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 editing-clojure-filesgit 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/editing-clojure-files)<a href="https://agentmods.dev/skills/betterthantomorrow/calva-backseat-driver/editing-clojure-files"><img src="https://agentmods.dev/badge/skills/betterthantomorrow/calva-backseat-driver/editing-clojure-files/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/editing-clojure-files"><img src="https://agentmods.dev/badge/skills/betterthantomorrow/calva-backseat-driver/editing-clojure-files.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 | $0.00135 | $0.02076 |
| Opus 5.5 | $0.00054 | $0.00830 |
| Sonnet 5.5 | $0.00027 | $0.00415 |
| Haiku 4.5 | $0.00014 | $0.00208 |
Grade A, and why
editing-clojure-files 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 1mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editing Clojure Files
Clojure code is a tree of forms, not lines of text. The unit of editing is the top-level form: ns, defn, def, (comment ...), etc. The structural editing tool clojure_edit_files understands this structure, auto-balances brackets via Parinfer, and returns post-edit diagnostics. Use clojure_edit_files whenever a structural edit is possible.
Delegation
Unless you have been specifically tasked with editing files yourself, always delegate file editing to a subagent. This protects the context window and isolates errors. Prefer the Clojure-editor subagent when available.
When delegating: Provide exact file paths, REPL-verified code with proper indentation, target line info, decision context, and explicit edit order instructions.
Code Shape for Tool Success
Structural editing tools operate on whole top-level forms — they read, transform, and rewrite the entire form in one pass. Smaller, simpler forms have higher success rates.
Thresholds
| Metric | Target |
|---|---|
| Function length | |
| Nesting depth | Under 4 levels |
| Cyclomatic complexity | Under 9 branches |
Code smells that break structural edits
- Large Method — Over ~25 lines. Split at responsibility boundaries; use
defn-helpers so each is an independently editable top-level form. - Deep Nested Complexity — 3+ levels of
let/when/if/condinside each other. Use threading macros (->,->>) to flatten transformations. Extract inner bodies into named functions. - Bumpy Road — Alternating simple and complex sections in one function. Each bump is a misalignment point. One responsibility per function.
- Complex Method — Many conditional branches in one function. Keep
case/cond/condpbranch bodies to one-liners or calls. Prefer data-driven dispatch (defmethod, maps of keyword → handler) over deep conditional trees. - Code Duplication — Repeated structure across functions. Extract once; each duplicate doubles the chance of structural mismatch during edits.
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.
- 1mo ago First seen · 148 lines · 135 tokens per session scan A 000876533770
editing-clojure-files is a skill published in the GitHub repository BetterThanTomorrow/calva-backseat-driver (63 stars, last pushed 6d ago), licensed MIT. It adds 135 tokens to every session and 2,076 once invoked, about $0.0005 per session on Opus 5.5. 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…
jetbrains-session
Use when working on the JetBrains chat session UI or SessionModel/SessionController — transcript cards, retained Swing lifecycle, session background surfaces, editor-derived styling, adding session events, and session/controller testing with FakeSessionRpcApi.
icon-jetbrains
Create or review IntelliJ New UI SVG icons, theme variants, sizes, and palette.
pr-track-v1
Create a GitHub tracking issue in Kilo-Org/kilocode that captures a merged Kilo v1 PR's behavior so it can be re-implemented or verified in opencode v2. Use when the user invokes /pr-track-v1 or asks to track a v1 core fix/feature for the v2 rewrite.
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.).