calva-backseat-driver: Instructions file for Codex

AGENTS.md

calva-backseat-driver AGENTS.md is an instructions file for Codex, OpenCode from BetterThanTomorrow/calva-backseat-driver. It costs 3,441 tokens per session, scanned A, original, MIT.

Developer instructions for a ClojureScript VS Code extension that gives AI agents access to a running REPL, an interactive programming environment. They explain the application state and the system that separates state changes from side effects such as I/O.

In plain words
What is it for?
Use them when adding actions or effects, inspecting runtime state, writing tests, or changing the extension’s REPL, MCP, and language-model integrations.
Why use it?
They help contributors preserve the extension’s data flow and runtime boundaries. This makes changes easier to test and reduces errors from mixing pure logic with external actions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is BetterThanTomorrow/calva-backseat-driver's own configuration. It tells Codex and OpenCode how to work on calva-backseat-driver itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything calva-backseat-driver configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BetterThanTomorrow/calva-backseat-driver. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/BetterThanTomorrow/calva-backseat-driver/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/BetterThanTomorrow/calva-backseat-driver

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for calva-backseat-driver AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/betterthantomorrow/calva-backseat-driver/agents-md.svg)](https://agentmods.dev/instructions/betterthantomorrow/calva-backseat-driver/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/betterthantomorrow/calva-backseat-driver/agents-md"><img src="https://agentmods.dev/badge/instructions/betterthantomorrow/calva-backseat-driver/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,441 This file is loaded in full into every session.
When invoked 3,441 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03441 $0.03441
Opus 5 $0.01721 $0.01721
Sonnet 5 $0.00688 $0.00688
Haiku 4.5 $0.00344 $0.00344

Measured 8d ago against content hash 8e1fa81569a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

calva-backseat-driver AGENTS.md 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 8d 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.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Calva Backseat Driver - AI Agent Guide

ClojureScript VS Code extension providing REPL access to AI agents via Language Model API and MCP. Enables Interactive Programming where AI evaluates code in the user's running environment rather than guessing.

When authoring code and test, ask yourself: Will this and the tests work on Windows too?

Essential Architecture

Action/Effect System ("Ex")

Functional core with unidirectional flow:

dispatch! → handle-actions → [enrich → route] → {:ex/db, :ex/fxs, :ex/dxs} → update state → execute effects

Actions (*/axs.cljs): Pure functions returning state changes and effects Effects (*/fxs.cljs): Side effect handlers with dispatch access State: Single app-db atom in src/calva_backseat_driver/app/db.cljs

Runtime State Structure

The app-db atom contains:

{:vscode/extension-context    ; VS Code extension API access
 :app/log-file-uri            ; Logging location
 :app/min-log-level           ; :debug/:info/:warn/:error
 :mcp/wrapper-config-path     ; ~/.config/calva/backseat-driver
 :calva/output-line-counter   ; Monotonic line counter for output entities
 :calva/history-storage-uri   ; Workspace-scoped Transit file for persistent history
 :extension/disposables       ; VS Code subscriptions
 :extension/when-contexts}    ; Context keys for enablement

Datascript Connections

  • !output-conn — Session-scoped, schemaless. All REPL output categories. Cap: 1000 entities.
  • !history-conn — Persistent, :output/line unique identity schema. evaluatedCode only. Cap: 10000 entities. Persisted to eval-history.transit.json under context.storageUri.

Calva API Integration

Available at calva-backseat-driver.integrations.calva.api/calva-api:

{:repl     {:evaluateCode, :currentSessionKey, :onOutputLogged
            :listSessionsAndRuntimes, :onSessionsChanged}
 :ranges   {:currentTopLevelForm, :currentEnclosingForm, ...}
 :editor   {:replace}
 :document {:getNamespace, :getNamespaceAndNsForm}
 :info     {:getSymbolInfo, :getClojureDocsDotOrg}}

Read the full file on GitHub · 260 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. 8d ago First seen · 260 lines · 3,441 tokens per session scan A 8e1fa81569a7

Subscribe to this mod's changes

calva-backseat-driver AGENTS.md is an instructions file published in the GitHub repository BetterThanTomorrow/calva-backseat-driver (64 stars, last pushed 10d ago), licensed MIT. It adds 3,441 tokens to every session, about $0.0172 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens