Checker Summarizer — Security agent for Claude Code
Runs a given checker CLI command and returns a compact, structured verdict — never the raw output.
How to install Checker Summarizer
Installs to ~/.claude/agents/dannybrown37-skill-tree-checker-summarizer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dannybrown37/skill-tree/HEAD/agents/checker-summarizer.md -o ~/.claude/agents/dannybrown37-skill-tree-checker-summarizer.md Restart Claude Code, or start a new session, for it to be picked up.
What Checker Summarizer does
name: checker-summarizer description: Runs a given checker CLI command and returns a compact, structured verdict — never the raw output. Use for deterministic audit/lint/check tools whose output is a PASS/FAIL/MANUAL-style table but whose next step is "judge the flagged items." model: haiku tools: Bash, Read, Grep
Run exactly the command you're given. Do not modify flags, retry with different options, or "fix" anything — you are a reporter, not a decision-maker.
Report back in this sha
Alternatives in Security
- Claude Code System Prompts — by Piebald AI - All parts of Claude Code's system prompt, including builtin tool descriptions, sub agent promp 6.3k ★
- Project Auditor — Read-only health audit of the VibeFrame monorepo 165 ★
- Rust-claude-code-api V0.6.0 Quality Audit Report — Date: 2026-02-11 Auditors: Claude Code (team lead) + Codex (security) + Gemini CLI (API ergonomics) Method: 3 152 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Rust Unsafe Auditor
Use to audit Rust unsafe blocks, FFI boundaries (extern "C", bindgen / cbindgen / pyo3 / napi-rs / wasm-bindge
Audit Reporter
Deterministic report assembly — aggregates verdicts and findings, builds the Scope Coverage table, severity ro
Fallow
Run a codebase-intelligence audit (fallow) scoped to working-tree changes and report raw findings — dead code,
Tool Caller
Runs well-defined, high-output mechanical tool calls (test, lint and security runs, wide searches, doc lookups
Cavet Security
Runs a cavet security scan for the given scope and phase, triages every finding, and returns the CLI's structu
Cloud Auditor
Authenticated AWS cloud-configuration audit for a contracted engagement. Given an AWS CLI profile + slug, runs
Related Skills
LinkedIn Post Analyser
Claude Code / Cowork skill that scores a drafted LinkedIn post across 7 platform dimensions before you publish
Chess Verdict
Claude skill that gives a verdict on a chess position: reads a board diagram or FEN, runs Stockfish, and retur
Claude Compact Keeper
Compaction without amnesia: the summarizer is told to keep your goal, constraints, decisions and paths verbati