claude-wayfinder

Q: How to install claude-wayfinder?

Create the skills directory: mkdir -p .claude/skills. Then run: mkdir -p .claude/skills && curl -o .claude/skills/claude-wayfinder.md https://raw.githubusercontent.com/glitchwerks/claude-wayfinder/main/SKILL.md. Finally, /claude-wayfinder in Claude Code.

Q: What is claude-wayfinder best for?

claude-wayfinder is categorized under General. It covers: agent.

New

1GitHubGeneralby glitchwerks

Deterministic, auditable agent/skill dispatch for Claude Code. A typed seven-decision scoring kernel runs after the router has read the conversation — post-cognitive routing instead of prose-scanning. Auto-generates its catalog from skill sidecars and agent frontmatter.

First seen 6/7/2026

Summary

It automatically generates its catalog from skill sidecars and agent frontmatter, enabling reliable routing to the right skill or agent for any task.
This skill is useful for developers who need predictable, traceable orchestration of multiple agents or skills in complex workflows.

Install & Usage

Create the skills directory

mkdir -p .claude/skills

Download the skill file

mkdir -p .claude/skills && curl -o .claude/skills/claude-wayfinder.md https://raw.githubusercontent.com/glitchwerks/claude-wayfinder/main/SKILL.md

Invoke in Claude Code

/claude-wayfinder

Use Cases

Route a security audit request to the appropriate vulnerability scanning agent based on conversation context.

Dispatch a code review task to a specialized agent for static analysis without ambiguity.

Automatically select the correct deployment skill when a user asks to push code to production.

Audit which agent handled a previous request by inspecting the scoring kernel's decision log.

Seamlessly integrate new skills into the catalog without manual configuration by leveraging sidecar metadata.

Ensure compliance with organizational policies by enforcing deterministic routing rules for sensitive operations.

Usage Examples

/claude-wayfinder route 'scan this repository for SQL injection vulnerabilities'

Use Wayfinder to dispatch a request to the code review agent for the latest commit.

/claude-wayfinder audit last decision --show-scores

View source on GitHub

agent

Security Audits

LicenseUnknownSourceWarnRepositoryPass

Frequently Asked Questions

What is claude-wayfinder?

Claude Wayfinder provides deterministic, auditable agent dispatch for Claude Code by using a typed seven-decision scoring kernel that evaluates conversations post-cognition, rather than scanning prose. It automatically generates its catalog from skill sidecars and agent frontmatter, enabling reliable routing to the right skill or agent for any task. This skill is useful for developers who need predictable, traceable orchestration of multiple agents or skills in complex workflows.

How to install claude-wayfinder?

To install claude-wayfinder: create the skills directory (mkdir -p .claude/skills), then run: mkdir -p .claude/skills && curl -o .claude/skills/claude-wayfinder.md https://raw.githubusercontent.com/glitchwerks/claude-wayfinder/main/SKILL.md. Finally, /claude-wayfinder in Claude Code.

What is claude-wayfinder best for?

claude-wayfinder is a skill categorized under General. It is designed for: agent. Created by glitchwerks.

What can I use claude-wayfinder for?

claude-wayfinder is useful for: Route a security audit request to the appropriate vulnerability scanning agent based on conversation context.; Dispatch a code review task to a specialized agent for static analysis without ambiguity.; Automatically select the correct deployment skill when a user asks to push code to production.; Audit which agent handled a previous request by inspecting the scoring kernel's decision log.; Seamlessly integrate new skills into the catalog without manual configuration by leveraging sidecar metadata.; Ensure compliance with organizational policies by enforcing deterministic routing rules for sensitive operations..