Help us improve
Share bugs, ideas, or general feedback.
From ai-cli
Guides writing ai-cli mode files to configure non-interactive Claude Code agents with locked system prompts, model selection, and prompt wrappers. Use when authoring custom modes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-cli:modes-authoringThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Modes are markdown files that configure non-interactive Claude Code sessions via the Agent SDK. Each mode defines a system prompt, model, and optional prompt wrapper — producing a preconfigured, fire-and-forget agent.
Share bugs, ideas, or general feedback.
Modes are markdown files that configure non-interactive Claude Code sessions via the Agent SDK. Each mode defines a system prompt, model, and optional prompt wrapper — producing a preconfigured, fire-and-forget agent.
| Location | Scope | Precedence |
|---|---|---|
.claude/.ai/modes/<name>.md | Project-local | Wins over built-in |
ai-cli/modes/<name>.md | Built-in (bundled) | Fallback |
---
model: opus
system-prompt-mode: append
---
| Field | Required | Values | Default |
|---|---|---|---|
model | Yes | Any valid model ID | — |
system-prompt-mode | No | append, replace | append |
append — mode's system prompt is appended to the default Claude Code system prompt. The agent retains all standard capabilities.replace — mode's system prompt completely replaces the default. Use for fully custom agent personas.Everything after the frontmatter (before ## Prompt Wrapper if present) becomes the system prompt content.
---
model: claude-sonnet-4-5-20250929
system-prompt-mode: append
---
You are a security auditor. Report vulnerabilities only — never edit code.
Focus on: injection, auth bypass, data exposure, SSRF.
A ## Prompt Wrapper heading defines a template applied to the user's -p argument. Use {{prompt}} as the placeholder.
---
model: opus
system-prompt-mode: append
---
You are a systematic debugger. Investigate only — no code changes.
## Prompt Wrapper
Debug the following issue. Diagnose root cause — don't fix.
Issue description:
{{prompt}}
Without a prompt wrapper, the -p argument is passed directly as the user prompt.
# Built-in mode
ai -m review -p "src/auth/"
# Project-local mode
ai -m security-audit -p "check the API layer"
# List all available modes (built-in + local)
ai -l
append for most modes — the agent keeps Claude Code's full toolset; you're just narrowing its focusreplace sparingly — only when you need a completely custom personageneral — sonnet, append, no wrapper. Minimal: "direct, efficient assistant"debug — opus, append, wrapper frames input as "Issue description". Multi-phase methodology in system prompt.review — opus, append, wrapper frames input as review target. Detailed concern taxonomy in system prompt.Modes are callable from hooks, scripts, and other tools:
# In a pre-commit hook
ai -m validate-commit -p "$(git diff --cached)"
# In a CI script
ai -m review -p "$(git diff origin/main...HEAD)"
npx claudepluginhub crouton-labs/crouton-kit --plugin ai-cliProvides reference for configuring Claude Code with CLAUDE.md templates, best practices, thinking keywords, debugging tips, and advanced usage patterns. Useful for agentic coding workflows.
Guides new Claude Code users interactively through environment setup (CLAUDE.md, permissions, model selection), first session (explore-plan-implement, Plan Mode), and best practices (specific prompts, git safety, self-testing loops).
Claude Code extensibility and configuration reference: plugins, hooks, skills, subagents, MCP servers, output styles, memory, settings, and model configuration. Invoke whenever Claude Code itself is the subject — questions, configuration, building extensions, debugging, or understanding internals.