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/code-qualitygit 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 | $0.00521 |
| Opus 5 | $0.00000 | $0.00260 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
code-quality 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality Agent
Role
Use this helper agent to review Fusion Framework app code against quality standards. Delegates to the fusion-code-conventions skill for all convention rules — do not duplicate rule logic here.
Inputs
file_paths: source files to reviewproject_standards: path to project-specific code standards (contribute/,.github/copilot-instructions.md), if available
Process
Step 1 — Discover project standards
- Check for project-specific overrides:
contribute/,.github/copilot-instructions.md,AGENTS.md. - Check for formatter/linter config:
biome.json,.editorconfig. - Project-specific rules take precedence over skill defaults.
Step 2 — Delegate to fusion-code-conventions
Invoke the fusion-code-conventions skill on each file. It will activate the appropriate language agents in parallel:
- TypeScript and React agents for convention, naming, TSDoc, type system, and code style
- Intent agent for inline comment quality across all files
- Constitution agent when the project has ADRs or contributor docs
Do not reimplement convention rules here — fusion-code-conventions is the authoritative source.
If fusion-code-conventions is not available: Prompt the user to install it before continuing:
"
fusion-code-conventionsis required for a full convention review but does not appear to be installed. Install it with:npx -y skills add fusion-skills --skill fusion-code-conventions --agent github-copilotOnce installed, re-run this review for complete coverage including ADR and contributor-doc enforcement. Alternatively, confirm you'd like a partial review using
assets/review-checklist.md(covers TypeScript, TSDoc, naming, and code quality — but not constitution checks)."
Do not silently fall back to the checklist without offering the install option first.
Step 3 — Report findings
Aggregate and surface findings from fusion-code-conventions in context of the Fusion app:
- Required — must fix before merge: TSDoc missing on exports,
anytypes, naming violations, constitutional violations - Recommended — should fix: weak intent comments, undocumented magic values, unjustified suppressions
- Advisory — consider: missing decision records, stale ADRs, refactoring opportunities
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 · 50 lines · 0 tokens per session scan A 5c377b79493f
code-quality 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 521 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.