agentmods.dev

copilot: Instructions file for GitHub Copilot

.github/copilot-instructions.md

copilot copilot-instructions.md is an instructions file for GitHub Copilot from navikt/copilot. It costs 1,115 tokens per session, scanned A, original, MIT.

A set of coding instructions for Nav's GitHub Copilot ecosystem, a group of tools for managing Copilot access, usage data, and related MCP services. It describes the repository's applications, deployment platform, and development standards.

In plain words
What is it for?
It helps develop the subscription portal, backend API, usage-metrics job, and MCP registry or onboarding service while following Nav's architecture, security, and delivery practices.
Why use it?
It gives agents the project structure and shared engineering rules needed to make consistent changes across several applications and services.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions AGENTS.md; mentions OpenCode.

This is navikt/copilot's own configuration. It tells GitHub Copilot how to work on copilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything copilot configures →

not rated 56repo +1 changed 9d ago A scan 1,115 tokens original MIT
View source ↗ navikt/copilot ki-utvikling.nav.no
Reuse

Borrowing it

Nothing to install: this file belongs to navikt/copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/navikt/copilot/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/navikt/copilot

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for copilot copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/navikt/copilot/copilot-instructions/github.svg)](https://agentmods.dev/instructions/navikt/copilot/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/navikt/copilot/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/navikt/copilot/copilot-instructions/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.

agentmods 80×15 button for copilot copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/navikt/copilot/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/navikt/copilot/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,115 This file is loaded in full into every session.
When invoked 1,115 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01115 $0.01115
Opus 5.5 $0.00446 $0.00446
Sonnet 5.5 $0.00223 $0.00223
Haiku 4.5 $0.00112 $0.00112

Measured 9d ago against content hash 5e49849cc33c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

copilot copilot-instructions.md 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 9d 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.

.github/copilot-instructions.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot instructions for navikt/copilot

Monorepo for Nav's Copilot ecosystem and AI developer tooling:

  • apps/my-copilot: Next.js 16 and Aksel web portal (Zone 1 public routes and Zone 2 authenticated BFF)
  • apps/copilot-api: Go backend API for GitHub Copilot and BigQuery data (Zone 3 internal backend, plus /public/v1/videos* in Zone 1)
  • apps/copilot-cli: Go proxy that verifies GitHub App user tokens for nav-pilot
  • apps/copilot-survey: Go service and PostgreSQL store for anonymous surveys (Zone 3 internal backend)
  • apps/copilot-metrics: Go batch job for GitHub Copilot usage and billing metrics
  • apps/copilot-adoption: Go batch job scanning navikt repositories for AI adoption
  • apps/mcp-registry: Go service serving the Nav MCP allowlist
  • apps/mcp-onboarding: Go reference MCP server with OAuth 2.1 and PKCE
  • cli/nav-pilot: Go CLI that installs customizations and launches Copilot or OpenCode
  • agents/, skills/, instructions/, prompts/, hooks/: Distributable customizations synced to Nav repositories

Read AGENTS.md for workflow rules and SECURITY.md for the security model and trust boundaries.

Security and trust boundaries

  • Three-zone architecture (SECURITY.md):
    • Zone 1 (public): Unauthenticated routes in my-copilot (autoLoginIgnorePaths not in PRIVATE_*_PATHS) and /public/v1/videos* in copilot-api. Must serve no sensitive user, billing, or internal data.
    • Zone 2 (protected BFF): Authenticated pages and /api/* routes in my-copilot. src/proxy.ts introspects bearer tokens via Texas and exchanges them via OBO before calling Zone 3 backends. my-copilot holds no GitHub App keys or BigQuery credentials.
    • Zone 3 (internal backend APIs): copilot-api (holds the GitHub App private key and BigQuery access) and copilot-survey (PostgreSQL survey store). Both validate Entra ID JWTs (azp caller allowlist via JWKS / Texas) and honour X-On-Behalf-Of only when the token represents an application (idtyp=app / access_as_application).
  • copilot-survey anonymity: Validates Entra ID bearer tokens through Texas (auth.go), stores HMAC-hashed participant keys in survey_participation and unlinked answers in survey_answers (no user ID or timestamp), and must never log caller identities or hold GitHub credentials.
  • copilot-cli authentication: Verifies ghu_ tokens against GitHub (POST /applications/{client_id}/token), checks active navikt organization membership fail-closed, validates login against GitHub's username format, and forwards the verified username to copilot-api via X-On-Behalf-Of.
  • cli/nav-pilot hostile repo boundary: Treat target repositories and .nav-pilot/ or opencode.json configs as untrusted. Reject symlinks in artifact directories and exports (source.CheckSymlink), never expand arbitrary host environment variables into OpenCode configs, and never run nav-pilot in tests without testhome.Run and isolatedConfig(t).
  • No secrets or PII in code or logs: Never commit credentials or tokens. Never log tokens, Authorization headers, SAML nameId values, emails, or raw SQL errors containing user input.

Read the full file on GitHub · 37 lines

Changes

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.

  1. 9d ago Changed · -446 lines · -2,807 tokens per session 5e49849cc33c
  2. 1mo ago Changed · +11 lines · +153 tokens per session 53d80cd88245
  3. 1mo ago First seen · 472 lines · 3,769 tokens per session scan A 9b76cfe5eb04

Subscribe to this mod's changes

copilot copilot-instructions.md is an instructions file published in the GitHub repository navikt/copilot (56 stars, last pushed today), licensed MIT. It adds 1,115 tokens to every session, about $0.0045 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.

agentscopilotmcpskills
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens