Tool Caller — Security agent for Claude Code
Runs well-defined, high-output mechanical tool calls (test, lint and security runs, wide searches, doc lookups) and returns a compact result.
How to install Tool Caller
Installs to ~/.claude/agents/joshido-ai-template-tool-caller.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/joshido/ai-template/HEAD/.claude/agents/tool-caller.md -o ~/.claude/agents/joshido-ai-template-tool-caller.md Restart Claude Code, or start a new session, for it to be picked up.
What Tool Caller does
name: tool-caller description: Runs well-defined, high-output mechanical tool calls (test, lint and security runs, wide searches, doc lookups) and returns a compact result. No decisions. model: haiku gemini-model: flash copilot-model: Claude Haiku 4.5 (copilot) tools: Bash, Read, Glob, Grep, WebSearch, WebFetch
Tool Caller
Run exactly the tool calls you are asked for and return a compact result.
- Batch independent calls in parallel.
- Return the requested format. By default:
- Co
Alternatives in Security
- Token Auditor — Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d 79.4k ★
- Claude Code System Prompts — by Piebald AI - All parts of Claude Code's system prompt, including builtin tool descriptions, sub agent promp 6.3k ★
- General Technical Project Lead — Use this agent proactively when you need principal-level technical leadership for complex projects, performanc 248 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Infra Vuln Management
CVE prioritization and patch sequencing. Mostly mechanical lookups against your inventory. Peer to infra-secur
Claudemd Author
Invoked by /context to generate or audit ONE directory cluster's CLAUDE.md from the actual code, detected stac
Nextjs Verifier
Independently verifies a Next.js SDD implementation against acceptance criteria, lint, type checks, tests, bui
Checker Summarizer
Runs a given checker CLI command and returns a compact, structured verdict — never the raw output. Use for det
Project Auditor
Read-only health audit of the VibeFrame monorepo. Use for a periodic project review — structure, CLI/doc drift
Unity Security Reviewer
Reviews Unity projects for security vulnerabilities — PlayerPrefs secrets, unencrypted saves, hardcoded API ke
Related Skills
Livekit Agent Simulator
Black-box LiveKit voice agent testing: real WebRTC/SIP calls with an AI caller. Catch barge-in, noise, quiet-m
Elevenlabs Agent Caller
AI agent that makes phone calls for you. give it a task like ordering from a bakery and it dials the number, t
Researcher Skill
ReAct deep search skill for Claude Code. Searches deep, not wide — each round follows leads from the last.