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 | $0.06080 |
| Opus 5.5 | $0.00015 | $0.02432 |
| Sonnet 5.5 | $0.00008 | $0.01216 |
| Haiku 4.5 | $0.00004 | $0.00608 |
Grade A, and why
nav-pilot 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 — 347 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 there and wait for explicit user confirmation before proceeding. Ending a phase with questions outstanding is normal and is not a reason to keep going.
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, 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.
| Tier | Criteria | Phase behaviour |
|---|---|---|
| Trivial | Single file, bug fix, rename, config change, no new data flows, no auth changes, no security-critical code | Single-pass, no phase stops |
| Compressed | Multi-file, known pattern, no new service boundary, no new data flows or auth changes, no security-critical code | Traverse all phases internally, show phase results in one response |
| Full | New service, new data flow, new auth, major refactor that changes behaviour, security-critical code | Full phase loop with mandatory stops between each phase |
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 763a798b2896
- 3d ago Changed 1b67c4cd0ebd
- 11d ago Changed 71e46ac2868c
- 12d ago Changed · -9 lines 2339a650aeb7
- 13d ago Changed · +1 lines 92bc5b172dd1
- 14d ago Changed · +2 lines 018471685b00
- 18d ago Changed · +24 lines 8c6cbe9101b5
- 19d ago Changed · +4 lines 4aadbcc545ec
- 20d ago Changed · +4 lines 2ba916f4de76
- 27d ago First seen · 321 lines · 38 tokens per session scan A c2ec92805bae
nav-pilot is an agent published in the GitHub repository navikt/copilot (57 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 6,080 once invoked, about $0.0002 per session on Opus 5.5. 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
wordpress-development-expert
Expert WordPress developer that provides custom plugin and theme development capabilities. Masters WordPress coding standards, hooks/filters architecture, Gutenberg blocks, REST API, WooCommerce integration, and site/portal development. Use PROACTIVELY for WordPress plugin development, theme customization, Gutenberg…
nestjs-testing-expert
NestJS testing specialist that provides unit tests, integration tests, end-to-end tests, test database setup, mocking strategies, and testing best practices. Use proactively when writing tests for NestJS applications, setting up testing infrastructure, creating test fixtures, mocking dependencies, or implementing…
php-software-architect-expert
Expert PHP software architect that provides guidance on Clean Architecture, Domain-Driven Design (DDD), and modern PHP patterns. Reviews PHP codebases (Laravel, Symfony) for architectural integrity, proper module organization, and SOLID principles. Use PROACTIVELY for PHP architectural decisions, DDD modeling, and…
nestjs-unit-testing-expert
Expert in unit testing with NestJS, Jest, and testing utilities that provides comprehensive test strategies, test architecture, and testing best practices for TypeScript applications. Use PROACTIVELY for writing unit tests, improving test coverage, or reviewing testing strategies in NestJS applications.
nestjs-database-expert
NestJS database specialist that provides expertise in Drizzle ORM setup, schema design, migrations, queries, transactions, and database operations. Use proactively when working with database-related code in NestJS applications, setting up Drizzle ORM, creating migrations, writing queries, or optimizing database…
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.