skills/swarm/SKILL.md
Alias for /ro:planner-worker. Multi-agent coding swarm — planner + worker + merger over git worktrees on the Max plan. When the user types /ro:swarm, /swarm, "kick off the swarm", "run the swarm", "swarm coding", or anything matching "swarm + code/PR/PRD", redirect to /ro:planner-worker.
npx skillsauth add RonanCodes/ronan-skills swarmInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This is a thin alias for /ro:planner-worker. Both invocations resolve to the same behaviour.
Use /ro:planner-worker directly — it has the full skill body. /ro:swarm exists so the friendlier word also works.
Use /ro:night-shift if you want a multi-wave indefinite drain across the whole backlog, not just a single planner-worker pass. Night-shift wraps planner-worker with a ranked queue, file-area conflict detection across waves, draft-grilling, parent-PRD auto-slicing, follow-up-issue creation, and an end-of-session nightsheet. It opens with a four-question scope grill so AFK semantics are explicit.
See ~/.claude/plugins/cache/ronan-skills/<v>/skills/planner-worker/SKILL.md for:
--github, --judge-agent, --afk, --workers N, --resume, live status, postmortem.swarm.json config/ro:swarm --prd <name> # same as /ro:planner-worker --prd <name>
/ro:swarm --afk # same as /ro:planner-worker --afk
/ro:swarm --resume # same as /ro:planner-worker --resume
All flags supported by /ro:planner-worker are supported here.
testing
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
development
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
tools
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
research
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".