agentmods.dev

clave: Instructions file for Claude Code

CLAUDE.md

clave CLAUDE.md is an instructions file for Claude Code from codika-io/clave. It costs 4,137 tokens per session, scanned A, original, MIT.

Project instructions for Clave, a Mac desktop app that runs multiple coding-agent command-line sessions, terminals, and remote agents side by side.

In plain words
What is it for?
Use them when developing Clave, including running its checks, building macOS packages, updating its companion plugin, and handling signing or notarization.
Why use it?
They give an agent the commands, architecture, conventions, and release requirements needed to work consistently in the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is codika-io/clave's own configuration. It tells Claude Code how to work on clave 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 clave configures →

not rated 47repo changed 1mo ago A scan 4,137 tokens original MIT
View source ↗ codika-io/clave
Reuse

Borrowing it

Nothing to install: this file belongs to codika-io/clave. 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/codika-io/clave/prod/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/codika-io/clave

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.

agentmods badge for clave CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/codika-io/clave/claude-md/github.svg)](https://agentmods.dev/instructions/codika-io/clave/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/codika-io/clave/claude-md"><img src="https://agentmods.dev/badge/instructions/codika-io/clave/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.

agentmods 80×15 button for clave CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/codika-io/clave/claude-md"><img src="https://agentmods.dev/badge/instructions/codika-io/clave/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,137 This file is loaded in full into every session.
When invoked 4,137 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.04137 $0.04137
Opus 5.5 $0.01655 $0.01655
Sonnet 5.5 $0.00827 $0.00827
Haiku 4.5 $0.00414 $0.00414

Measured 1mo ago against content hash 0296c77a8d09, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

clave CLAUDE.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **PATH resolution in packaged app (CRITICAL)**: Packaged Electron apps have a minimal PATH (`/usr/bin:/bin:/usr/sbin:/sbin`). The user's full PATH must be resolved by spawning a login shell. **NEVER use `execSync`** —
CLAUDE.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clave

Mac desktop app for managing multiple coding-agent CLI sessions in parallel. Provider-agnostic: it orchestrates Claude Code (Cmd+N), Antigravity CLI (Cmd+I), Codex CLI (Cmd+U), and Pi (Cmd+Shift+P) sessions side by side, plus plain terminals (Cmd+T) and remote agents over OpenClaw. Electron + React + TypeScript.

Clave's companion agent plugin (clave, exposing /clave:create-workspace and /clave:recover-sessions) ships from plugin/ in this repo — see plugin/CLAUDE.md. It is installed with npx plugins add codika-io/clave, resolved through .claude-plugin/marketplace.json at the root. The Electron app reads installed plugins from ~/.claude/plugins/ at runtime and never reads plugin/ directly; the folder is here so a .clave format change and the skill that describes it land in the same commit (see the schema sync rule below).

Commands

  • npm run dev — start dev (Electron window + hot reload)
  • npm run build — typecheck + build
  • npm run build:mac — build + package macOS universal dmg + zip (signed + notarized)
  • npm run typecheck — typecheck only
  • npm run lint — eslint
  • Releases ship via CI on push to prod (bump from a [minor]/[major] commit-message marker, else patch) — see .claude/rules/release.md. npm run release -- --patch|--minor|--major remains the local fallback.

Architecture

Three-process Electron app:

  • Main (src/main/): Electron window, node-pty, IPC handlers, domain managers. Agent PTYs spawn through launch profiles as <shell> -l -c '<wrapper>', where the shell is the user's own while it speaks POSIX and Clave's (/bin/zsh on macOS, /bin/sh elsewhere) when it does not — Nushell and Fish cannot parse the wrapper (src/main/shell-launch.ts). IPC handlers are split into modular files under ipc-handlers/.
  • Preload (src/preload/): Typed window.electronAPI via contextBridge. All main↔renderer communication goes through IPC.
  • Renderer (src/renderer/src/): React + Zustand + xterm.js + Tailwind v4 + Framer Motion.

Read the full file on GitHub · 93 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. 1mo ago Changed · +1 lines · +216 tokens per session 0296c77a8d09
  2. 1mo ago Changed · +2 lines · +155 tokens per session 3182fcb39030
  3. 1mo ago Changed · +141 tokens per session ebe222ccf6a7
  4. 1mo ago First seen · 90 lines · 3,625 tokens per session scan A 4178c4411f53

Subscribe to this mod's changes

clave CLAUDE.md is an instructions file published in the GitHub repository codika-io/clave (47 stars, last pushed 1mo ago), licensed MIT. It adds 4,137 tokens to every session, about $0.0165 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Codeclaudedeveloper-toolselectronmacosterminal
Related

Other instructions, from other repositories

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 · 9,715 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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens