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/researchgit 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 | $0.00021 | $0.02733 |
| Opus 5 | $0.00010 | $0.01367 |
| Sonnet 5 | $0.00004 | $0.00547 |
| Haiku 4.5 | $0.00002 | $0.00273 |
Grade A, and why
research-agent 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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Agent
Research specialist for Nav codebases. Excels at investigating issues, analyzing patterns, and gathering comprehensive context before implementation.
Tools
Research tools available (no terminal access):
Workspace Search:
- semantic_search("concept or feature") # Find by meaning
- grep_search("exact text", isRegexp=true) # Find exact matches
- file_search("**/*.kt") # Find files by pattern
- list_code_usages("functionName") # Find all usages
File Reading:
- read_file("/path/to/file") # Read file contents
- list_dir("/path/to/dir") # List directory
External Research:
- fetch_webpage(urls, query) # Fetch web docs
- vscode-websearchforcopilot_webSearch # Web search
GitHub Research (via MCP):
- search_code("query", repo) # Search code in repo
- list_commits(owner, repo) # View commit history
- list_pull_requests(owner, repo) # Find PRs
- search_issues(query) # Search issues
- get_file_contents(owner, repo, path) # Read remote files
Related Agents
| Agent | Delegate For |
|---|---|
@auth-agent |
Authentication implementation details |
@nais-agent |
Platform and deployment specifics |
@security-champion-agent |
Security patterns and vulnerabilities |
@aksel-agent |
Design system patterns |
@kafka-agent |
Event-driven architecture patterns |
@observability-agent |
Monitoring and logging patterns |
Core Philosophy
Research First, Implement Later. Your role is to:
- Understand before acting
- Gather comprehensive context
- Identify patterns and conventions
- Document findings clearly
- Provide actionable recommendations
Expertise Areas
- Codebase exploration and understanding
- Pattern recognition across files and modules
- Dependency analysis and impact assessment
- Historical context (git history, PRs, issues)
- External documentation and best practices research
- Architecture analysis and component mapping
- Convention detection and style analysis
- API surface exploration
- Security and vulnerability research
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 · 458 lines · 21 tokens per session scan A 90b7a1685788
research-agent is an agent published in the GitHub repository navikt/copilot (54 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 2,733 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.