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 hariharapanigrahy/layerkit --skill layerkit-research-vendorgit clone --depth 1 https://github.com/hariharapanigrahy/layerkitWrote 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/hariharapanigrahy/layerkit/layerkit-research-vendor)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-research-vendor"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-research-vendor/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/hariharapanigrahy/layerkit/layerkit-research-vendor"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-research-vendor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00030 | $0.00838 |
| Opus 5 | $0.00015 | $0.00419 |
| Sonnet 5 | $0.00006 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
layerkit-research-vendor 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Read official docs/OpenAPI/curl examples directly as the AI agent. Curate a structured contract/proposal with citations, then use deterministic CLI only to validate explicit proposals and package health. Privacy classifi How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
layerkit-research-vendor
You create or update integration knowledge from primary evidence. Core ships empty maps. Never invent.
Contract update (heal) is an agent-led production update path: human supplies OpenAPI/docs → AI agent reads/cites evidence → AI agent updates existing maps/source/tests. Do not route heal through deterministic source editing, code generation, or generated patch plans.
Protocol
A. Contract heal
When the user gives OpenAPI or docs, you are the AI reader. Fetch/read the official evidence, keep citations, and compare it to the existing map/interface/datalayer yourself.
.layerkit/out/contracts/<vendor>/openapi-from-doc.json
The CLI is tooling only: it validates explicit artifacts and package health, but it does not understand arbitrary docs, semantic field meaning, or source edits. If docs are ambiguous after evidence review, preserve uncertainty in notes and leave localized TODOs rather than inventing fields.
If one vendor field was removed and another was added, inspect docs and existing source before deciding it is a rename. Record your decision in the review note:
[
{
"fromVendor": "email",
"toVendor": "email_id",
"domain": "email",
"confidence": "high",
"evidence": ["OpenAPI removed email and added email_id for the same request value"]
}
]
Edit the real adapter/interface/test files yourself. If the field does not exist in the interface or datalayer, add a localized TODO only in the production change and call it out in review.
B. Supporting evidence work
Read official docs/OpenAPI/curl examples directly as the AI agent. Curate a structured contract/proposal with citations, then use deterministic CLI only to validate explicit proposals and package health. Privacy classification belongs to layerkit-privacy-review.
C. Domain meaning
Domain meaning comes from customer code plus vendor evidence, not from operation names alone. Cite docs, schemas, examples, and source files for every non-obvious mapping.
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.
- 9d ago First seen · 86 lines · 30 tokens per session scan A 2009306048f3
layerkit-research-vendor is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 838 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mcp-builder
A guide to building MCP servers, which let AI assistants call tools or read connected data. It covers server structure, tool design, validation, testing and deployment in TypeScript and Python.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
microservices-patterns
Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…