Call Claude

Name: Call Claude
Author: stablyai

stablyai/call-claude

3 installs
7 repo stars
Updated April 25, 2026
stablyai/call-claude

Helps with ai & agent building tasks during AI-assisted development.

About

call-claude is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.

call-claude
AI & Agent Building
AI-coding skill

Call Claude by the numbers

3 all-time installs (skills.sh)
Ranked #13,657 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Jul 27, 2026 (Skillselion catalog sync)

npx skills add https://github.com/stablyai/call-claude --skill call-claude

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/stablyai/call-claude.svg)](https://skillselion.com/skills/stablyai/call-claude)

Installs	3
repo stars	★ 7
Last updated	April 25, 2026
Repository	stablyai/call-claude ↗

What it does

Helps with ai & agent building tasks during AI-assisted development.

Files

SKILL.mdMarkdownGitHub ↗

call-claude

Delegate an arbitrary prompt to Claude and return the output.

Arguments

Required: a prompt.

Optional flags (parsed from the user's message):

Flag	Values	Default
`--model`	`opus`, `sonnet`, `haiku`, or a full model ID	`opus`
`--effort`	`low`, `medium`, `high`, `xhigh`, `max`	_(omitted)_

Process

1. Parse the user's message — extract the prompt and any --model / --effort overrides. 2. Invoke the wrapper script that ships alongside this SKILL.md:

   "$(dirname "$0")/call-claude.sh" [--model <alias>] [--effort <level>] "<prompt>"

For multi-line prompts, pipe via stdin:

   echo "<prompt>" | "$(dirname "$0")/call-claude.sh" --model opus

3. Return Claude's full output to the user. Don't summarize unless asked.

claude -p is non-interactive and prints the final answer to stdout, so the wrapper output can be captured directly.

Prerequisite

Claude Code must be installed — verify with claude --version.

Examples

# Default (opus)
./call-claude.sh "explain what this repo does"

# Override model
./call-claude.sh --model sonnet "summarize the README"

# Override model + effort
./call-claude.sh --model opus --effort high "design a caching layer"

#!/usr/bin/env bash
# call-claude: thin wrapper around `claude -p` for use by agents (Codex, Cursor, etc.)
#
# Usage (after `npm i -g github:stablyai/call-claude`):
#   call-claude [--model <alias>] [--effort <level>] "<prompt>"
#   echo "<prompt>" | call-claude [--model <alias>] [--effort <level>]
#
# Or with zero install:
#   npx github:stablyai/call-claude [--model <alias>] [--effort <level>] "<prompt>"
#
# Defaults:
#   --model opus
#
# Flags:
#   --model <alias>   opus | sonnet | haiku | <full-model-id>   (default: opus)
#   --effort <level>  low | medium | high | xhigh | max          (omitted by default)

set -euo pipefail

MODEL="opus"
EFFORT=""
PROMPT=""

while [[ $# -gt 0 ]]; do
  case "$1" in
    --model)
      MODEL="$2"; shift 2 ;;
    --effort)
      EFFORT="$2"; shift 2 ;;
    --help|-h)
      sed -n '2,17p' "$0" | sed 's/^# \{0,1\}//'; exit 0 ;;
    --)
      shift; PROMPT="$*"; break ;;
    *)
      PROMPT="$*"; break ;;
  esac
done

ARGS=(-p --model "$MODEL")
[[ -n "$EFFORT" ]] && ARGS+=(--effort "$EFFORT")

if [[ -n "$PROMPT" ]]; then
  exec claude "${ARGS[@]}" "$PROMPT"
elif [[ ! -t 0 ]]; then
  # stdin has a prompt piped in
  exec claude "${ARGS[@]}"
else
  echo "error: no prompt provided (pass as argument or via stdin)" >&2
  exit 2
fi