stars
software-for-agents skill software-for-agents is a Claude Code skill that redirects older OpenRig instructions to agent-operated-software. It supports projects that still use the former skill name.
CX Codex +1
★ 8,928repo stars
session-compaction-and-restore skill session-compaction-and-restore — a skill for Claude Code, Codex, Cursor and other platforms. Preserves agent working state across compaction, restart or session refresh using a restore packet.
CX Codex +1
★ 8,928repo stars
seat-continuity-and-handover skill The seat-continuity-and-handover skill for Claude Code covers replacing an agent while keeping its seat identity stable. It separates creating a successor from binding it to the seat and recording the transition.
CX Codex +1
★ 8,928repo stars
retiring-and-inheriting-a-seat skill retiring-and-inheriting-a-seat is a Claude Code skill for planned agent transitions when a seat is nearing its context limit. It prepares a successor with a handover packet and records the seat’s lineage.
CX Codex +1
★ 8,928repo stars
refocusing skill The refocusing skill for Claude Code and Codex brings a long-running agent back to its current goal and working context. It traces project trees before a consequential next step.
CX Codex +1
★ 8,928repo stars
queue-handoff skill queue-handoff hands off tasks through OpenRig queue items across agents and humans. Keeps progress moving across context compactions and interruptions.
CX Codex +1
★ 8,928repo stars
orienting-to-an-inherited-seat skill The orienting-to-an-inherited-seat skill guides an agent taking over an existing seat after a planned handover. It covers what to carry forward and what to verify first.
CX Codex +1
★ 8,928repo stars
openrig-user skill openrig-user — a reference skill for the rig CLI: exact command syntax, JSON shape, defaults and error meanings once you already know which command to run.
CX Codex +1
★ 8,928repo stars
openrig-operating-model skill openrig-operating-model maps agent context across OpenRig topology and task trees. It helps agents find relevant guidelines and place new findings into proper files.
CX Codex +1
★ 8,928repo stars
mission-slice-sop skill mission-slice-sop guides agents through a mission or slice, from resolving its context to checking the result and handing work off. Useful for projects that track delivery in OpenRig files.
CX Codex +1
★ 8,928repo stars
loading-addressable-markdown skill loading-addressable-markdown pulls exactly one Markdown section out of a filesystem tree by an address like file.md#h2-slug. Handy when a task points at a spec section instead of a whole file.
CX Codex +1
★ 8,928repo stars
forming-an-openrig-mental-model skill forming-an-openrig-mental-model gives agents a direct runtime mental model of OpenRig: topology terms, layer hierarchy, tmux session addressing, and lifecycle commands.
CX Codex +1
★ 8,928repo stars
delegating-work skill delegating-work helps choose between doing a task yourself, spawning a subagent, or routing it to an agent that already has the needed context.
CX Codex +1
★ 8,928repo stars
claude-compaction-restore skill claude-compaction-restore keeps the connections between files and decisions alive across context compaction: write a restore map before the squeeze, read it back after and rebuild the picture.
CX Codex +1
★ 8,928repo stars
applying-a-permission-policy skill applying-a-permission-policy is a Claude Code skill that sets OpenRig permissions before a team launch. It activates during command-permission setup or when native approval prompts interrupt work.
CX Codex +1
★ 8,928repo stars
agent-operated-workflows skill The agent-operated-workflows skill explains how an agent can run a bounded procedure when the real system may differ from the expected path. Use it to plan actions, verify results, and leave evidence for a later resume.
CX Codex +1
★ 8,928repo stars
agent-operated-software skill The agent-operated-software Claude Code skill covers applications whose live backend or control loop includes OpenRig agents. It guides architecture work and diagnosis across code and agent control files.
CX Codex +1
★ 8,928repo stars
dogfood skill The dogfood skill explores a web app, checks its interface and behaviour, and creates a report with evidence for each issue. Use it for exploratory QA of a site or service.
CX Codex +1
★ 8,928repo stars
context-engineering skill context-engineering — a skill about how an agent's context window gets filled, pruned and shared. Useful when an agent drifts or forgets constraints mid-task.
CX Codex +1
★ 8,928repo stars
review-team skill review-team enforces disciplined code reviews in OpenRig with grounded findings, anti-slop checks, and markdown reports.
CX Codex +1
★ 8,928repo stars
oversight-team skill The oversight-team skill guides a monitor that checks other agent rigs for drift and chooses a measured response. It waits for a signal instead of polling continuously.
CX Codex +1
★ 8,928repo stars
orchestration-team skill orchestration-team — an orchestration skill: it splits work into assignments, dispatches them, and watches for idle or blocked agents instead of doing the implementation itself.
CX Codex +1
★ 8,928repo stars
development-team skill development-team coordinates building and QA inside a development pod. It guides agents to deliver working code verified against public contracts.
CX Codex +1
★ 8,928repo stars
ui-mockup skill ui-mockup is a Claude Code skill that creates ASCII wireframes, standalone HTML screens, and live prototypes from product requirements. Review proposed screens before building them.
CX Codex +1
★ 8,928repo stars
requirements-writer skill requirements-writer talks a product manager through rough feature notes and turns them into a single SPEC.md with observable acceptance criteria and explicit scope.
CX Codex +1
★ 8,928repo stars
plan-review skill plan-review reviews feature plans and requirements documents across strategy, design, and engineering feasibility before development begins.
CX Codex +1
★ 8,928repo stars
office-hours skill The office-hours skill challenges a feature idea with six product questions about demand, current workarounds, and scope. It ends with a documented verdict.
CX Codex +1
★ 8,928repo stars
exec-summary skill exec-summary turns a feature folder into one 600–800 word document: a sales pitch, a leadership brief and a behavioral overview for engineering.
CX Codex +1
★ 8,928repo stars
context-builder skill context-builder gathers feature background from meetings, competitor research, and regulations. Generates a concise background.md and updates shared team context.
CX Codex +1
★ 8,928repo stars
backlog-capture skill backlog-capture — a skill for Claude Code and five other coding agents that turns rough notes into structured backlog entries. Fire it after meetings or calls to grab an idea before it slips away.
CX Codex +1
★ 8,928repo stars
watchdog skill A skill for configuring rig watchdog policies: it picks the right intervention when an agent goes idle, drifts, or needs a checkpoint.
CX Codex +1
★ 8,928repo stars
topology-mutation-and-seat-management skill topology-mutation-and-seat-management guides agents in altering live OpenRig topologies on the fly: expanding capacity, removing seats, binding tmux sessions, and preventing stale edges.
CX Codex +1
★ 8,928repo stars
specification-system skill specification-system guides the design and review of OpenRig rig, agent, and workflow specs. Use it to catch portability problems and check that a declared setup can run.
CX Codex +1
★ 8,928repo stars
session-source-fork skill session-source-fork is a Claude Code and Codex skill that launches a managed seat from another session via session_source with fork mode. It defines the schema and validation rules.
CX Codex +1
★ 8,928repo stars
rig-lifecycle skill Teaches the agent to reason about OpenRig lifecycle operations, verify post-reboot state in rig ps, and handle recovery without silent fresh fallbacks.
CX Codex +1
★ 8,928repo stars
rig-bundles-and-shareable-artifacts skill rig-bundles-and-shareable-artifacts is a Claude Code skill for creating, inspecting, and installing OpenRig bundles. It supports bundle authoring and portability audits.
CX Codex +1
★ 8,928repo stars
openrig-upgrade skill openrig-upgrade is a Claude Code skill that guides OpenRig CLI and daemon upgrades. It checks each change and preserves active seats and local plugin edits.
CX Codex +1
★ 8,928repo stars
openrig-software-factory skill The openrig-software-factory skill organizes OpenRig agent teams in software repositories. It sets up review handoffs and execution workflows between Claude Code and Codex seats.
CX Codex +1
★ 8,928repo stars
openrig-skills skill This skill helps an agent in OpenRig find the right context for a handover, debugging, or recovery task. It also shows how to locate and load other skills with rig.
CX Codex +1
★ 8,928repo stars
1–40 of 49