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-drivergit 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)<a href="https://agentmods.dev/skills/betterthantomorrow/calva-backseat-driver/backseat-driver"><img src="https://agentmods.dev/badge/skills/betterthantomorrow/calva-backseat-driver/backseat-driver/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"><img src="https://agentmods.dev/badge/skills/betterthantomorrow/calva-backseat-driver/backseat-driver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 8 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
- medium Rogue Agent · line 97 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00186 | $0.03151 |
| Opus 5 | $0.00093 | $0.01576 |
| Sonnet 5 | $0.00037 | $0.00630 |
| Haiku 4.5 | $0.00019 | $0.00315 |
Grade A, and why
backseat-driver 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 11d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backseat Driver — Effective Tool Usage
"Use the REPL" means: call the clojure_evaluate_code tool. This is the Backseat Driver tool that evaluates code in Calva's connected REPL — the same REPL the user is connected to. Always use this tool rather than launching a terminal REPL. If there is no REPL connection, ask the user to connect one.
Step 0: Add Clojure skills
Scan your available skills for Clojure-related ones. If you see a skill named Clojure, or a skill being about Clojure, read it in full and internalize its content.
In lack of Clojure skills
If you don't see such a skill available, tell the user to install the clojure plugin from the Awesome Backseat Driver marketplace. Give these instructions:
1. From the VS Code command palette run: **Chat: Install Plugin from Source**
1. Paste: https://github.com/BetterThanTomorrow/awesome-backseat-driver
1. Select **clojure**
Core Principles
-
ClojureDocs before guessing — Before using any core function you the very least unsure about how to use effectively, call
clojuredocs_info. You will get docstrings, argument lists, community examples, and gotchas. What's not to love? -
Structural editing for structural code — Clojure is a structural language. Use the structural editing tools, not generic text replacement. See
dev/tool-instructions/editing-clojure-files.mdfor detailed workflows.
The Workflow
Every task — implementing, debugging, planning, reviewing — follows this loop:
- ORIENT → clojure_list_sessions (know your REPLs)
- RESEARCH → clojuredocs_info / clojure_symbol_info / clojure_evaluate_code (understand the functions)
- EXPLORE → clojure_evaluate_code (test ideas in the REPL)
- BUILD UP → clojure_evaluate_code (compose verified pieces)
- APPLY → structural editing tools (edit files with verified code — check returned linter diagnostics)
- VERIFY → clojure_load_file / clojure_evaluate_code (load file or namespace, call functions) + get_errors (Problems report)
- MONITOR → clojure_repl_output_log (side effects, errors) + get_errors (new warnings/errors)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 226 lines · 186 tokens per session scan A 44ab5def5dba
backseat-driver is a skill published in the GitHub repository BetterThanTomorrow/calva-backseat-driver (64 stars, last pushed today), licensed MIT. It adds 186 tokens to every session and 3,151 once invoked, about $0.0009 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
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…
icon-jetbrains
Create or review IntelliJ New UI SVG icons, theme variants, sizes, and palette.
release-jetbrains
Use when releasing the Kilo JetBrains plugin -- resolve a version ("next rc" or explicit), run the prepare workflow, edit and commit a filtered human-readable changelog on the release PR, then watch publish to completion.
chart
Use when the user asks to visualize data with charts, graphs, or plots using the chart tool (bar, line, scatter, pie, time series, etc.).
gh-issues
Use when creating, triaging, or commenting on GitHub issues for the Kilo VS Code extension or JetBrains plugin via gh. Covers issue templates, project board assignment, title conventions, and required gh scopes.