/looper
Design and scaffold a Looper agent loop.
$ npx -y skills add ksimback/looper --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/looper
Context preview
What this command does when you run it.
Design and scaffold a Looper agent loop.
Command definition
looper.mddescription: Design and scaffold a Looper agent loop.
argument-hint: [target-dir] [--template <name>]
allowed-tools: Read, Write, Bash
/looper
Run the Looper skill as an explicit slash command.
Arguments from the user: `$ARGUMENTS`
Resolve Looper
Find the Looper skill root before doing any loop-design work:
1. Prefer the global Claude Code skill install:
- Windows: `%USERPROFILE%\.claude\skills\looper`
- macOS/Linux: `$HOME/.claude/skills/looper`
2. If that directory does not contain `SKILL.md`, stop and tell the user to install Looper with the README instructions. 3. Read `SKILL.md` from that directory completely and follow its workflow exactly. Treat the located directory as `CLAUDE_SKILL_DIR` when running helper scripts.
Arguments
Parse `$ARGUMENTS` as `[target-dir] [--template <name>]`, in any order:
- If `--template` is present, take the next token as the template name and
follow the skill's Template Mode (the catalog lives at `templates/loops/` inside the skill directory). `--template` with no name means: show the catalog and ask.
- Remove `--template <name>` from the arguments first; everything left is the
target directory — treat it as a single path even if it contains spaces (e.g. `C:\My Loops\out`), and do not split it into multiple tokens. If nothing is left, use `./looper-output`.
Then continue with the Looper skill workflow.
Read more
description: Design and scaffold a Looper agent loop. argument-hint: [target-dir] [--template <name>] allowed-tools: Read, Write, Bash
/looper
Run the Looper skill as an explicit slash command.
Arguments from the user: `$ARGUMENTS`
Resolve Looper
Find the Looper skill root before doing any loop-design work:
1. Prefer the global Claude Code skill install:
- Windows: `%USERPROFILE%\.claude\skills\looper`
- macOS/Linux: `$HOME/.claude/skills/looper`
2. If that directory does not contain `SKILL.md`, stop and tell the user to install Looper with the README instructions. 3. Read `SKILL.md` from that directory completely and follow its workflow exactly. Treat the located directory as `CLAUDE_SKILL_DIR` when running helper scripts.
Arguments
Parse `$ARGUMENTS` as `[target-dir] [--template <name>]`, in any order:
- If `--template` is present, take the next token as the template name and
follow the skill's Template Mode (the catalog lives at `templates/loops/` inside the skill directory). `--template` with no name means: show the catalog and ask.
- Remove `--template <name>` from the arguments first; everything left is the
target directory — treat it as a single path even if it contains spaces (e.g. `C:\My Loops\out`), and do not split it into multiple tokens. If nothing is left, use `./looper-output`.
Then continue with the Looper skill workflow.
Design visual, review-gated agent loops for Claude Code before you run them.
Repo: ksimback/looper