fabric

Master entry for the fabric family. Use for /fabric or when you must pick a multi-agent mode: reads the task, picks one mode, says why in one line, then follows that skill.

SKILL.md

GitHub

/fabric — pick the mode, then run it

fabric has no pipeline of its own. It reads the task, chooses one mode from the table, prints one line (fabric: <mode> — <reason>), and then follows that skill's contract. Ask the human only if two modes fit equally well.

Mode Pick it when Skill
fabric-graph An approved plan should be built and correctness beats speed: durable production_artifacts/state.json, Reviewer repair loop, automated quality gate, human escalation. fabric-graph
fabric-multigraph A small throwaway fan-out (2-4 nodes, nothing persistent) in any project. fabric-multigraph
fabric-teamwork The brief is still vague and needs 9-step prompt crafting before delegation to a team. fabric-teamwork
fabric-swarm Many similar workers taking items from one shared pool (production_artifacts/swarm.json, 4 workers, cap 6). fabric-swarm
fabric-loop A repeating cycle until an exit check is green (CI green, review rounds), bounded by round limits. fabric-loop

Choosing

  1. The task needs resumable state, a review loop or a quality gate before anything ships: fabric-graph.
  2. The task splits into a few independent slices and nothing has to survive the session: fabric-multigraph.
  3. The goal is unclear and a team will receive it: fabric-teamwork first, then one of the above.
  4. Repeat-until-done with an exit check and round limits: fabric-loop. Many near-identical slices: fabric-swarm.
  5. A small task needs no mode at all: do it yourself.

Pass the goal text through verbatim; flags are described below.

Flags and building blocks

  • --skill=<name>: handled by fabric-graph and fabric-multigraph. fabric-swarm and fabric-loop pass it through to each worker brief. fabric-teamwork does not support it.
  • --profile=<name>: domain profile from .agents/profiles/<name>.json; handled by the workflow script of fabric-graph. An unknown profile escalates.
  • --workstreams: workflow script of fabric-graph only; the Architect plans 1-6 dynamic workstreams (target 4, cap 6). Off by default.
  • Teams: aos-team list, aos-team show <id>, aos-team new <id> [--from-playbook <name>]; add --json for machine output. Team JSON lives in ~/.aos/teams or .aos/teams (project wins); shipped teams are in lib/roles/teams.
  • Roles: a registry of role JSON files (types plan, approve, build, review, gate, specialist). Precedence: project .aos/roles over user ~/.aos/roles over shipped. Role flags beyond the registry: unverified.

One loop for every harness. fabric-graph (and a fabric-loop round) runs on the aos-fabric CLI: start, then next and report by hand with your own executor, or drive for a headless run. It needs no workflow runtime and works without AO.

Agents never invoke each other. The dispatcher (the main session or the workflow script) decides every next step. Independent sub-tasks go to subagents; only work whose members must react to each other needs a team.

Safety

git push, npm publish and npm version stay behind the go-gate. Choosing a mode never grants a GO.