Skill

ash-guide

Use when summoning Rune agents, when encountering "agent not found" errors, when selecting which review agents to use, or when checking agent capabilities and tools. Quick reference for all 109 agents across 6 categories (66 core + 43 extended in review, research, work, utility, investigation, testing). Keywords: agent list, Ash, subagent type, agent not found. <example> Context: User wants to know which agents are available user: "What review agents does Rune have?" assistant: "Loading ash-guide for the agent reference table" </example>

From rune
Install
1
Run in your terminal
$
npx claudepluginhub vinhnxv/rune --plugin rune
Tool Access

This skill is limited to using the following tools:

ReadGlob
Skill Content

Ash Guide

Quick reference for all Rune plugin agents, their roles, and invocation patterns.

Invocation Models

Direct Invocation (standalone tasks, custom workflows)

All Rune agents are plugin agents. Invoke with the rune: namespace prefix:

Agent rune:review:ward-sentinel("Review these files for security")
Agent rune:review:ember-oracle("Check performance bottlenecks")
Agent rune:utility:runebinder("Aggregate review findings")

Common mistake: Using agent name without namespace prefix.

# WRONG - agent not found
Agent ward-sentinel(...)

# CORRECT - full namespace
Agent rune:review:ward-sentinel(...)

Composite Ash Invocation (review/audit workflows)

The /rune:appraise and /rune:audit commands use general-purpose subagents with composite Ash prompt templates from agents/. Each Ash embeds multiple agent perspectives into a single teammate. This is intentional — composite Ashes don't map 1:1 to individual agent files.

Agent({ subagent_type: "general-purpose", team_name: teamName, name: "ash-name", prompt: /* from ../../agents/{category}/{role}.md */ })

The agent file allowed-tools are not enforced at runtime for composite Ashes. Tool restriction is enforced via prompt instructions (defense-in-depth).

Note: Agents listed below with rune:review:*, rune:testing:*, or rune:utility:* types may live in registry/ rather than agents/. Registry agents cannot be spawned directly via Agent({ subagent_type: "rune:review:blight-seer" }) — the plugin-namespaced type won't resolve. Instead, use subagent_type: "general-purpose" and inject the agent body via the agent_detail(name) MCP call or Read("registry/{category}/{name}.md"). Agents in agents/ (e.g., ward-sentinel, ember-oracle, flaw-hunter) ARE directly spawnable via their listed type names.

Review Agents

35 specialized reviewers that form Ash teams:

AgentRolePerspective
rune:review:ward-sentinelSecurity reviewVulnerabilities, auth, injection, OWASP, prompt injection
rune:review:ember-oraclePerformance reviewBottlenecks, N+1 queries, async patterns, memory
rune:review:rune-architectArchitecture reviewLayer violations, DDD, dependency direction
rune:review:simplicity-wardenSimplicity reviewYAGNI, over-engineering, premature abstraction
rune:review:flaw-hunterLogic reviewEdge cases, race conditions, null handling, off-by-one
rune:review:mimic-detectorDuplication reviewDRY violations, copy-paste code, similar patterns
rune:review:pattern-seerPattern reviewNaming consistency, convention adherence
rune:review:void-analyzerCompleteness reviewMissing error handling, incomplete implementations
rune:review:wraith-finderDead code & unwired code reviewUnused functions, DI wiring gaps, orphaned routes/handlers, AI orphan detection
rune:review:phantom-checkerDynamic reference checkReflection, string-based imports, meta-programming
rune:review:type-wardenType safety reviewType hints, mypy strict, Python idioms, async correctness
rune:review:trial-oracleTDD compliance reviewTest-first order, coverage gaps, assertion quality
rune:review:depth-seerMissing logic reviewError handling gaps, state machines, complexity hotspots
rune:review:blight-seerDesign anti-pattern reviewGod Service, leaky abstractions, temporal coupling, observability
rune:review:forge-keeperData integrity reviewMigration safety, reversibility, lock analysis, transaction boundaries, PII
rune:review:tide-watcherAsync/concurrency reviewWaterfall awaits, unbounded concurrency, cancellation, race conditions
rune:review:refactor-guardianRefactoring completeness reviewOrphaned callers, incomplete extractions, missing dependency moves, stale test refs
rune:review:reference-validatorReference integrity reviewImport paths, config-to-source refs, frontmatter schema, version sync
rune:review:reality-arbiterProduction viability truth-tellingIntegration honesty, production readiness, data reality, error path honesty
rune:review:assumption-slayerPremise validation truth-tellingProblem-solution fit, cargo cult detection, complexity justification
rune:review:entropy-prophetLong-term consequence truth-tellingComplexity compounding, dependency trajectory, lock-in, maintenance burden
rune:review:design-system-compliance-reviewerDesign system compliance reviewToken usage, variant patterns, import paths, class merge utilities, dark mode implementation
rune:review:ux-heuristic-reviewerUX heuristic evaluationNielsen Norman 10 heuristics at code level, 50+ checklist items (UXH-). Conditional: ux.enabled + frontend files
rune:review:ux-flow-validatorUser flow completenessLoading states, error boundaries, empty states, confirmation dialogs, undo, graceful degradation (UXF-). Conditional: ux.enabled + frontend files
rune:review:ux-interaction-auditorMicro-interaction auditHover/focus states, keyboard accessibility, touch targets (44px), animation, prefers-reduced-motion (UXI-). Conditional: ux.enabled + frontend files
rune:review:ux-cognitive-walkerCognitive walkthroughFirst-time user simulation, discoverability, learnability, error recovery, progressive disclosure (UXC-). Conditional: ux.enabled + cognitive_walkthrough: true

Ash Roles (Consolidated Teammates)

In /rune:appraise, agents are grouped into 7 built-in Ashes (extensible via talisman.yml):

AshAgents EmbeddedScope
Forge Wardenrune-architect, ember-oracle, flaw-hunter, mimic-detector, type-warden, depth-seer, blight-seer, forge-keeperBackend code (.py, .go, .rs, .rb, .java)
Ward Sentinelward-sentinelALL files (security always)
Veil Piercerreality-arbiter, assumption-slayer, entropy-prophetALL files (truth-telling always)
Pattern Weaversimplicity-warden, pattern-seer, wraith-finder, phantom-checker, void-analyzer, trial-oracle, tide-watcher, refactor-guardian, reference-validatorALL files (quality patterns)
Glyph ScribeInline perspectives (TypeScript safety, React performance, accessibility)Frontend code (.ts, .tsx, .js, .jsx)
Knowledge KeeperInline perspectives (accuracy, completeness, consistency)Docs (.md files, conditional)
Codex OracleInline perspectives (cross-model security, logic, quality via codex exec)ALL files (when codex CLI available)

Note: Forge Warden, Ward Sentinel, Veil Piercer, and Pattern Weaver embed dedicated review agent files. Glyph Scribe, Knowledge Keeper, and Codex Oracle use inline perspective definitions in their Ash prompts (no dedicated agent files). Codex Oracle is CLI-gated and wraps the external codex exec command.

Utility Agents

AgentRole
rune:utility:runebinderAggregates review/audit outputs → writes TOME.md
rune:utility:truthseer-validatorAudit coverage validation (Phase 5.5)
rune:utility:flow-seerSpec flow analysis
rune:utility:scroll-reviewerDocument quality review
rune:utility:decree-arbiterTechnical soundness review for plans
rune:utility:mend-fixerParallel code fixer for /rune:mend findings
rune:utility:knowledge-keeperDocumentation coverage reviewer for plans
rune:utility:veil-piercer-planPlan-level truth-teller (Phase 4C plan review)
rune:utility:ux-pattern-analyzerCodebase UX maturity assessment — inventories loading, error, form, navigation, empty state, confirmation/undo patterns (devise Phase 0.3)

Research Agents

AgentRole
rune:research:practice-seekerExternal best practices research
rune:research:repo-surveyorCodebase/repo exploration
rune:research:lore-scholarFramework documentation research
rune:research:echo-readerReads Rune Echoes (past learnings)
rune:research:git-minerGit history archaeology

Work Agents

AgentRole
rune:work:rune-smithCode implementation (TDD-aware)
rune:work:trial-forgerTest generation

Testing Agents

AgentRole
rune:testing:unit-test-runnerDiff-scoped unit test execution (Sonnet)
rune:testing:integration-test-runnerIntegration test execution with service management (Sonnet)
rune:testing:e2e-browser-testerE2E browser testing via agent-browser (Sonnet)
rune:testing:test-failure-analystRead-only failure analysis and fix suggestions (Opus inherit)

Ash Selection Logic

The /rune:appraise command selects Ash based on file extensions (Rune Gaze):

File PatternAsh Selected
**/*.pyForge Warden + Ward Sentinel + Pattern Weaver + Veil Piercer
**/*.{ts,tsx,js,jsx}Glyph Scribe + Ward Sentinel + Pattern Weaver + Veil Piercer
**/*.md (>= 10 lines changed)Knowledge Keeper (conditional)
Mixed code + docsAll applicable Ash

Ward Sentinel, Pattern Weaver, and Veil Piercer are selected for every review regardless of file types.

See roundtable-circle skill for full Ash architecture and prompts.

Stats
Parent Repo Stars1
Parent Repo Forks0
Last CommitMar 18, 2026