win4r

Claude Code Dynamic Workflows — Security skill for Claude Code

Security community

Four reusable dynamic-workflow templates for Claude Code (multi-dimension review, exhaustive audit, budget-scaled bug hunt, judge-panel design) + an offline validator.

How to install Claude Code Dynamic Workflows

This entry records only its repository, not the path inside it, so there is no exact command to give. Open win4r/claude-code-dynamic-workflows and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Code Dynamic Workflows does

Four reusable dynamic-workflow templates for Claude Code (multi-dimension review, exhaustive audit, budget-scaled bug hunt, judge-panel design) + an offline validator.

Alternatives in Security

  • /web3 Audit — Smart contract security audit using the 10-bug-class methodology 927 ★
  • Bountyforge — All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, T 399 ★
  • Raptor Loop Hunt — RAPTOR autonomous looping multi-altitude security vulnerability hunt — Claude Code skill 212 ★

README

claude-code-dynamic-workflows

Four reusable **[dynamic workflow](https://code.claude.com/docs/en/workflows)** templates for [Claude Code](https://claude.com/claude-code) — drop them into `~/.claude/workflows/` and invoke them by name. Each one encodes a repeatable, multi-agent quality pattern (adversarial verification, loop-until-dry discovery, budget-scaled fan-out, judge-panel synthesis) so you get a more trustworthy result than a single pass.

Every script is verified against the runtime's loader contract by the included [`validate.js`](#validating).


What is a dynamic workflow?

A dynamic workflow is **a JavaScript script that orchestrates subagents at scale**. Claude writes the script for the task you describe, and a runtime executes it in the background — in an isolated environment, separate from your conversation — while your session stays responsive. ([docs](https://code.claude.com/docs/en/workflows))

The key idea is *"moving the plan into code."* With plain subagents, skills, or agent teams, Claude is the orchestrator and decides turn-by-turn what to spawn — and every result lands in its context window. **A workflow script holds the loop, the branching, and the intermediate results itself, so Claude's context holds only the final answer.** That's what makes it practical to fan out to dozens or hundreds of agents, and to apply patterns a single pass structurally can't — like having independent agents adversarially review each other's findings before anything is reported. ([blog](https://claude.com/blog/introducing-dynamic-workflows-in-claude-code))

Subagents / skills / agent teams Dynamic workflow
Who decides what runs next Claude, turn by turn The script
Where intermediate results live Claude's context window Script variables
What's repeatable The worker definition The orchestration itself
Interruption Restarts the turn Resumable in the same session

Requirements

-