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 skills add BetterThanTomorrow/calva-backseat-driver --skill backseat-driver-testinggit clone --depth 1 https://github.com/BetterThanTomorrow/calva-backseat-driverWrote 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.
[](https://agentmods.dev/skills/betterthantomorrow/calva-backseat-driver/backseat-driver-testing)<a href="https://agentmods.dev/skills/betterthantomorrow/calva-backseat-driver/backseat-driver-testing"><img src="https://agentmods.dev/badge/skills/betterthantomorrow/calva-backseat-driver/backseat-driver-testing/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.
<a href="https://agentmods.dev/skills/betterthantomorrow/calva-backseat-driver/backseat-driver-testing"><img src="https://agentmods.dev/badge/skills/betterthantomorrow/calva-backseat-driver/backseat-driver-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00106 | $0.08098 |
| Opus 5 | $0.00053 | $0.04049 |
| Sonnet 5 | $0.00021 | $0.01620 |
| Haiku 4.5 | $0.00011 | $0.00810 |
Grade A, and why
backseat-driver-testing 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 10d 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 — 618 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backseat Driver Testing Skill
Strategies and patterns for testing the Backseat Driver MCP server toolset. Each section is self-contained — run one section, a few, or all of them depending on what needs testing.
When to Use This Skill
- After bumping Backseat Driver dependencies and rebuilding
- When testing new or modified tool parameters
- When validating structural editing, REPL evaluation, or output log behavior
- When testing shadow-cljs runtime discovery (
includeAllRuntimes) or targeted evaluation (targetRuntimeId) - When debugging who-tracking or cross-evaluator awareness
Before You Start
Call clojure_list_sessions immediately. Both a clj (JVM Clojure) and a bb (Babashka) session are expected. If either is missing, use #askQuestions to tell the user which REPL(s) are absent and ask them to start the REPL(s) before continuing. Do not proceed with REPL-dependent tests without these sessions unless the user responds that it is okay to continue without them.
Test Scope
Match the user's request to the relevant section(s). When asked to "run a full test" or "smoke test the extension," work through all sections. When asked to test something specific ("test the bracket balancer," "check who-tracking"), go directly to that section.
Section index — each section lists its own prerequisites:
- REPL Session Listing — no prerequisites
- Shadow-cljs Runtime Targeting — requires shadow-cljs REPL connected with at least one live runtime (manual gate; see section)
- REPL Evaluation — requires session listing first
- Load File — requires session listing first
- Structural Editing — requires session listing first
- Output Log Queries — requires some prior REPL evaluations to have populated the log
- Symbol Info and ClojureDocs — requires session listing first
- Bracket Balancer — no prerequisites, no REPL needed
- Bundled Skills — no prerequisites; client-agnostic discovery/load check
- Skills Opt-Out — requires toggling VS Code settings (manual)
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.
- 10d ago First seen · 618 lines · 106 tokens per session scan A 28a23e26e2de
backseat-driver-testing is a skill published in the GitHub repository BetterThanTomorrow/calva-backseat-driver (64 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 8,098 once invoked, about $0.0005 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 skills, from other repositories
vscode-visual-regression
Write Storybook stories and visual regression tests for the Kilo VS Code extension webview UI.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
lore
SpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence, and interactively forge the chosen ones into skills installed across all your agent harnesses. Use when the user…
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.
unit-test-generator
Automatically generate unit tests based on source code, supporting multiple languages and testing frameworks.