calc1f4r

Finding Chain Synthesizer — Security agent for Claude Code

Security community

Chains confirmed audit findings into multi-step, cross-domain exploit candidates and searches for a unique emergent exploit path that is not visible from any single finding.

How to install Finding Chain Synthesizer

Installs to ~/.claude/agents/calc1f4r-horus-finding-chain-synthesizer.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/calc1f4r/Horus/HEAD/.claude/agents/finding-chain-synthesizer.md -o ~/.claude/agents/calc1f4r-horus-finding-chain-synthesizer.md

Restart Claude Code, or start a new session, for it to be picked up.

What Finding Chain Synthesizer does

name: finding-chain-synthesizer description: "Chains confirmed audit findings into multi-step, cross-domain exploit candidates and searches for a unique emergent exploit path that is not visible from any single finding. Use after triage, judging, or confirmation when CONFIRMED-REPORT.md, 05-findings-triaged.md, issues/, or judge outputs exist. Requires maximum-depth reasoning, concrete reachability proofs, and produces exploit-chain-candidates.md/json for protocol-reasoning and poc-writing."

Alternatives in Security

  • Token Auditor — Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d 79.4k ★
  • Security Analyzer (Synthesizer) — You consolidate findings from research agents into prioritized hypotheses 215 ★
  • After Confirming A Vulnerability — findings.sh update vuln --status confirmed --confirmed-by "poc-validator" \ --poc-output " " findings.sh updat 213 ★

Full documentation available on GitHub

View Source Repository

Related Agents

POC Engineer — Security agent for Claude Code

POC Engineer

Given a confirmed finding + its context worksheet, produces the smallest self-contained crate that reproduces

Security community
POC Builder — Security agent for Claude Code

POC Builder

Build a minimal proof of concept for a confirmed security finding. Writes a failing test, a small script, or a

Security community
Security Triage — Security agent for Claude Code

Security Triage

Independently evaluate a single security finding to decide whether it is a real, exploitable vulnerability or

Security community
Worthiness Evaluator — Security agent for Claude Code

Worthiness Evaluator

Advisory test-worthiness audit for the emergent surface. Reads only the phase''s changed test files plus their

Security community
Code Review Agent — Security agent for Claude Code

Code Review Agent

Independent code review with no knowledge of how the code was written - security, quality, documentation, arch

Security community
Nextjs Verifier — Security agent for Claude Code

Nextjs Verifier

Independently verifies a Next.js SDD implementation against acceptance criteria, lint, type checks, tests, bui

Security community

Related Skills

POC — Security skill for Claude Code

POC

Generate an executable proof-of-concept exploit for a confirmed High/Critical finding — detect the toolchain,

Security community
Chain Findings — Security skill for Claude Code

Chain Findings

Escalate low-severity findings into reportable vulnerabilities by building exploit chains (A→B→C)

Security community
Claude Skill — Development skill for Claude Code

Claude Skill

🔍 Enhance code searches with ast-grep, finding patterns in your code structure for improved error handling an

Development community