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.
git 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/commands/betterthantomorrow/calva-backseat-driver/test-tools)<a href="https://agentmods.dev/commands/betterthantomorrow/calva-backseat-driver/test-tools"><img src="https://agentmods.dev/badge/commands/betterthantomorrow/calva-backseat-driver/test-tools/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/commands/betterthantomorrow/calva-backseat-driver/test-tools"><img src="https://agentmods.dev/badge/commands/betterthantomorrow/calva-backseat-driver/test-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00021 | $0.01082 |
| Opus 5 | $0.00010 | $0.00541 |
| Sonnet 5 | $0.00004 | $0.00216 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
test-tools 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 today.
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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backseat Driver Tool Smoke Tests
You are an AI agent testing the Backseat Driver MCP server tools by using them directly. These tools are designed for AI agents like you to perform Clojure development tasks.
Your mission is to manually exercise each Backseat Driver tool to validate:
- Core functionality works as expected when you use the tools
- Error handling provides clear, actionable feedback to you as an agent
- Edge cases related to fuzzy line matching and error context are handled gracefully
Important: This is NOT about writing or running automated tests. You will directly invoke each tool, observe the results, and verify they work correctly for agent-driven development workflows.
Test Workflow
Query Current Settings
Before testing, check the current fuzzy matching and error context settings using Joyride:
(require '["vscode" :as vscode])
(let [config (vscode/workspace.getConfiguration "calva-backseat-driver")]
{:fuzzy-line-targeting-padding (.get config "editor.fuzzyLineTargetingPadding")
:line-context-response-padding (.get config "editor.lineContextResponsePadding")})
Note the values for:
- fuzzyLineTargetingPadding (default: 2) - lines to search ±target line
- lineContextResponsePadding (default: 10) - lines shown in error messages
Create Test Files
Use the Create Clojure File tool to create these test files for different edge case scenarios:
- Main test file:
src/mini/tool_smoke_test_<round_number>.clj(standard size, 15+ lines) - Tiny file:
src/mini/tiny_edge_case.clj(only 3-4 lines total) - Similar lines file:
src/mini/similar_lines.clj(contains duplicate/similar code patterns)
Then test each category systematically:
1. Structural Editing Tools
Test the complete file editing lifecycle:
Create Clojure File
- Create new file with namespace and one simple function
- ✓ Verify: File created with valid syntax, no diagnostics errors
Append Code
- Add 1-2 functions to end of file
- ✓ Verify: Forms appended correctly, syntax remains valid
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.
- today First seen · 125 lines · 21 tokens per session scan A 989ed6fb3c73
test-tools is a command published in the GitHub repository BetterThanTomorrow/calva-backseat-driver (64 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,082 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 2026-09-10.
Other commands, from other repositories
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.
octo-loop
Your first output line MUST be: 🐙 Octopus Loop Mode.
code-review
Code review the current proposed code change.
octo-debug
Debug a symptom through reproducible, bounded evidence.
merge-conflict
Resolve a merge conflict.
api-aqa-flow-test-correction
Phase 7 Test Corrections of api-aqa-flow (USER APPROVAL REQUIRED).