Install
$ agentstack add skill-mikeparcewski-wicked-garden-agentic-patterns ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Agentic Patterns
Reference guide for proven agentic architecture patterns and common anti-patterns to avoid.
Core Patterns
| 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.
Anti-Patterns Quick Reference
- God Agent: Single agent doing everything. Split responsibilities.
- Tight Coupling: Agents depend on internal implementation details. Use interfaces.
- Missing Guardrails: No constraints on agent actions. Add validation and limits.
- Deep Nesting: Agents calling agents calling agents. Flatten hierarchy.
- No Observability: Can't see what agents are doing. Add logging and tracing.
- Sequential Bottleneck: Everything waits for slowest agent. Add parallelism.
- Context Bloat: Passing entire history to every agent. Compress and filter.
- Redundant Agents: Multiple agents doing same thing. Consolidate.
- Hardcoded Prompts: Prompts baked into code. Externalize and version.
- Missing Timeouts: Agents can run forever. Add time and resource limits.
Pattern Selection Decision Tree
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.
Combining Patterns
Patterns are composable:
- Hierarchical + ReAct: Parent plans, children adapt execution
- Sequential + Reflection: Each stage includes self-review
- Collaborative + Human-in-Loop: Peer review with human arbitration
- Autonomous + Hierarchical: Independent teams with team leads
Pattern Anti-Affinities
Avoid these combinations:
- Plan-Execute + ReAct: Contradictory - either plan upfront or adapt dynamically
- Autonomous + Tight Coordination: Defeats the purpose of autonomy
- Deep Hierarchies + Reflection: Exponential token cost
Quick Start
- Identify if task is decomposable (subtasks?) or atomic
- Identify if execution is predictable (plan?) or dynamic (adapt?)
- Identify if agents should coordinate (hierarchy/collaboration) or work independently
- Check anti-patterns list against current design
- See refs/pattern-catalog.md for detailed examples
References
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)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mikeparcewski
- Source: mikeparcewski/wicked-garden
- License: MIT
- Homepage: https://wg.wickedagile.com/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.