From rune
Use when choosing between supervisor, swarm, or pipeline coordination for multi-agent workflows, when two agents produce conflicting findings and deduplication is needed, when TOME aggregation fails or produces duplicate prefixes, or when output format mismatch causes downstream parse errors. Use when defining inscription contracts for file-based handoff, or when detecting which Ash type to use for a given review dimension. Keywords: orchestration, conflict detection, TOME aggregation, inscription, output format mismatch, file-based handoff, supervisor, swarm, pipeline. <example> Context: Running multi-agent code review user: "Review this PR with multiple agents" assistant: "I'll use rune-orchestration for context isolation and file-based handoff" </example> <example> Context: Coordinating a codebase audit user: "Run an audit with security and performance focus" assistant: "I'll use rune-orchestration for audit agent coordination and output format" </example>
npx claudepluginhub vinhnxv/rune --plugin runeThis skill is limited to using the following tools:
Guides designing distributed multi-agent systems that partition work across multiple language model instances to overcome single-agent context limitations.
references/damage-control.mdreferences/diff-scope.mdreferences/inscription-protocol.mdreferences/issue-creation.mdreferences/output-formats.mdreferences/prompt-weaving.mdreferences/role-patterns.mdreferences/structured-reasoning.mdreferences/talisman-config.mdreferences/team-lifecycle-guard.mdreferences/truthsight-pipeline.mdreferences/verifier-prompt.mdDesigns and implements multi-agent LLM systems covering orchestrator patterns, parallel coordination, pipelines, hierarchical delegation, communication, and failure handling. For multi-agent workflows and debugging.
Orchestrates multi-agent workflows by spawning parallel CLI subagents, coordinating via MCP Memory, monitoring progress, decomposing tasks, verifying outputs, and retrying failures. For complex automated parallel executions.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
Guides designing distributed multi-agent systems that partition work across multiple language model instances to overcome single-agent context limitations.
Sub-agents exist primarily to isolate context, not to anthropomorphize role division.
The fundamental value lies in distributing cognitive load across separate context windows rather than simulating organizational hierarchies.
| Category | Workflows | Orchestration Pattern |
|---|---|---|
| Reviews | /rune:appraise | Ash Specialists |
| Audits | /rune:audit | Roundtable Circle (Fan-out / Fan-in) |
| Research | /rune:devise | Parallel Exploration |
| Work | /rune:strive | Swarm Workers |
| Custom | Any workflow summoning 3+ agents | Choose pattern from below |
Generic trigger conditions:
Instead of supervisor synthesizing responses (telephone game), agents write directly to files:
| Workflow Type | Output Directory | Output Type | Example Contents |
|---|---|---|---|
| Reviews | tmp/reviews/{pr-number}/ | Report (P1/P2/P3) | forge-warden.md, ward-sentinel.md, TOME.md |
| Audits | tmp/audit/{audit-id}/ | Report (P1/P2/P3) | security.md, performance.md, TOME.md |
| Plan research | tmp/plans/{timestamp}/research/ | Research | repo-analysis.md, best-practices.md, framework-docs.md |
| Work (swarm) | tmp/work/{timestamp}/ | Patches | patches/*.patch, proposals/*.md, inscription.json |
| Custom | tmp/{workflow-name}/ | Varies | Named by teammate role |
Directory Purpose:
todos/): Findings that become actionable itemstmp/): Intermediate artifacts consumed by coordinatorThe workflow: Agents write findings → Coordinator reads files → Synthesizes into Tome (TOME.md)
Structured output: Ash MAY also write companion JSON files ({ash}-findings.json) for CI/CD integration. Legacy: completion.json was used in early versions but is no longer written by built-in workflows. Use Seal metadata + TOME.md for workflow results. See Output Format for full specs.
Each agent writes findings in a format matching its workflow type. All formats require mandatory evidence blocks.
When multiple agents flag the same code with different priorities:
| Conflict | Resolution |
|---|---|
| P1 vs P2 | P1 wins (highest priority) |
| P1 vs P1 (different issues) | Both retained |
| Security vs Performance | Security wins |
| Same issue, different agents | Deduplicate, keep first |
ward-sentinel P1 > any other agent P1
any agent P1 > any agent P2
any agent P2 > any agent P3
Central coordinator delegates to specialists and aggregates results.
The Tarnished (orchestrator)
├── forge-warden (backend review)
├── ward-sentinel (security review)
├── pattern-weaver (quality patterns)
├── glyph-scribe (frontend review)
└── knowledge-keeper (docs review)
Used by: /rune:appraise, /rune:audit
Mitigate telephone game: Use file-based handoff, not message passing.
Direct agent-to-agent communication. Workers self-organize and race to claim tasks.
Used by: /rune:strive
Example use case: Multiple rune-smiths claiming independent tasks from a shared pool.
Layered abstractions. Use for complex multi-phase workflows.
Strategy Layer (plan)
└── Planning Layer (spec)
└── Execution Layer (implement)
Used by: /rune:devise → /rune:strive → /rune:appraise
Defines how agents are organized for each workflow type, including conditional summoning rules and validation pipelines.
tmp/reviews/{pr}/. See Role Patternstmp/audit/{id}/. See Role Patternstmp/plans/{timestamp}/research/. See Role Patternstmp/work/. See Role Patterns| Approach | Token Multiplier | When to Use |
|---|---|---|
| Single agent | 1x | Simple tasks |
| Multi-agent | ~15x | Complex review, parallel analysis |
Guideline: Use multi-agent only when context isolation is necessary, not for simple division of labor.
Problem: Coordinator overwhelmed by aggregating many agent responses.
Solution: Glyph Budget — each agent writes to file, returns only file path + 1-sentence summary (max 50 words).
Problem: Too much time on handoff protocols.
Solution: Clear file-based handoff with consistent format.
Problem: Agents disagree indefinitely.
Solution:
Problem: Early agent error cascades.
Solution:
Every agent in a parallel workflow:
See context-weaving skill for the full Glyph Budget protocol and pre-summon checklist.
All Rune multi-agent workflows use Agent Teams (TeamCreate) + inscription.json.
Rune command (any agent count) → Agent Teams + inscription.json
Custom workflow (3+ agents) → Agent Teams + inscription.json
Three steps:
inscription.json before summoning agents/teammatesAgents send structured Seal messages (key-value: file, sections, findings, evidence-verified, confidence, self-reviewed, summary). TaskList completed is authoritative; Seal is supplementary metadata.
Full spec: Inscription Protocol
Multi-agent workflows benefit from structured reasoning at key decision points.
Three reasoning checkpoints for the Tarnished:
| Checkpoint | When | Key Action |
|---|---|---|
| Pre-summon | Before launching agents | 8-thought checklist (see context-weaving) |
| Mid-monitor | During agent execution | Intervene on timeout, clarification requests, partial failures |
| Post-aggregate | After collecting all outputs | Resolve conflicts between agents using branching analysis |
Full protocol: Structured Reasoning
On context compaction or session resume during any Rune workflow:
~/.claude/teams/{team-name}/config.jsonTaskList() to discover team statetmp/{workflow}/{id}/inscription.json.rune/arc/{id}/checkpoint.jsonSession handoff template: session-handoff.md
context-weaving (Glyph Budget, pre-summon checklist)roundtable-circle skill