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-design-flowgit 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-design-flow)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-design-flow"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-design-flow/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-design-flow"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-design-flow.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 | $0.00027 | $0.00510 |
| Opus 5.5 | $0.00011 | $0.00204 |
| Sonnet 5.5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
layerkit-design-flow 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
layerkit-design-flow
Use this skill to decide how the client package should express a vendor integration change.
Protocol
- Read the existing integration topology: mappers, adapters, routers, registries, tests, and feature flags.
- Read vendor evidence for the changed endpoint, payload, auth, batching, or ordering requirement.
- Prefer changing the existing mapper/adapter path.
- Use a multi-step flow in client code only when vendor evidence requires sequencing, branching, batching, or retries that are not already represented.
- Before adding a new abstraction, document why the existing abstraction cannot be changed.
- Update tests around the actual production path.
Design Outputs
- Existing file/function to update.
- Stale code/docs/tests to delete or rewrite.
- Required source edits.
- Tests to add or update.
- Residual TODOs where the client datalayer cannot satisfy the vendor contract.
Multi-vendor / new vendor on existing path
When the package already ships one or more vendors and the user wants a new vendor:
- Pick a sibling vendor adapter/mapper as the structural reference (
file://path). - Design the new integration by following that existing path: same module root, registry/router wire, privacy hooks, and test layout.
- Prefer cloning the sibling structure over inventing a parallel facade or side registry.
- Document: sibling reference path → new vendor files → registry entry → tests cloned from sibling.
- Only introduce a new abstraction when no sibling file can own the vendor-specific behavior, and list what existing surface cannot be extended.
Forbidden
- Designing a Layerkit runtime flow instead of client-owned source code.
- Adding a side registry/facade when the existing route/mapper can be edited.
- Inventing auth, endpoint, batching, or routing behavior without evidence.
- Finalizing while package verification fails.
- Designing a freestyle tree beside an existing multi-vendor module root.
Success Criteria
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.
- 1mo ago First seen · 52 lines · 27 tokens per session scan A acf18d914b71
layerkit-design-flow is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 510 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
cto-advisor
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Use when assessing technical debt, scaling engineering teams, evaluating technologies, or making architecture decisions.
agent-protocol
Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging. Use when building multi-agent systems, defining tool interfaces, or implementing agent-to-agent communication.
api-test-suite-builder
Generate API test suites from route definitions across frameworks: auth, input validation, contract, k6 load testing, mocking, and OpenAPI-driven generation. Use when adding new APIs, auditing test coverage, or building regression suites.
aws-solution-architect
Design AWS serverless architectures for startups with IaC. Use when designing serverless architecture, writing CloudFormation, optimizing AWS costs, setting up CI/CD, or migrating to AWS across Lambda, API Gateway, and DynamoDB.
mcp-server-builder
Build MCP (Model Context Protocol) servers with tool definitions, resource providers, prompt templates, and transports. Use when exposing APIs to AI agents, building tool servers, converting OpenAPI to MCP, or creating MCP integrations.
saas-scaffolder
Generate SaaS boilerplate with auth, database schemas, Stripe billing, multi-tenancy, API routes, and dashboard UI on a Next.js/TypeScript/Tailwind stack. Use when starting a new SaaS product, subscription app, or multi-tenant platform.