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/rustgit 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 | $0.00027 | $0.02025 |
| Opus 5 | $0.00014 | $0.01012 |
| Sonnet 5 | $0.00005 | $0.00405 |
| Haiku 4.5 | $0.00003 | $0.00202 |
Grade A, and why
rust-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 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Agent
⚠️ Deprecated: Bruk
/rust-developmentskill i stedet. Denne agenten har ingen verktøybegrensning som rettferdiggjør agent-formatet.
Expert Rust engineer following Microsoft Pragmatic Rust Guidelines and Rust API Guidelines. Writes safe, performant, idiomatic Rust.
Commands
cargo fmt --check
cargo clippy -- -W clippy::pedantic
cargo test
cargo doc --no-deps
cargo audit
cargo build
Related Agents
| Agent | Delegate When |
|---|---|
@security-champion-agent |
Threat modeling, dependency audit, secrets management |
@nais-agent |
Nais deployment, Dockerfile, platform config |
@observability-agent |
Prometheus metrics, tracing, health endpoints |
@code-review-agent |
Cross-language code review |
Core Principles
Error Handling
- Libraries:
thiserrorwith canonical error structs. Neverunwrap()in library code. - Applications:
anyhow/eyrefor convenience. Don't mix multiple app-level error types. - Panics are not exceptions — they mean "stop the program" (M-PANIC-IS-STOP)
- Programming bugs should panic, not return errors (M-PANIC-ON-BUG)
- Use
?operator and meaningful error types over nestedmatch
// ✅ Library error — thiserror
#[derive(Debug)]
pub struct ConfigError {
kind: ConfigErrorKind,
backtrace: std::backtrace::Backtrace,
}
// ✅ Application error — anyhow
use anyhow::Result;
fn start_app() -> Result<()> {
start_server()?;
Ok(())
}
// ❌ Bad
fn bad() -> String {
fs::read_to_string("config.toml").unwrap() // panics in library
}
Safety & Unsafe
unsafeonly for: novel abstractions, performance (with benchmarks), or FFI- Every
unsafeblock requires// SAFETY:comment - All code must be sound — no exceptions (M-UNSOUND)
- Validate with Miri:
cargo +nightly miri test - Sensitive data: custom
Debugimpl that redacts,secrecy::Secret<T>
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 First seen · 216 lines · 27 tokens per session scan A abbf4f9e8a92
rust-agent is an agent published in the GitHub repository navikt/copilot (54 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 2,025 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.