Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add j4flmao/agent-skills --skill design-patternsgit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/j4flmao/agent-skills/design-patterns)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/design-patterns"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/design-patterns/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/j4flmao/agent-skills/design-patterns"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/design-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.03720 |
| Opus 5.5 | $0.00042 | $0.01488 |
| Sonnet 5.5 | $0.00021 | $0.00744 |
| Haiku 4.5 | $0.00010 | $0.00372 |
Grade A, and why
design-patterns scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Patterns
Purpose
Guide pattern selection across all categories — GoF, enterprise, integration, concurrency, architectural — with decision trees, applicability rules, trade-off analysis, and composition guidance.
Agent Protocol
Trigger
User request includes: design pattern, gof, gang of four, pattern catalog, creational, structural, behavioral, pattern selection, enterprise pattern, integration pattern, concurrency pattern, architectural pattern, anti-pattern, pattern composition, CQRS, event sourcing, saga, repository, unit of work, messaging pattern, circuit breaker, strangler fig, saga pattern, hexagonal architecture, clean architecture.
Input Context
- Problem statement with constraints (performance, memory, team size, tech stack)
- Current architecture description
- Existing patterns already in use
- Pattern category preference or openness
Output Artifact
Selected pattern(s) with rationale, rejected candidates with explicit elimination reasons, implementation sketch, trade-off table, and composition rules if multiple patterns are needed.
Response Format
No preamble. No postamble. No explanations. Strip articles a/an/the where unambiguous. Compress output. If no pattern fits, output No matching pattern. Consider: [alternative approach]. and stop.
Completion Criteria
- Decision tree traversed and documented
- Rejected candidates include explicit elimination reason
- Implementation sketch covers pattern structure (not full business logic)
- Trade-offs documented for each selected pattern
- Pattern composition rules applied if multiple patterns
Architecture Decision Tree
Which Pattern Category?
What kind of problem are you solving?
├── Object creation, instance management → Creational (Singleton, Factory, Builder, Prototype)
├── Class/object composition, interfaces → Structural (Adapter, Decorator, Proxy, Facade)
├── Object communication, algorithms → Behavioral (Observer, Strategy, Command, State)
├── Business logic organization, persistence → Enterprise (Repository, Unit of Work, Aggregate)
├── Service-to-service communication → Integration (Message Queue, Event Bus, API Gateway)
├── Thread safety, async coordination → Concurrency (Mutex, Semaphore, Actor, Fan-out/Fan-in)
├── High-level system structure → Architectural (Clean Architecture, Hexagonal, CQRS, Event Sourcing)
└── Code smells affecting maintainability → Anti-Pattern to refactor (God Class, Spaghetti Code)
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- microservices/SKILL.md 8.9 KB
- references/anti-patterns.md 34 KB
- references/behavioral_patterns.md 8.5 KB
- references/concurrency-patterns.md 21 KB
- references/design-patterns-fundamentals.md 6.4 KB
- references/domain-driven-design-patterns.md 7.1 KB
- references/enterprise-patterns.md 38 KB
- references/gof-patterns.md 35 KB
- references/integration-patterns.md 21 KB
- references/pattern-relationships.md 36 KB
- references/selection-decision-tree.md 5.1 KB
- references/structural_patterns.md 8.4 KB
- references/testing-patterns.md 8.6 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +13 lines 0a5c41f99515
- 10d ago Changed · -122 lines 0d86ce9d59bb
- 2mo ago First seen · 530 lines · 104 tokens per session scan A d395a4b155a1
design-patterns is a skill published in the GitHub repository j4flmao/agent-skills (38 stars, last pushed 3d ago), licensed MIT. It adds 104 tokens to every session and 3,720 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
design-patterns compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-patternsj4flmao/agent-skills | Skill | 38 | 3d ago | MIT | A | 104 | Claude Code, Codex |
| platform-apex-generateforcedotcom/sf-skills | Skill | 1.1k | 2d ago | Apache-2.0 | A | 122 | Claude Code |
| flow-next-impl-reviewgmickel/flow-next | Skill | 717 | yesterday | MIT | A | 34 | Claude Code, Codex |
| api-contract-reviewTencentCloudBase/CloudBase-AI-Toolkit | Skill | 1.2k | yesterday | MIT | A | 54 | Claude Code |
| flow-next-resolve-prgmickel/flow-next | Skill | 717 | yesterday | MIT | A | 36 | Claude Code, Codex |
| ring:mapping-streaming-eventsLerianStudio/ring | Skill | 218 | 6d ago | Apache-2.0 | A | 95 | Cursor |
| ring:instrumenting-streaming-eventsLerianStudio/ring | Skill | 218 | 6d ago | Apache-2.0 | A | 102 | Cursor |