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 monkilabs/opencastle --skill api-patternsgit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/monkilabs/opencastle/api-patterns)<a href="https://agentmods.dev/skills/monkilabs/opencastle/api-patterns"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/api-patterns/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/monkilabs/opencastle/api-patterns"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/api-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00472 |
| Opus 5.5 | $0.00022 | $0.00189 |
| Sonnet 5.5 | $0.00011 | $0.00094 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
api-patterns 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 10d 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.
Smoke-test a new endpoint against the dev server with `curl -fsS` before you call it done. What it actually says
API Patterns
The project's endpoints and where they live: .opencastle/stack/api-config.md when it has one, and the skill bound to the framework slot. Match what the existing endpoints do; where they disagree, follow the majority and say so, rather than add a third way.
Contract first
Decide the request, the response, the status codes and the error cases before you write the handler. Writing the handler first is how inconsistent APIs happen.
- Validate every input with a schema at the top of the handler (Zod, Pydantic, the framework's validator): 400 or 422 on failure, naming the field.
- One error shape, such as
{ "error": { "code": "VALIDATION_ERROR", "message": "...", "details": [...] } }, with no stack trace or query in it. The status says what happened: 400, 401, 403, 404, 409, 422, 429, 500. - Lists are paginated, with a cursor when the data changes under the reader, and
limitcapped on the server. - Changes are additive. Add fields; never remove or rename one a client may use without a new version and a deprecation period.
Writes and side effects
- A mutation a client may retry is idempotent: an idempotency key, or an upsert on a natural key.
- Authorization is checked on the server for every call (security-hardening).
External APIs
- A timeout on every call. Retry only what is safe to repeat, at most twice, with backoff.
- Map their errors to your error shape, and log the upstream detail on the server.
Limits and caching
Rate-limit public endpoints. Set Cache-Control, and an ETag on responses clients poll.
Smoke-test a new endpoint against the dev server with curl -fsS before you call it done.
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.
- 10d ago Changed · +3 lines · +19 tokens per session fecb5c1097b2
- 12d ago Changed · -18 tokens per session 753dc9362933
- 1mo ago First seen · 31 lines · 55 tokens per session scan A 682e3e7b4022
api-patterns is a skill published in the GitHub repository monkilabs/opencastle (80 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 472 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
telnyx-twilio-migration
Migrate from Twilio to Telnyx. Orchestrates a complete 6-phase migration: discovery, planning, setup, code migration, validation, and cleanup. Covers voice (TwiML to TeXML, Call Control API), messaging, WebRTC, SIP trunking, verify, fax, video, IoT, number lookup, and porting. Includes automated scanners, validation…
telnyx-ai-inference-curl
Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides REST API (curl) examples.
telnyx-numbers-config-curl
Configure phone number settings including caller ID, call forwarding, messaging enablement, and connection assignments. This skill provides REST API (curl) examples.
telnyx-sip-integrations-curl
Manage call recordings, media storage, Dialogflow integration, and external connections for SIP trunking. This skill provides REST API (curl) examples.
telnyx-ai-assistants-curl
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
telnyx-email-domains-curl
Manage email sending domains, verify DNS records (SPF, DKIM, DMARC, MX), check domain health, and configure domain-level webhooks for delivery events.