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 equinor/fusion-skills --skill fusion-core-servicesgit clone --depth 1 https://github.com/equinor/fusion-skillsWrote 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/equinor/fusion-skills/fusion-core-services)<a href="https://agentmods.dev/skills/equinor/fusion-skills/fusion-core-services"><img src="https://agentmods.dev/badge/skills/equinor/fusion-skills/fusion-core-services/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/equinor/fusion-skills/fusion-core-services"><img src="https://agentmods.dev/badge/skills/equinor/fusion-skills/fusion-core-services.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00088 | $0.01822 |
| Opus 5 | $0.00044 | $0.00911 |
| Sonnet 5 | $0.00018 | $0.00364 |
| Haiku 4.5 | $0.00009 | $0.00182 |
Grade A, and why
fusion-core-services 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 2d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fusion Core Services
When to use
Use when the task involves one or more Fusion Core service APIs and the agent needs to identify the right service guidance without requiring separate skill installs.
Typical triggers:
- implement a Fusion API client
- wire a Fusion backend service integration
- figure out which Fusion Core service owns a workflow
- solve a cross-service task such as context plus people, roles plus notifications, or apps plus service messages
When not to use
- Modifying code inside
fusion-core-services - Non-Fusion APIs or generic Microsoft Graph / Power BI work with no Fusion service layer
- Standalone product workflows already covered by another dedicated skill outside Fusion Core services
Required inputs
- target workflow or user goal
- target consumer shape (
react,typescript client,csharp httpclient,backend service, or other) - known service hints, if any
- versioning or authorization expectations when relevant
Instructions
- Scope the request first.
- Identify whether the workflow touches one service or multiple.
- If service is ambiguous, use
agents/service-router.mdto map the workflow to likely services before producing implementation guidance.
- Read only the relevant service references.
- Start with Combined API surface.
- Then open the matching per-service reference file.
- Pull in the endpoint catalog and model asset for only the services that materially affect the answer.
- Fetch the live OpenAPI document before trusting exact names or shapes.
- Every Fusion Core service publishes its current OpenAPI document publicly, with no JWT required:
https://{service}.api.fusion.equinor.com/openapi/api-v{version}.json(e.g.https://people.api.fusion.equinor.com/openapi/api-v3.json,https://context.api.fusion.equinor.com/openapi/api-v1.json). - The bundled reference files are a curated index of which services/controllers exist and how to
approach them — not the source of truth for exact schema/type names, which drift as services
change. Fetch the live document for the target service(s) and read
components.schemasfor the real type names — responses are commonlyApi{Entity}and request bodies a plain{Verb}{Entity}Requestname, but the live document's exact name always wins over any pattern; never invent aDto-suffixed name that isn't actually incomponents.schemas. - If you cannot fetch the live OpenAPI document (no web-fetch tool or network access), explicitly state that limitation, treat bundled references/assets as best-effort, and avoid asserting exact schema/type names or required fields.
- If the subdomain isn't already known from the service catalog below, resolve it via Fusion service discovery rather than guessing, per the platform-wide rule of never hardcoding service addresses.
What ships with it
40 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/service-router.md 2.3 KB
- assets/fusion-apps-endpoint-catalog.md 7.2 KB
- assets/fusion-apps-models.ts 14 KB runs code
- assets/fusion-bookmarks-endpoint-catalog.md 2.0 KB
- assets/fusion-bookmarks-models.ts 3.8 KB runs code
- assets/fusion-context-endpoint-catalog.md 3.3 KB
- assets/fusion-context-models.ts 3.2 KB runs code
- assets/fusion-contract-personnel-endpoint-catalog.md 9.7 KB
- assets/fusion-contract-personnel-models.ts 9.9 KB runs code
- assets/fusion-mail-endpoint-catalog.md 4.0 KB
- assets/fusion-mail-models.ts 5.8 KB runs code
- assets/fusion-notification-endpoint-catalog.md 1.9 KB
- assets/fusion-notification-models.ts 4.0 KB runs code
- assets/fusion-people-endpoint-catalog.md 6.2 KB
- assets/fusion-people-models.ts 19 KB runs code
- assets/fusion-portal-config-endpoint-catalog.md 4.0 KB
- assets/fusion-portal-config-models.ts 6.5 KB runs code
- assets/fusion-reports-endpoint-catalog.md 3.3 KB
- assets/fusion-reports-models.ts 9.1 KB runs code
- assets/fusion-roles-v2-endpoint-catalog.md 8.3 KB
- assets/fusion-roles-v2-models.ts 19 KB runs code
- assets/fusion-service-messages-endpoint-catalog.md 2.0 KB
- assets/fusion-service-messages-models.ts 4.6 KB runs code
- assets/fusion-tasks-endpoint-catalog.md 2.4 KB
- assets/fusion-tasks-models.ts 7.3 KB runs code
- assets/models.ts 969 B runs code
- CHANGELOG.md 2.5 KB
- references/api-surface.md 4.6 KB
- references/fusion-apps.md 5.6 KB
- references/fusion-bookmarks.md 3.2 KB
- references/fusion-context.md 4.6 KB
- references/fusion-contract-personnel.md 4.4 KB
- references/fusion-mail.md 3.7 KB
- references/fusion-notification.md 4.1 KB
- references/fusion-people.md 5.1 KB
- references/fusion-portal-config.md 3.9 KB
- references/fusion-reports.md 3.5 KB
- references/fusion-roles-v2.md 4.8 KB
- references/fusion-service-messages.md 3.6 KB
- references/fusion-tasks.md 4.3 KB
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.
- 2d ago Changed · +26 lines d2ff1b61e353
- 10d ago First seen · 106 lines · 88 tokens per session scan A 41eb586454e8
fusion-core-services is a skill published in the GitHub repository equinor/fusion-skills (1 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,822 once invoked, about $0.0004 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 2026-08-31.
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.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
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.