Claude Code mod
layer0-compose
Moves the top-priority rule list (Layer 0) from per-turn UserPromptSubmit injection into the system prompt, where prompt caching applies. The injected copy is removed only when the system prompt really carries the same text.
Install
git clone https://github.com/chami1221-eng/my-ai-workbench.git
claude --plugin-dir ./my-ai-workbench/mods/layer0-composeThe repo has no marketplace file, so load the plugin folder directly with --plugin-dir.
What it can access
- Reach
- L1Reads: reads files, reads env vars
- Sees
- classic hooks
- Hooks
session.startprompt.composeclassic.UserPromptSubmitcommand.run
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- chami1221-eng/my-ai-workbench
- Folder
mods/layer0-compose- License
- Apache-2.0
- Last updated
- 15 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is layer0-compose?
Moves the top-priority rule list (Layer 0) from per-turn UserPromptSubmit injection into the system prompt, where prompt caching applies. The injected copy is removed only when the system prompt really carries the same text. It is a mod for Claude Code, from chami1221-eng/my-ai-workbench on GitHub.
What can the layer0-compose mod access?
Its widest reach is "reads" (reads files, reads env vars). It sees classic hooks. Like any mod, it runs with your permissions.
How do I install layer0-compose?
Clone chami1221-eng/my-ai-workbench and start Claude Code with --plugin-dir pointing at the mod's folder (mods/layer0-compose).
More guard & safety mods
harness
Paradox07127/claude-utopia
Skills and guard hooks: ai-code-cleanup, interrogate, shape-task, verify-change, setup, a shared-worktree git guard, and a guard against reading API-key config files
mission-control
aecheman27-gif/claude-mods
Mission-control skin: [SYS]/[TOOL]/[EDIT] tool rows with per-tool icons and one status block above the prompt (under flightdeck's session log while its pane is open): [SYS] repo, branch, model, hw-guard; [CTL] model and effort buttons; [CTX] context fill with a /ctx pane by tool. /clean for a checklist view.
guardrails
azoof-ahmed/claude-mods
A lint gate for Claude's edits: your project's rules, a baseline of existing violations, and a PreToolUse check that refuses only edits adding new ones.
mod-firewall
bbarney7/claude-code-mods
A firewall for Claude Code mods: watches what every other mod does (network, processes, secret files, env vars) and asks, blocks or logs
entregas
plasdigital/mods-claude-code-kit-aluno
Guarda todo arquivo que a IA cria ou edita, em qualquer conversa: /entregas lista com link, e um "cadê" já chega respondido
redact
JinhaoFang/claude-mods
Rewrites sensitive data (emails, IPs, credentials, addresses) out of what enters the model context
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.