What is caveman-code CLAUDE.md?

A guide to caveman-cli, a TypeScript monorepo containing a terminal coding agent and supporting packages. A monorepo is one repository that contains several related packages, such as the agent runtime, terminal interface, and software-development kit.

Use it when changing caveman-cli's coding agent, language-model integrations, agent runtime, terminal interface, SDK, or shared package workflows.

It shows which packages belong to the main product, what each one does, and which commands build, lint, and format them. This helps agents work in the correct package and follow project conventions.

How JuliusBrussee/caveman-code configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to JuliusBrussee/caveman-code. 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/JuliusBrussee/caveman-code/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/JuliusBrussee/caveman-code

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/juliusbrussee/caveman-code/claude-md/github.svg)](https://agentmods.dev/instructions/juliusbrussee/caveman-code/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/juliusbrussee/caveman-code/claude-md"><img src="https://agentmods.dev/badge/instructions/juliusbrussee/caveman-code/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/juliusbrussee/caveman-code/claude-md"><img src="https://agentmods.dev/badge/instructions/juliusbrussee/caveman-code/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 957 This file is loaded in full into every session.

When invoked 957 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.

Model	Per session	Once invoked
Fable 5.1	$0.00957	$0.00957
Opus 5.5	$0.00383	$0.00383
Sonnet 5.5	$0.00191	$0.00191
Haiku 4.5	$0.00096	$0.00096

Measured 2mo ago against content hash 7dd3b9f66c12, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

caveman-code CLAUDE.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 2mo 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.

CLAUDE.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CAVE CLI — caveman-cli

Minimal terminal coding agent + multi-provider LLM toolkit. TypeScript monorepo.

Packages

Package	CLI	Purpose
v2 core (load-bearing):
`packages/coding-agent`	`caveman`	Coding agent: sessions, extensions, skills, themes, slash commands, subagents
`packages/ai`	`pi-ai`	Unified LLM API: OpenAI, Anthropic, Google, more
`packages/agent`	—	Agent runtime: tool calling, loop, state, system-prompt/toolFilter/maxTurns
`packages/tui`	—	Terminal UI: differential rendering, chord input, notifications
`packages/sdk`	—	`@juliusbrussee/caveman-sdk` — TS client for caveman-code daemon HTTP+WS API (openapi-generated)
`packages/markdown-preview`	—	Markdown renderer used by TUI

Key Commands

npm install          # install all deps
npm run build        # build all packages
npm run lint         # biome lint
npm run format       # biome format

Context Hierarchy

See context/CLAUDE.md. The active plan is context/plans/cave-v2-best-in-class.md. Legacy CaveKit kits/plans/impl have been moved to context/archive/.

Conventions

Biome for lint/format (not ESLint/Prettier). Config: biome.json.
TypeScript strict. Shared tsconfig: tsconfig.base.json.
Package scope: @juliusbrussee/caveman-* (all packages on npm). Main CLI package: @juliusbrussee/caveman-code. Bin registers caveman AND caveman-code aliases.
Node.js 20+.

Current State (2026-05-01)

No permission system. Sandbox/permissions/approval-prompts stripped on branch strip/permissions. Caveman Code runs autopilot. Don't reintroduce. See memory feedback_no_permissions.
Plan mode wired. /plan enters read-only chat mode (no edits, no shell writes); /act exits. Slash command at packages/coding-agent/src/core/slash-commands/plan.ts. Plan-mode gating also enforced inside the Task tool for spawned subagents.
Subagents. Registry + SendMessage tool in coding-agent. Subagent isolation honored by Task tool. Agent definitions use tool constraints instead of removed permissionMode frontmatter.
AgentSession features: checkpoints, repomap, chat mode, soft compaction, hooks, MCP, skills, recipes, /clear, /quick-open, /task-list.
Goal loop (in-flight, untracked): packages/coding-agent/src/core/goal-loop/ — goal-runner, goal-state, goal-prompts. Not yet committed; dev work on strip/permissions.
Walkthrough doc: context/notes/agent-loop-walkthrough.md traces the full path from caveman boot → interactive-mode dispatch → session.prompt → agent-loop.runLoop. Read this first when touching the loop.

Read the full file on GitHub · 74 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.

2mo ago First seen · 74 lines · 957 tokens per session scan A 7dd3b9f66c12

Subscribe to this mod's changes

caveman-code CLAUDE.md is an instructions file published in the GitHub repository JuliusBrussee/caveman-code (947 stars, last pushed 2mo ago), licensed MIT. It adds 957 tokens to every session, about $0.0038 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.

Building agents

caveman-code CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
caveman-code CLAUDE.mdJuliusBrussee/caveman-code	Instructions file	947	2mo ago	MIT	A	957	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

caveman-code: Instructions file for Claude Code