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 plugin-architecturegit 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/plugin-architecture)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/plugin-architecture"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/plugin-architecture.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
- 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 | $0.00109 | $0.03720 |
| Opus 5 | $0.00055 | $0.01860 |
| Sonnet 5 | $0.00022 | $0.00744 |
| Haiku 4.5 | $0.00011 | $0.00372 |
Grade A, and why
backend-plugin-architecture scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
// Process isolation (Node.js child_process) How it starts
The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Plugin Architecture
Purpose
Design extensible backend systems where third-party code (plugins) can be loaded dynamically at runtime through well-defined extension points and service provider interfaces (SPI). A plugin architecture enables the host application to be extended without modifying its core code.
Agent Protocol
Trigger
Exact user phrases: "plugin system", "plugin architecture", "extension point", "SPI", "service provider interface", "hot-plug", "modular design", "plugin loader", "extensible", "plugin API", "custom extension", "plug-in", "dynamic loading".
Input Context
- What the host application does and where extensibility is needed.
- Language/runtime (supports dynamic loading?).
- Security requirements for plugin isolation.
Output Artifact
Plugin system design or implementation code. No file unless requested.
Response Format
Extension Point: {name}
SPI: {interface/contract}
Loading: {dynamic|compile-time|classpath}
Isolation: {classloader|process|container}
Completion Criteria
- Extension points defined and documented.
- SPI interface created for each extension point.
- Plugin loader implemented.
- Plugin lifecycle (load, init, start, stop, destroy) managed.
- Isolation and security boundaries established.
Max Response Length
3 lines per extension point. 20 lines for full system.
Architecture Decision Tree
Should I Build a Plugin System?
Do you need to support third-party extensions?
├── Yes → Plugin architecture
└── No → Can the functionality be handled by configuration?
├── Yes → Use configuration, not plugins
└── No → Is the extension point stable (won't change monthly)?
├── Yes → Plugin architecture is appropriate
└── No → Plugin API will need constant breaking changes — reconsider
Plugin Loading Strategy
Can plugins be loaded at runtime without restart?
├── Yes → Dynamic loading (hot-plug)
│ ├── Language supports dynamic loading (JS, Python, Java, .NET, Go plugins)
│ ├── Plugin discovery via file system scanning or registry
│ └── Risk: Version conflicts, dependency hell
└── No → Compile-time loading
├── Simpler, safer, no runtime isolation concerns
├── Requires recompile/redeploy for new plugins
└── Use when: Plugin churn is low, safety is critical
What ships with it
6 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.
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 First seen · 503 lines · 109 tokens per session scan A 2324e2e6d398
backend-plugin-architecture is a skill published in the GitHub repository j4flmao/agent-skills (21 stars, last pushed 2d ago), licensed MIT. It adds 109 tokens to every session and 3,720 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
architecture-paradigm-microkernel
Applies microkernel architecture with minimal core and plugin extensibility. Use when building platforms where third parties extend core functionality.
architecture-paradigm-service-based
Applies coarse-grained service architecture for deployment independence. Use when independent deployment is needed but shared databases rule out microservices.
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
opentelemetry
OpenTelemetry observability patterns: traces, metrics, logs, context propagation, OTLP export, Collector pipelines, and troubleshooting.
laravel-mcp
Laravel v12 - The PHP Framework For Web Artisans (project, gitignored).
laravel
Laravel v12 - The PHP Framework For Web Artisans.