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 ambient-code/platform --skill ambient-api-servergit clone --depth 1 https://github.com/ambient-code/platformWrote 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/ambient-code/platform/ambient-api-server)<a href="https://agentmods.dev/skills/ambient-code/platform/ambient-api-server"><img src="https://agentmods.dev/badge/skills/ambient-code/platform/ambient-api-server/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/ambient-code/platform/ambient-api-server"><img src="https://agentmods.dev/badge/skills/ambient-code/platform/ambient-api-server.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 | $0.00000 | $0.00860 |
| Opus 5.5 | $0.00000 | $0.00344 |
| Sonnet 5.5 | $0.00000 | $0.00172 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
ambient-api-server 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: ambient-api-server
Activates when: Working in components/ambient-api-server/ or asked about API server, REST endpoints, gRPC, OpenAPI, or plugins.
What This Skill Knows
You are working on the Ambient API Server — a Go REST + gRPC server built on the rh-trex-ai framework. It serves the Ambient Platform's resource API under /api/ambient/v1/.
Plugin System (critical)
Every resource kind is a self-contained plugin in plugins/<kind>/. The 8-file structure is mandatory:
plugins/<kind>/
plugin.go # route + gRPC registration
model.go # GORM DB struct
handler.go # HTTP handlers
service.go # business logic
dao.go # DB layer
presenter.go # model → API response
migration.go # DB schema
mock_dao.go # test mock
*_test.go # table-driven tests
Generate scaffold: go run ./scripts/generator.go --kind Foo --fields "name:string,status:string"
OpenAPI is the source of truth
openapi/openapi.yaml
→ make generate → pkg/api/openapi/ (DO NOT EDIT)
→ ambient-sdk make generate → all SDKs
Never edit pkg/api/openapi/ files — they are generated from openapi/openapi.yaml.
gRPC
- Protos:
proto/ambient/v1/ - Stubs:
pkg/api/grpc/ambient/v1/(generated) - Auth:
pkg/middleware/bearer_token_grpc.go - Watch streams: server-side streaming RPCs — emit AG-UI events to clients
- Ownership bypass: when JWT username not in context (test tokens), skip per-user ownership check
Environments
AMBIENT_ENV |
Auth | DB | Use for |
|---|---|---|---|
development |
disabled | localhost:5432 | local make run |
integration_testing |
mock | testcontainer (ephemeral) | make test |
production |
JWT required | cluster Postgres | deployed |
Test setup
systemctl --user start podman.socket
export DOCKER_HOST=unix:///run/user/$(id -u)/podman/podman.sock
cd components/ambient-api-server && make test
Runbook: Add a New API Resource
- Define schema in
openapi/openapi.yaml - Run
make generate(updates Go stubs) go run ./scripts/generator.go --kind MyResource --fields "..."- Implement
service.goanddao.gobusiness logic - Write table-driven tests in
*_test.go - Run
make test— all green - Run
make generateinambient-sdkto propagate to SDKs - Run
make buildinambient-clito update CLI
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 · 95 lines · 0 tokens per session scan A 4e7c4683fb1f
ambient-api-server is a skill published in the GitHub repository ambient-code/platform (131 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 860 tokens. 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
oss-alternatives
Find actively maintained open source alternatives to any paid SaaS tool or commercial API. Use this skill whenever a user mentions wanting to replace, swap out, self-host, or find a free/open source version of a paid tool — including but not limited to tools like Datadog, Algolia, Twilio, Stripe, Auth0, Segment…
contribute-spec-fix
Fix a broken OpenAPI spec in jentic-public-apis with an OpenAPI Overlay, validate it (spectral lint + idempotency check), and contribute it back via a PR to the community catalog. Falls back to applying the same overlay to the local Jentic registry if the user can't wait for maintainer approval, and closes the loop by…
write-microflows
Microflow syntax reference in MDL — every activity type, control flow, expressions, and the mistakes that fail mxcli check. Use before writing any CREATE MICROFLOW, and when debugging a microflow syntax error.
01-bootstrap
Design and validate a new SaaS's architecture into an INSTALL.md via Q&A and stack comparison. Use when the user starts a project, chooses a stack, or picks an architecture pattern. Not for editing an existing stack or scaffolding code.
java-actions
Create and call custom Java actions — extending Mendix with server-side Java, and invoking those actions from microflows in MDL. Use when logic needs a Java library, an algorithm microflows cannot express, or an integration only available in Java.
json-structures-and-mappings
Create and manage JSON structures, import mappings and export mappings in MDL, plus the domain-model shapes they map onto. Use when turning a JSON payload into entities, mapping a REST or queue response, or exporting objects as JSON.