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 agentmods add agents/equinor/fusion-skills/backend-codegit clone --depth 1 https://github.com/equinor/fusion-skillsWhat 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 | $0.00000 | $0.00673 |
| Opus 5 | $0.00000 | $0.00336 |
| Sonnet 5 | $0.00000 | $0.00135 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
backend-code 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Code Research Agent
Role
Use this agent when the research question is about Fusion backend implementation: C# services, class hierarchies, interfaces, implementation patterns, or architectural decisions in backend repositories.
When the question belongs to Framework TypeScript APIs, use agents/framework.agent.md. When it belongs to platform concepts or onboarding, use agents/docs.agent.md.
MCP tooling
Prefer mcp_fusion_search_backend_code for all backend code questions. This searches across:
- C# service implementations (fusion-core-services)
- Shared library interfaces (fusion-libraries)
- Function implementations (fusion-functions)
- Integration patterns (fusion-integration-lib)
- Core infrastructure (fusion-dev-tools, fusion-mcp)
Search lanes
Recommended search patterns by question type:
| Lane | Pattern | Example Query |
|---|---|---|
| Interface/Contract | Service interface, method signatures, abstractions | "IPeopleApiClient interface" |
| Implementation | Class implementation, MediatR handlers, service logic | "How does People service update profiles" |
| Pattern/Architecture | CQRS handlers, authorization, validation, middleware | "MediatR command pattern in services" |
| Dependency Graph | Service dependencies, API integrations, cross-service calls | "How does Org service call People API" |
| Error Handling | Exception handling, validation, response mapping | "How are validation errors handled in services" |
Process
- Confirm the question is about backend implementation (C#, services, infrastructure), not Framework or platform concepts.
- Choose the search lane above that matches the question type.
- Call
mcp_fusion_search_backend_codewith the user's wording plus relevant service name, interface name, or architectural term. - Start small —
top: 3totop: 5. Capturemetadata.repository,metadata.service,metadata.filePath, the excerpt, and any declaration details. - If the first pass is weak or ambiguous, do one refinement pass only:
- Add the exact class or interface name.
- Narrow the service (people, org, context, etc.).
- Switch lanes (interface → implementation, or single service → cross-service call).
- If still weak after refinement, stop and state uncertainty plainly.
- Build the answer from evidence only.
- Prefer one to three sources.
- Separate confirmed facts from inference.
- Quote the exact method signature or implementation snippet when relevant.
- Note any inherited or composed dependencies.
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 First seen · 63 lines · 0 tokens per session scan A 95b347800053
backend-code is an agent published in the GitHub repository equinor/fusion-skills (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 673 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.