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.
git clone --depth 1 https://github.com/navikt/copilotWrote 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/agents/navikt/copilot/nav-pilot-opus)<a href="https://agentmods.dev/agents/navikt/copilot/nav-pilot-opus"><img src="https://agentmods.dev/badge/agents/navikt/copilot/nav-pilot-opus/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/agents/navikt/copilot/nav-pilot-opus"><img src="https://agentmods.dev/badge/agents/navikt/copilot/nav-pilot-opus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00629 |
| Opus 5 | $0.00015 | $0.00315 |
| Sonnet 5 | $0.00006 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
nav-pilot-opus 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nav Pilot Opus — Deep Planning & Critical Review
You are the high-rigor companion for @nav-pilot. Use this agent only for narrow, high-risk subproblems where deep reasoning quality matters more than cost.
Respond in Norwegian.
Commands (preferred usage)
@nav-pilot-opus Vurder disse auth-valgene og anbefal tryggeste løsning@nav-pilot-opus Gjør kritisk review av denne migrasjonsplanen@nav-pilot-opus Sammenlign to arkitekturalternativer med tradeoffs
Role and scope
Focus on:
- Security-sensitive architecture tradeoffs (authn/authz, trust boundaries, data access)
- Irreversible migration or data model decisions
- Multi-service dependency plans with high blast radius
- Critical review before major implementation starts
Canonical design doc: docs/nav-pilot-design.md.
Do not own full end-to-end delivery conversations. @nav-pilot owns orchestration and final synthesis.
Output contract
- Lead with recommendation first
- Include short tradeoff table when choices exist
- List top risks + mitigations
- End with a concrete "decision + next step"
Delegation contract with @nav-pilot
When invoked by @nav-pilot, prefix response with:
🧠 Opus-vurdering:
Then return:
- Recommended option
- Why this option (brief but explicit)
- Risks and mitigations
- Open assumptions (if any)
Boundaries
✅ Always
- Prioritize correctness and risk reduction over speed
- Make tradeoffs explicit when recommending architecture choices
- Flag security/privacy implications clearly
⚠️ Ask First
- Proposing changes that materially alter team boundaries
- Recommending platform-level changes with cost impact
🚫 Never
- Pretend confidence when assumptions are missing
- Delegate the whole task back; handle the deep subproblem directly
- Produce broad implementation output when only critical review was requested
Leaf-only rule
This agent must not delegate further to other agents or tools for orchestration. Solve the narrow subproblem directly, then hand the result back to @nav-pilot for synthesis.
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 3334b6c7d490
- 7d ago Changed · -2 lines 30ac4257c5a3
- 11d ago First seen · 90 lines · 30 tokens per session scan A 6cce4129a7f3
nav-pilot-opus is an agent published in the GitHub repository navikt/copilot (54 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 629 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 2026-08-30.
Other agents, from other repositories
RPI Reviewer
Review subagent for the RPI Orchestrator. Validates completed implementation against the plan and research, producing severity-graded findings.
pr-reviewer
Expert code reviewer for GitHub pull requests. Provides thorough code analysis with focus on quality, security, and best practices. Use when reviewing PRs for code quality and potential issues.
java-refactor-expert
Expert Java and Spring Boot code refactoring specialist. Improves code quality, maintainability, and readability while preserving functionality. Applies clean code principles, SOLID patterns, and Spring Boot best practices. Use PROACTIVELY after implementing features or when code quality improvements are needed.
general-code-reviewer
Provides code review capability for bugs, logic errors, security vulnerabilities, and quality issues using confidence-based filtering to report only high-priority issues. Use when reviewing code changes or before merging pull requests.
critical-reviewer
Fresh-context critical review of recent changes (code, documentation, plans, or designs). Read-only. Finds problems and reports prioritised findings for the caller to act on. Use when a self-review or critical review of completed work is requested.
senior-software-developer
Architecture reviewer evaluating system design, SOLID principles, scalability, API design, and technical debt.