renatoschust-dot/gamai-skills/agents-swarm-orchestration

Claude Code and agent skill by renatoschust-dot/gamai-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Coordinates multi-agent execution across subagents, teams, and workflows. Use when planning dependency-aware fan-out, verifier passes, runtime selection, or Loop Engineering.

Install

npx vskill@latest install renatoschust-dot/gamai-skills/agents-swarm-orchestration

SKILL.md

The same SKILL.md was published earlier as renatoschust-dot/gamai-skills/agents-swarm-orchestration.

Swarm Orchestration

Advanced execution layer for multi-worker runs after agent or team selection.

Coordinate multiple workers without polluting the main thread. Use this skill after agents-subagents has already selected the right agent, member, team, or debate pattern. This skill is for choosing the orchestration surface, freezing task ownership before fan-out, and requiring structured outputs that the lead agent can validate and merge safely.

Terminology (Aug 2026)

"Swarm" is community vocabulary — it appears nowhere in Anthropic documentation. Use the official primitive names when writing configs, prompts, or docs; keep "swarm" only as informal shorthand for the whole category.

InformalOfficial primitiveStatus (Aug 2026)
"swarm of subagents"SubagentsGA. Background behavior is mode-dependent; background: true forces background but false is not a documented foreground pin. Recursive spawn currently defaults to three layers below the main session
"swarm with peer chat"Agent teamsExperimental, env-gated CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Behavior churns weekly — re-verify before relying
"scripted swarm"Dynamic workflowsShipped 2026-05. JS in .claude/workflows/; ≤1000 agents/run, 16 concurrent. The repeatable-orchestration artifact
"swarm across terminals"Cross-session messagingAug 2026, macOS/Linux. Sessions message each other without a team — lighter than teams for passing findings

Quick Reference

SituationDefault patternWhy
1-2 tasks or shared-file editsStay in the main conversationParallelism adds coordination overhead without payoff
Focused worker that only needs to report backClaude Code subagent or Codex workerIsolated context, simple coordination
Workers must talk to each otherClaude Code agent teamShared task list plus direct messaging
Read-heavy scans, tests, triage, summarizationParallel workersKeeps noisy intermediate output off the lead thread
One coordinator should retain user ownershipManager / agents-as-toolsLead keeps control of decisions and final answer
Specialist should take over the conversationHandoffOwnership moves to the specialist agent
Work of unknown extent — discovery is the taskLoop until K empty roundsA fixed task list cannot be enumerated up front
Loop Engineering: recurring discovery or evaluationLoop-until-dry or budget-bounded loopDefine convergence, termination, and state checkpoints
Many items, known stages, high intermediate volumeScripted workflow (Claude Code)Script holds control flow; lead context holds only the result

Navigation

Maintainer note: eight URLs here are intentionally duplicated from ../agents-subagents/data/sources.json (Claude Code subagents, Agent Teams, Codex Multi-Agents, Codex Subagents, both OpenAI Agents SDK pages, OpenAI prompt-caching guide, Karpathy coding notes). Each skill frames those sources for a different reader. When a URL rotates, update both files in the same commit.

When To Use / Not To Use

UseDo Not Use
agents-subagents already chose the team; now needs execution planningStill deciding which agent, team, or debate mode fits
3+ bounded tasks with clear ownership or dependenciesTasks share the same file or unresolved interface
Requirements, decisions, synthesis must stay in one lead contextMain blocker is product ambiguity, not execution bandwidth
Exploration, tests, logs, or review can run in parallelWorkers would need the same context and make the same decisions
Loop Engineering needs a bounded multi-pass orchestration contractOne pass or a simple queue already meets the goal
Verification must be explicit, not implied by worker confidenceWork is small enough that orchestration cost exceeds execution cost

Relationship To Agents-Subagents

agents-subagents is the entry point. It selects the mode and prepares the first launch prompt. This skill takes over when the plan needs multi-wave execution, worker dependencies, verifier passes, or merge/conflict control.

Operating Principles

  • Lead owns requirements, decisions, approvals, and final synthesis — not execution.
  • Default to read-heavy parallelism; parallel writes are higher-risk.
  • Freeze shared interfaces before dispatching edit-capable workers.
  • Give every worker exclusive owned_files and explicit do_not_touch boundaries.
  • Pass distilled dependency outputs, not raw logs or long transcripts.
  • Require structured worker reports — the lead validates and merges deterministically.
  • Re-plan when conflict resolution costs more than the fan-out saved.
  • Fresh context per worker: each worker brief contains only its task, plan section, file ownership, and interface contracts — not the lead's full history. Prevents context rot; gives each worker a full window.
  • State in files: task graph, progress, decisions, and dependency outputs live in structured files (frontmatter MD / JSON / YAML). Any new lead session resumes by reading files, not memory.
  • Checkpoint long runs: snapshot task state, reports, and decisions to checkpoints/ at each wave boundary.
  • Budget per worker: explicit token/time/tool caps at dispatch. Budget-conservation invariant: child budgets are strict subsets of the parent's remaining budget. Workers that breach their budget stop and escalate — they do not continue. (Ye & Tan, Agent Contracts: A Formal Framework for Resource-Bounded Autonomous AI Systems, arXiv:2601.08815, 2026)
  • Telemetry per worker: assign a run id or span id; log inputs, outputs, status, tokens, and duration to one structured location.
  • Durable approval channels: route approvals through mailbox/poller with request IDs, not ephemeral callbacks.
  • Minimum toolset per worker: use tools, disallowedTools, and skills fields to give each worker only what it needs.
  • Memory opt-in: prefer clean-context workers + file-backed checkpoints. Enable memory only when the role genuinely benefits from cross-run priors; never default it for verifiers or reviewers. Prefer file tools over schema-constrained memory APIs. (Lance Martin, 2026-04-24; `../ai-context-layer/references/filesystem-as-memory.md`)

For context rotation and state handoff patterns, see `../ai-agents/references/context-rotation-and-state.md`.

Explicit Fan-Out Is The Durable Default

Claude Opus 4.7 (GA 2026-04-16) shipped a lasting behavior change: it spawns fewer subagents by default than 4.6, favoring single-response completion over implicit parallelism. Fan-out workflows that previously worked without being asked — read-heavy scans, multi-file refactors, review waves, cross-repo audits — now silently serialize unless the lead is told to fan out explicitly. Opus 4.8 (current as of this writing) inherits the same conservative default; treat "assume no auto-parallelism" as the standing assumption for whatever frontier model is current, and re-verify against release notes each time the lead model changes.

Anthropic's source guidance is to give the model explicit fan-out instructions; it does not prescribe where the instruction must live. Our repo convention is to install the canonical phrasing once in AGENTS.md / CLAUDE.md (not duplicated per launch prompt):

Spawn multiple subagents in the same turn when fanning out across items or reading multiple files. Do not spawn a subagent for work you can complete in a single response.

Full guidance and source links live in agents-subagents. Judgment call for the lead: after any model swap, run one throwaway fan-out task and watch whether it parallelizes on its own — cheaper than discovering silent serialization mid-migration.

Named Patterns

Name the pattern explicitly when proposing a design. Full detail: ../agents-subagents/references/harness-patterns.md.

This is the start of the file. Read the full SKILL.md on GitHub.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/renatoschust-dot/gamai-skills/agents-swarm-orchestration/badge)](https://verified-skill.com/skills/renatoschust-dot/gamai-skills/agents-swarm-orchestration)

Something wrong with this skill or its page? Tell us.