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 agentmods add skills/jhlee0409/claude-plugins/layer-detectornpx skills add jhlee0409/claude-plugins --skill layer-detectorgit clone --depth 1 https://github.com/jhlee0409/claude-pluginsWrote 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/jhlee0409/claude-plugins/layer-detector)<a href="https://agentmods.dev/skills/jhlee0409/claude-plugins/layer-detector"><img src="https://agentmods.dev/badge/skills/jhlee0409/claude-plugins/layer-detector.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00014 | $0.02257 |
| Opus 5 | $0.00007 | $0.01128 |
| Sonnet 5 | $0.00003 | $0.00451 |
| Haiku 4.5 | $0.00001 | $0.00226 |
Grade A, and why
layer-detector 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 4d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layer Detector Skill
FSD 레이어 구조를 감지하고 분석합니다.
WHEN TO USE
This skill is invoked by:
/fsdarch:init- Initial project setup/fsdarch:analyze- Project analysis
EXECUTION INSTRUCTIONS
Step 1: Find Source Directory
Action: Determine the source directory path
1. Check if srcDir is passed as parameter
→ If yes, use it directly
2. If no parameter, read .fsd-architect.json
→ Use Read tool to get srcDir field
→ Default to "src/" if not specified
3. Verify directory exists:
→ Use Glob: "{srcDir}/"
→ If no match, return error E101
Glob command:
Glob: "src/"
# Or if config specifies different path:
Glob: "{config.srcDir}/"
Step 2: Detect Layers
Action: Scan for FSD layer directories
Standard FSD layers (in hierarchy order):
1. shared (lowest - utilities, ui kit, api clients)
2. entities (domain models and business entities)
3. features (user interactions and business logic)
4. widgets (composite UI blocks)
5. pages (route-level compositions) → "views" in Next.js
6. app (highest - app initialization) → "core" in Next.js
Glob commands to execute (in parallel):
For standard projects:
Glob: "{srcDir}/app/"
Glob: "{srcDir}/pages/"
Glob: "{srcDir}/widgets/"
Glob: "{srcDir}/features/"
Glob: "{srcDir}/entities/"
Glob: "{srcDir}/shared/"
For Next.js projects (layer aliases):
Glob: "{srcDir}/core/" # app → core
Glob: "{srcDir}/views/" # pages → views
Glob: "{srcDir}/widgets/"
Glob: "{srcDir}/features/"
Glob: "{srcDir}/entities/"
Glob: "{srcDir}/shared/"
Layer alias mapping (user-configurable):
// Layer aliases are stored in .fsd-architect.json
// Users can customize these during /fsdarch:init
interface LayerAliases {
app: string; // 'app', 'core', '_app', 'application', etc.
pages: string; // 'pages', 'views', '_pages', 'screens', etc.
}
// Common presets:
const LAYER_ALIAS_PRESETS = {
standard: { app: 'app', pages: 'pages' },
nextjs_recommended: { app: 'core', pages: 'views' },
nextjs_underscore: { app: '_app', pages: '_pages' },
nextjs_verbose: { app: 'application', pages: 'screens' }
};
// Read from config:
function getLayerPath(layer: string, config: Config): string {
if (config.layerAliases && config.layerAliases[layer]) {
return config.layerAliases[layer];
}
return layer; // default: use layer name as-is
}
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.
- 4d ago First seen · 337 lines · 14 tokens per session scan A fa235ca9e48b
layer-detector is a skill published in the GitHub repository jhlee0409/claude-plugins (4 stars, last pushed 7mo ago), licensed MIT. It adds 14 tokens to every session and 2,257 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
datamodel-code-generator
Use this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects.…
preserved_skill
previous skill.
performing-api-fuzzing-with-restler
Uses Microsoft RESTler to perform stateful REST API fuzzing by automatically generating and executing test sequences that exercise API endpoints, discover producer-consumer dependencies between requests, and find security and reliability bugs. The tester compiles an OpenAPI specification into a RESTler fuzzing…
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.