skills/agentic/agentic-patterns/SKILL.md
Use when designing or analyzing multi-agent architectures — covers core patterns (sequential, hierarchical, parallel, event-driven), anti-patterns, and the five-layer model (Cognition → Context → Interaction → Runtime → Governance) for separating concerns in production-grade agentic systems. NOT for reviewing existing agentic code (use review-methodology) or framework selection (use the frameworks skill).
npx skillsauth add mikeparcewski/wicked-garden wicked-garden-agentic-agentic-patternsInstall 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.
Reference guide for proven agentic architecture patterns and common anti-patterns to avoid.
| Pattern | Use when | Example | Tradeoffs | |---------|----------|---------|-----------| | Sequential | Linear workflow, clear dependencies, predictable stages | Research → Analyze → Draft → Review | Simple coordination; bottlenecks if any agent is slow | | Hierarchical | Complex task decomposable into subtasks; central coordination | PM agent delegates to designer / dev / QA | Clear accountability, scales; single point of failure at parent | | Collaborative | Diverse perspectives matter; no clear lead | Multiple reviewers collaborating on code review | Rich outputs; needs conflict resolution + consensus | | Autonomous | Tasks are fully independent; parallel execution | Multiple monitoring agents checking different services | Max parallelism; no shared learning or coordination | | Human-in-the-Loop | High-stakes decisions, regulatory gates, human feedback | Agent drafts report; human approves before sending | Adds latency; ensures safety and quality | | ReAct | Dynamic environments; need adaptive behavior on feedback | Debug agent: try fix → observe tests → adapt | Flexible; high token/latency cost for reasoning | | Plan-Execute | Predictable environment; planning overhead justified | Multi-step pipeline with known transformations | Efficient; brittle if environment changes | | Reflection | Quality > speed; self-improvement valuable | Writer drafts → critiques → refines | Higher quality; more tokens and latency |
See refs/pattern-catalog.md for full descriptions and implementation notes per pattern.
Is task decomposable into subtasks?
├─ YES: Is there a clear lead/coordinator role?
│ ├─ YES: Use Hierarchical
│ └─ NO: Use Collaborative
└─ NO: Does task require adaptation based on results?
├─ YES: Can you plan all steps upfront?
│ ├─ YES: Use Plan-Execute
│ └─ NO: Use ReAct
└─ NO: Do you have multiple independent tasks?
├─ YES: Use Autonomous
└─ NO: Use Sequential
Add Human-in-the-Loop gates for any high-stakes decisions. Add Reflection layer when quality is critical.
Patterns are composable:
Avoid these combinations:
refs/pattern-catalog.md - Detailed pattern descriptions with implementation examplesrefs/anti-patterns-design.md - Design anti-patterns (God Agent, Tight Coupling, Missing Guardrails, Deep Nesting, No Observability)refs/anti-patterns-operational.md - Operational anti-patterns (Sequential Bottleneck, Context Bloat, Redundant Agents, Hardcoded Prompts, Missing Timeouts)development
Pattern-conformance agent-half: evaluates a produced artifact or diff against a set of architectural/design pattern rules from the conformance-rule store (wicked_governance schema). Returns structured findings with rule ID, severity, and rationale — the deterministic half (mechanical rule recall) is done by the guard pipeline; this is the semantic evaluation step. Triggered by: the guard_pipeline `outgov_pattern` check (session-close), or explicitly by an engineering review when WICKED_OUTGOV_RULES_DIR is populated. NOT a replacement for the full `engineering` review skill — focuses only on conformance to stored Pattern rules; architecture and code-quality checks live in the `engineering` skill. Semantic evaluation reuses `wicked-garden-qe-semantic-reviewer` as the designated agent-half evaluator (per garden#983 spec). This skill is the orchestrating wrapper that loads applicable Pattern rules and delegates the per-rule semantic judgment to qe-semantic-reviewer.
tools
The FOUNDATIONAL domain-model capability: extract a codebase's domain — testable business rules (with confidence + provenance), entities, requirements — as a schema-conformant model on the estate graph. The workers annotate the store; wicked-core reads it and builds the requirements graph, coverage-gating fail-closed. Steers three fork workers. A shared substrate, not a modernization tool. The `modernize` archetype DERIVES from it; build / migrate / review / specify / explore consume the SAME domain model — none OWN it. Understanding a codebase's domain is upstream of almost everything else garden does. Use when: "extract the business rules / domain model from this codebase", "build a requirements graph from the code", "what does this system actually require", "reverse-engineer the domain before we build/port/migrate". Works on ANY codebase (modern or legacy) — the value is the domain model, not the porting. NOT the code transform itself (that is the archetype consuming this model). This skill produces the DOMAIN MODEL, not new code.
development
Domain-graph fork worker for the modernize archetype. Groups the estate's Louvain communities into business domains, attaches each requirement to its cluster (advisory cluster_id provenance), and invokes wicked-core's domain-graph build (which reads the annotated estate store, recomputes coverage fail-closed, and builds the requirements graph) — then validates core's output against the vendored schema. Use when: dispatched by wicked-garden-domain after rule extraction to turn a flat rule set into cluster-keyed domains; "group these into domains", "build the requirements graph", "translate clusters into a domain model". NOT for mining the rules themselves (that is domain-extractor) or threat-modeling (that is domain-coverage).
tools
Rule-extraction fork worker for the FOUNDATIONAL domain-model capability. Mines testable business rules from a codebase — each with a numeric confidence and a provenance{source, ref, source_kinds} — and annotates them into the estate store so wicked-core can build the domain-model requirements graph (coverage-gated). This is a substrate, not a modernization tool: the `modernize` archetype DERIVES from it, and build / migrate / review / specify / explore can consume the same domain model — none OWN it. Use when: dispatched by wicked-garden-domain to mine the business_rules of a codebase (or a module); "extract the domain rules", "what does this system require", building the requirements half of a domain model. NOT for grouping into domains (that is domain-modeler) or judging coverage (that is domain-coverage — a seat-distinct evaluator).