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/epam/ai-dial-chat/api-designnpx skills add epam/ai-dial-chat --skill api-designgit clone --depth 1 https://github.com/epam/ai-dial-chatWrote 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/epam/ai-dial-chat/api-design)<a href="https://agentmods.dev/skills/epam/ai-dial-chat/api-design"><img src="https://agentmods.dev/badge/skills/epam/ai-dial-chat/api-design.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 | $0.00064 | $0.01052 |
| Opus 5 | $0.00032 | $0.00526 |
| Sonnet 5 | $0.00013 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
api-design 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Design
Use this skill before implementing or reviewing any HTTP API contract. It defines the
contract-first procedure for this repo. For backend implementation mechanics (DTO/Swagger/SDK
patterns, tests, Nx verification) follow apps/chat-api/AGENTS.md — do not restate them here. For library isolation follow the
"Library isolation" section in the root AGENTS.md: host/API/transport details stay in apps;
hand-authored libs/* receive resolved data, values, or callbacks. Exception: libs/chat-api-client
is the generated OpenAPI client.
Start Here
- Read
openspec/config.yamlfor API architecture, project boundaries, and proposal/spec/task rules. - Inspect the closest existing endpoint and its matching frontend client before designing a new contract:
- Backend controllers:
apps/chat-api/src/**/**.controller.ts - Backend DTOs:
apps/chat-api/src/**/dto/*.dto.ts - Frontend API helpers:
apps/chat/src/server-api/ - Shared interfaces:
libs/chat-shared/
- Backend controllers:
Contract Checklist
For every new or changed endpoint, define these before coding:
- Method and full path. Business endpoints are URI-versioned (
/api/v1/<resource>); infrastructure endpoints stay unversioned (/api/<resource>). - Request shape: path params, query params, body DTO, headers, cookies.
- Success response shape and status code.
- Error status codes and what each means: at least validation/auth/authorization/not found, plus
502(upstream non-OK),503(upstream timeout/unavailable). Never500exposing internals. - Authentication and authorization requirements, including whether the endpoint is explicitly public.
- Rate limiting. Public unauthenticated endpoints should usually tighten the global default.
- Cache behavior when applicable: TTL, invalidation, and key naming (
<domain>:<resource>[:<param>]). - Pagination for list endpoints: prefer cursor for large/append-heavy datasets; offset is acceptable for small admin-style or search flows.
- Frontend impact: thin domain wrapper in
apps/chat/src/server-api/that delegates to generated@epam/chat-api-client, shared type inlibs/chat-shared/if needed, and i18n strings for any errors surfaced in UI. - Library impact: if a hand-authored lib needs the data/behavior, name the prop/callback/resolved value it receives (see lib-isolation note above).
- Generated client impact: expected SDK class, method name (derived from the controller handler name via
operationIdFactory), request type, response type, and whether callers needRawaccess for headers/status.
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 · 67 lines · 64 tokens per session scan A b96d5a145bf3
api-design is a skill published in the GitHub repository epam/ai-dial-chat (504 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 1,052 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…