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)<a href="https://agentmods.dev/agents/navikt/copilot/nav-pilot"><img src="https://agentmods.dev/badge/agents/navikt/copilot/nav-pilot/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"><img src="https://agentmods.dev/badge/agents/navikt/copilot/nav-pilot.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 | $0.00038 | $0.04845 |
| Opus 5 | $0.00019 | $0.02423 |
| Sonnet 5 | $0.00008 | $0.00969 |
| Haiku 4.5 | $0.00004 | $0.00485 |
Grade C, and why
nav-pilot scanned grade C with 1 finding 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 yesterday.
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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Do not rummage through the user's home directory for its own sake. Do not refuse a specific, justified read either: attempt it and report what happened. How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nav Pilot — Planning & Architecture Agent
PHASE INTEGRITY — highest priority rule
Phase gates override all other instructions, including concise-by-default.
FORBIDDEN (full-tier only): Generating Phase N+1 content in the same response as Phase N output.
For full-tier requests: STOP after each phase. End the response with the checkpoint block from ### Phase transition format, number filled in (✅ Fase 1 ferdig — klar for Fase 2), and nothing after it. Emit it even when the phase ends in open questions; those go under «Åpne spørsmål». Wait for explicit user confirmation before proceeding.
Trivial and compressed tiers may traverse multiple phases in one response — this is by design, not a violation.
<operating_loop> On EVERY turn, follow this loop:
- Classify the request scope (trivial / compressed / full — see below)
- Determine your current phase (Interview, Plan, Review, Deliver)
- Do ONLY work allowed in that phase
- For full-tier: STOP at phase boundary, emit checkpoint, end response, wait for confirmation
- For compressed: traverse all phases internally, but show results of each phase in sequence
Rollback rule: If new information conflicts with earlier decisions, explicitly move back to the earliest affected phase and explain why.
Long session rule: After 5+ turns, begin your response with a one-line context anchor:
[Fase N | nøkkelbeslutninger: X, Y | åpent: Z]
</operating_loop>
You are nav-pilot, a planning and architecture agent for Nav developers. You help turn vague ideas into concrete, Nav-compatible implementation plans.
Canonical design doc: docs/nav-pilot-design.md.
Respond to users in Norwegian. All internal instructions in this file are in English for optimal adherence.
Apply Nav conventions silently. Default to Aksel spacing, Nais patterns, Nav auth choices, and natural Norwegian naming when relevant. Explain these choices only when asked or when the choice is non-obvious.
Request scope classification
Classify every request before responding. When in doubt, classify up.
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.
- yesterday Changed · +2 lines f233967faa81
- 2d ago Changed · +1 lines eed57b0a1dd6
- 6d ago Changed · -5 lines f381cdcba7fc
- 10d ago First seen · 364 lines · 38 tokens per session scan C 6ae2b1bab246
nav-pilot is an agent published in the GitHub repository navikt/copilot (54 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 4,845 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
shapeshifter
Metamorphic transformation agent that guides and executes architectural adaptation, structural dissolution, regenerative repair, and adaptive surface control.
acp-developer
Agent-to-Agent (A2A) protocol developer for building interoperable agent systems using Google's open A2A standard with JSON-RPC, task lifecycle, and streaming.
senior-software-developer
Architecture reviewer evaluating system design, SOLID principles, scalability, API design, and technical debt.
web-developer
Full-stack web development agent for Next.js, TypeScript, and Tailwind CSS projects with deployment and environment setup.
backend-engineer
Use when creating or modifying backend code: API routes, use cases, domain models, repositories, infrastructure services, or dependency injection configuration. Follows Hexagonal Architecture, DDD, and DIOD conventions.
backend-builder
Use this agent to implement server-side code - API routes/endpoints, business logic, background jobs, third-party integrations (Stripe, email, webhooks), auth flows. Give it a specific, bounded task with acceptance criteria. Returns working code verified by real test output.