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 niels-emmer/myace --skill api-discoverabilitygit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/api-discoverability)<a href="https://agentmods.dev/skills/niels-emmer/myace/api-discoverability"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/api-discoverability.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 5.1 | $0.00051 | $0.00919 |
| Opus 5 | $0.00026 | $0.00460 |
| Sonnet 5 | $0.00010 | $0.00184 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
API Discoverability for Agents 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. If supported, add the generator and serve the spec at a conventional path (`/openapi.json` preferred; `/swagger.json`, `/api-docs` acceptable). Verify with `curl`. How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Agents integrate with services by reading a machine-readable API description instead of crawling a web UI or reverse-engineering endpoints by trial and error. This skill makes that the default: bake the description in when you build a service, and look for it before you probe when you integrate with one. It's the discoverability half of the API story — api-design-checklist keeps an API internally consistent; this skill makes sure agents can actually find and use it.
When to use it
- BUILDING a new self-hosted service — after scaffolding, before considering it done.
- INTEGRATING with an existing unfamiliar service — before crawling the UI or probing endpoints by trial and error.
Decision tree
New service → bake-in. Existing service → discover-first, then probe-and-write-back only if no description exists.
Bake-in (new services)
Treat the API description as a required step before "done", not optional polish.
- Detect the framework from the project manifest (
package.json,pyproject.toml,go.mod, ...). - Check for cheap OpenAPI support — FastAPI and ASP.NET Core serve
/openapi.jsonwith zero extra code. - If supported, add the generator and serve the spec at a conventional path (
/openapi.jsonpreferred;/swagger.json,/api-docsacceptable). Verify withcurl. - Otherwise write a minimal
API.mdat the repo root covering every endpoint: method, path, params, and a working curl example. - Verify before done: every route appears in the spec or
API.md, the curl examples actually work, and the spec path is reachable at the conventional location.
Discover-first (existing services)
- Probe conventional spec paths:
/openapi.json,/swagger.json,/api-docs,/swagger-ui/,/redoc,/api,/docs. - Search the repo:
API.md, a README API section,docs/, OpenAPI yaml files, Postman collections,*.httpfiles. - Use what you find — extract base URL, auth scheme, endpoints, params, request/response shapes. Integrate against it; do not re-derive by probing.
- Only if neither a spec path nor repo documentation exists, fall back to probe-and-write-back.
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 · 59 lines · 51 tokens per session scan A 1f15b342012e
API Discoverability for Agents is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 919 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
a0-development
Development guide for extending Agent Zero from current source and DOX. Use for framework architecture, tools, extensions, API/WebUI handlers, agent profiles, prompts, skills, projects, runtime boundaries, and contribution workflow. Load the focused reference files before giving implementation guidance.
loom-event-driven
Event-driven architecture patterns including message queues, pub/sub, event sourcing, CQRS, and sagas.
loom-background-jobs
Background job processing patterns including job queues, scheduled jobs, worker pools, retry strategies, and delivery guarantees.
loom-serialization
Data serialization and deserialization patterns across formats.
loom-api-design
Designs RESTful APIs, GraphQL schemas, and RPC interfaces for consistency, usability, and scalability.
loom-api-documentation
Document REST APIs with OpenAPI/Swagger specifications, endpoint references, authentication flows, error handling, and SDK guides.