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 LedgerHQ/ledger-live --skill card-endpoint-shapegit clone --depth 1 https://github.com/LedgerHQ/ledger-liveWrote 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/ledgerhq/ledger-live/card-endpoint-shape)<a href="https://agentmods.dev/skills/ledgerhq/ledger-live/card-endpoint-shape"><img src="https://agentmods.dev/badge/skills/ledgerhq/ledger-live/card-endpoint-shape/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/ledgerhq/ledger-live/card-endpoint-shape"><img src="https://agentmods.dev/badge/skills/ledgerhq/ledger-live/card-endpoint-shape.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 | $0.00030 | $0.01183 |
| Opus 5 | $0.00015 | $0.00592 |
| Sonnet 5 | $0.00006 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00118 |
Grade A, and why
card-endpoint-shape 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 today.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Card endpoint shape
Every endpoint is a declaration. Four keys, always in this order:
someEndpoint: build.query<Canonical, Request>({
query: (request) => ({
url: "/v1/some/path",
method: "GET",
}),
rawResponseSchema: SomeWireSchema, // the wire shape
transformResponse: transformSome, // wire -> canonical
responseSchema: SomeSchema, // what callers receive
});
| Key | Answers | Lives in |
|---|---|---|
query |
What we send | api.ts |
rawResponseSchema |
What the backend promised | schema.ts |
transformResponse |
How it becomes ours | transforms.ts |
responseSchema |
What the caller gets | schema.ts |
Drop the keys you do not need. An endpoint whose wire shape is already canonical declares
responseSchema alone — logout and getUser both do.
Return the wire contract, nothing more. A field the backend never sent does not belong on the answer. If a caller needs one of its own request values afterwards, it already has it.
Never use queryFn
queryFn is the escape hatch for endpoints that are not one HTTP call. None here is, and it costs
more than it looks:
- RTK Query skips
transformResponsefor aqueryFnendpoint.getTransformCallbackForEndpointinbuildThunksis guarded byendpointDefinition.query &&. The mapper is silently ignored, so the mapping moves inside the function, by hand. - The
baseQueryresult isunknown, so the body needs a cast or a manualsafeParse. - Every one brings its own
if (response.error) return { error: response.error }.
Three lines of declaration become twenty of plumbing, and the endpoint stops reading like its neighbours.
An endpoint that handles a credential
The two OAuth2 grants are endpoints like any other, plus three rules. RTK Query puts the argument of a call on its pending action and the answer on its settled one, so a grant's credential travels through redux, and three controls keep it out of every reader:
extraOptions: { authenticated: false }, so the base query sends no Bearer and never renews. A grant presents its own credential, and a grant that renewed would loop on its own 401.- No hook. Export a hook for every other endpoint, and none for a grant.
track: falseat every call site, so the answer never becomes a cache entry in redux state.
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.
- today Changed · +17 lines · +6 tokens per session 9aa7ba37af51
- 5d ago First seen · 82 lines · 24 tokens per session scan A a244c04f1054
card-endpoint-shape is a skill published in the GitHub repository LedgerHQ/ledger-live (617 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,183 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
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.…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.
common-observability
Enforce structured JSON logging, OpenTelemetry distributed tracing, and RED metrics across backend services. Use when adding request correlation, setting up tracing spans, defining SLO burn-rate alerts, or instrumenting middleware.