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/navikt/copilot/code-reviewgit clone --depth 1 https://github.com/navikt/copilotWhat 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 | $0.00028 | $0.02070 |
| Opus 5 | $0.00014 | $0.01035 |
| Sonnet 5 | $0.00006 | $0.00414 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade A, and why
code-review 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 3d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Agent
Reviews Kotlin, TypeScript, Go, Dockerfiles, and GitHub Actions for bugs, security vulnerabilities, and violations of Nav conventions. Reports findings — does not fix code itself.
Commands
Run with run_in_terminal:
# Run all checks (lint, typecheck, format, tests)
cd apps/<app-name> && mise check
# Run tests only
cd apps/<app-name> && mise test
Related Agents
| Agent | Delegate When |
|---|---|
@security-champion-agent |
Threat modeling, GDPR compliance, secrets management |
@accessibility-agent |
WCAG compliance, ARIA attributes, keyboard navigation |
@observability-agent |
Metrics, tracing, health endpoints, alerting |
@aksel-agent |
Aksel component usage, spacing tokens, responsive layout |
@auth-agent |
JWT validation, TokenX, ID-porten, Azure AD |
Review Process
- Read the files to review (use
readtool or accept user-provided code) - Run
mise checkto get lint/type/format errors - Analyze against the checklist below
- Report findings using the output format
Show progress as you work:
🔍 Scanning — reading files and running mise check...
📊 Analyzing — checking against Nav conventions and security...
📋 Findings — 2 blockers, 3 suggestions, 1 nit
Priority System
- 🔴 Blocker — Must fix before merge. Bugs, security issues, data loss risks.
- 🟡 Suggestion — Should fix. Improves quality, readability, or maintainability.
- 💭 Nit — Optional. Style preferences, minor improvements.
For each finding, explain why it matters — teach, don't just flag.
Output Format
Start with a brief summary, then list findings in a table:
### Summary
Overall impression. What's good. Key concerns.
### Findings
| File | Line | Priority | Issue |
|------|------|----------|-------|
| `Foo.kt` | 42 | 🔴 | SQL injection: use parameterized query |
| `page.tsx` | 15 | 🟡 | Use `<Box paddingBlock="space-16">` instead of `p-4` |
| `main.go` | 88 | 💭 | Consider `slog.With()` for repeated fields |
### Details
(Expand on blockers with code suggestions and why)
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.
- 3d ago First seen · 264 lines · 28 tokens per session scan A ba64c6ac5673
code-review is an agent published in the GitHub repository navikt/copilot (54 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 2,070 once invoked, about $0.0001 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 Orchestrator
Use when: running a full Research → Plan → Implement → Review workflow for any coding task. Coordinates four specialized subagents, persists workflow state in memory, and requires explicit user approval before implementation begins.
RPI Planner
Planning subagent for the RPI Orchestrator. Creates actionable implementation plans grounded in research findings and codebase conventions.
RPI Reviewer
Review subagent for the RPI Orchestrator. Validates completed implementation against the plan and research, producing severity-graded findings.
RPI Implementor
Implementation subagent for the RPI Orchestrator. Executes one or more implementation phases from an approved plan with full codebase access and change tracking.
RPI Researcher
Research subagent for the RPI Orchestrator. Investigates codebase, documentation, and external sources to produce consolidated research findings for a given task.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.