Drive the botfile CLI to manage AI-agent skills, instructions, and commands. Use when asked to sync, plan, adopt, or check the status of agent components managed by botfile.
Installation
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Drive the botfile CLI to manage AI-agent skills, instructions, and commands. Use when asked to sync, plan, adopt, or check the status of agent components managed by botfile.
botfile
botfile manages AI-agent skills, instructions, and commands as symlinks from source repositories you control.
This skill carries botfile's operator guide. The CLI prints the same guide: run botfile guide (or botfile guide --format markdown|json); it is also published at botfile.org/agents.html. If botfile is not on PATH, install it first (with the user's agreement) per botfile.org.
Model
source: A local directory, often a git checkout, holding curated components. botfile reads it in place; git does any fetching.
plugin: A named bundle inside a source. Even a single-bundle source has an explicit plugin directory: <source>/<plugin>/.
component: A typed artifact under a plugin. Kinds today: a skill (a directory with a SKILL.md), an instruction (a .md file), and a command (a .md file the agent exposes as a slash command).
selection: A config rule mapping a source (and optionally one plugin or component) to one or more agents that should receive it.
botfile operates at user scope only: the per-user paths under your home directory. It never writes into a project checkout (a repo's .claude/ or an in-repo AGENTS.md); project-scoped components belong to the project.
Selections fan out: one component reaches every agent its selections name, one symlink per agent's native path, and agents reading the shared ~/.agents/skills pool are served by a single link. Symlinks, not copies, so an edit to the source is live through every agent at once.
The kinds differ in how they reach the model: an instruction is ambient (the harness injects it into every session), so it matters that instructions can be scoped to all, some, or one agent; a skill is on-demand: its name and description always sit in context and its body loads when the model matches it to the task or the user invokes it; a command is a prompt file the user runs explicitly (/name). On-demand kinds are cheap when idle, not free. Not every agent supports commands; the agents table shows a dash where a kind has no native surface.
A selection picks any depth of source > plugin > component: omit plugin and component for the whole source, set plugin for one bundle, set both for a single component (component is <kind>/<name>, like skill/review).
An omitted plugin or component is a wildcard; an unknown config key is rejected rather than ignored, so a typo cannot silently widen a selection.
Workflow
Run in this order; only run sync after the user agrees.
botfile status: See what is managed, out of sync, and adoptable. Read-only, safe to run anytime.
botfile plan: Preview the exact symlinks a sync would create or remove. Read-only; changes nothing.
confirm with the user: Show the plan and get the user's agreement before changing anything on disk.
botfile sync: Apply the plan only after the user agrees: create and remove symlinks to match the config.
botfile adopt --into /: If sync reports a conflict (a real file where botfile wants a link), adopt that file into a source instead of overwriting it. botfile never clobbers.
Commands
Command
Does
botfile plan
show what a sync would change
botfile sync
reconcile your agents to match your config
botfile status
show what is managed, out of sync, and adoptable
botfile adopt <path> --into <source>/<plugin>
bring an agent-created component under management
botfile guide
print this guide (text, markdown, or json)
botfile version
print the version
botfile upgrade [--check]
replace this binary with the latest release, checksum-verified (--check: report only)
Agents
Agent
Skills
Instructions
Commands
claude-code
~/.claude/skills/<name>/
~/.claude/rules/<name>.md
~/.claude/commands/<name>.md
codex-cli
~/.agents/skills/<name>/
~/.codex/AGENTS.md
~/.codex/prompts/<name>.md
copilot-cli
~/.agents/skills/<name>/
~/.copilot/copilot-instructions.md
-
copilot-vscode
~/.agents/skills/<name>/
~/.copilot/instructions/<name>.instructions.md
-
crush
~/.agents/skills/<name>/
~/.config/crush/CRUSH.md
-
opencode
~/.agents/skills/<name>/
~/.config/opencode/AGENTS.md
~/.config/opencode/commands/<name>.md
pi.dev
~/.agents/skills/<name>/
~/.pi/agent/AGENTS.md
~/.pi/agent/prompts/<name>.md
JSON for agents
Every command accepts --format json. Prefer it: parse the structured report rather than scraping text.
The JSON envelope carries schemaVersion, command, phase, outcome, exitCode, plus ops, notes, issues, and summary counts.
exitCode is authoritative: 0 ok, 1 blocked (a conflict or broken config refused the change), 2 a usage or effect error.
plan and status never modify anything; only sync and adopt change the filesystem, and upgrade replaces botfile's own binary (checksum-verified, never in the background).
