agentmods.dev

testing-rustyclaw-cli

A testing guide for RustyClaw, a Rust command-line tool with terminal-interface and desktop options.

In plain words
What is it for?
Use it to build the CLI without desktop dependencies, run Rust tests, check gateway errors, run Clippy, and test swarm commands such as creating and messaging groups of agents.
Why use it?
It collects build, test, lint, and end-to-end commands in one place, including commands for multi-agent swarm features.

Skill for Claude CodeCodex

59 8d ago A scan 36 tokens original MIT
View the source file rexlunae/RustyClaw
Install

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.

agentmods
npx agentmods add skills/rexlunae/rustyclaw/testing-rustyclaw-cli
Any agent
npx skills add rexlunae/RustyClaw --skill testing-rustyclaw-cli
Clone the repo
git clone --depth 1 https://github.com/rexlunae/RustyClaw

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,621 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.01621
Opus 5 $0.00018 $0.00811
Sonnet 5 $0.00007 $0.00324
Haiku 4.5 $0.00004 $0.00162

Measured 2d ago against content hash bd34e9b6aa24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing-rustyclaw-cli 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.

.agents/skills/testing-rustyclaw-cli/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing RustyClaw CLI

Build

The CLI binary is in the rustyclaw package (crate path: crates/rustyclaw-cli).

# Minimal build (TUI only, no desktop/GPU deps):
cargo build -p rustyclaw --no-default-features --features tui

# Binary location:
target/debug/rustyclaw

Feature flags:

  • tui — terminal UI (ratatui). Use this for CLI-only testing.
  • desktop — Dioxus desktop UI. Requires GTK/webkit libs; skip on headless VMs.
  • Default features include both; use --no-default-features --features tui to avoid desktop build deps.

Unit Tests

# Full test suite:
cargo test -p rustyclaw-core

# Focused error module tests:
cargo test -p rustyclaw-core -- gateway::errors::tests --nocapture

# Clippy (treat warnings as errors):
cargo clippy -p rustyclaw-core -- -D warnings -A clippy::needless_option_as_deref

Swarm Commands

The swarm subcommand manages multi-agent orchestration:

rustyclaw swarm templates    # List available swarm templates
rustyclaw swarm list         # List active swarms (empty by default)
rustyclaw swarm create [TEMPLATE]  # Create swarm (default: swarm)
rustyclaw swarm send <SWARM> <MESSAGE>  # Send message to swarm
rustyclaw swarm status <SWARM>   # Show swarm status
rustyclaw swarm stop <SWARM>     # Stop a swarm

Gateway Error Handling Architecture

The gateway error system lives in crates/rustyclaw-core/src/gateway/errors.rs.

GatewayError Enum

All gateway errors are unified into a GatewayError enum with variants:

  • Auth { provider, message } — authentication failures (401/403)
  • Provider { message } — generic model provider errors
  • TokenLimit — context window exceeded
  • ToolLoopExhausted { rounds } — tool call loop limit
  • ContextCompaction { message } — non-fatal compaction failure
  • Cancelled — user cancellation
  • Vault { message } — vault/secret storage errors
  • DeviceFlow { message } — OAuth device flow failures
  • Config { message } — configuration errors
  • TokenRefresh { message } — OAuth token refresh failures
  • UnexpectedFinish { reason } — model finished with unusual finish_reason

Read the full file on GitHub · 148 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. 2d ago First seen · 148 lines · 36 tokens per session scan A bd34e9b6aa24

Subscribe to this mod's changes

testing-rustyclaw-cli is a skill published in the GitHub repository rexlunae/RustyClaw (59 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 1,621 once invoked, about $0.0002 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.

E2E testingTesting
Related

Other skills, from other repositories

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

studio-e2e-tests

Write and run Playwright E2E tests for Supabase Studio (e2e/studio). Use when asked to run e2e tests, write new E2E tests, or debug flaky or failing Playwright tests. Covers running commands, avoiding race conditions, waiting strategies, selectors, helper functions, and CI vs local differences.

supabase/supabase · 74 tokens

playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

microsoft/playwright · 19 tokens

agent-host-e2e-tests

Use when writing, recording, updating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for Claude/Copilot/Codex). Covers adding a cross-provider test…

microsoft/vscode · 104 tokens

smoke-test

End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…

bytedance/deer-flow · 0 tokens

deploy-release-test

Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the teste2edeployrelease.yml GitHub Actions workflow. Use only when asked to run the full deploy test suite or this workflow specifically from an internal vercel/next.js PR branch. Do not use for…

vercel/next.js · 115 tokens