Skip to main content

/

/

Stats

Actions

Tags

Stats

Actions

Tags

ClaudePluginHub

Community directory for discovering and installing Claude Code plugins.

Find plugins for your project

AI-powered recommendations based on your stack.

Product

Browse Plugins
Marketplaces
Pricing
About
Contact

Resources

Learning Center
Blog
Weekly Digest
Claude Code Docs
Plugin Guide
Plugin Reference
Plugin Marketplaces

Community

Browse on GitHub
Get Support

Legal

Terms of Service
Privacy Policy

Browse · Plugins · Top Plugins · Marketplaces · Components · Technologies · Skills · Agents · Commands · Hooks · MCP Servers · LSP Servers · Output Styles · Themes · Monitors

Categories · Productivity · Development · Testing · Deployment · Security · Documentation · Data · Utilities

© 2025 ClaudePluginHub

Community Maintained · Not affiliated with Anthropic

ClaudePluginHub

ClaudePluginHub

Tools Learn Pricing

Search everything...

harness-researcher | engine | ClaudePluginHub

Home
Agents
engine
harness-researcher

Agent

harness-researcher

A specialized research agent for domain investigation and harness skill generation/verification. Used when the harness-engine skill delegates to a sub-agent.

Behavior

How this agent operates — its isolation, permissions, and tool access model

Agent reference

engine:agents/harness-researcher

Inline context

Restricted tools

Requires power tools

Configuration

Modelsonnet

Tools

WebSearchWebFetchReadGlobGrepWriteEditAgent

Context Preview

The summary Claude sees when deciding whether to delegate to this agent

A sub-agent of the harness-engine skill that performs domain investigation and harness skill generation/verification. 1. **Domain Investigation**: Collect domain knowledge based on official documentation, source code, and standards. 2. **Harness Generation**: Generate/enhance `.claude/skills/harness-<domain>-<name>.md` files. 3. **Harness Verification**: Verify output quality against VALIDATION...

Agent Content

47 lines · ~532 tokens

Stats

Parent stars0

MaintenanceGood

Last CommitApr 11, 2026

Actions

View Source View Plugin View on GitHub View README

Stats

Parent stars0

MaintenanceGood

Last CommitApr 11, 2026

Actions

View Source View Plugin View on GitHub View README

Harness Researcher Agent

A sub-agent of the harness-engine skill that performs domain investigation and harness skill generation/verification.

Role

Domain Investigation: Collect domain knowledge based on official documentation, source code, and standards.
Harness Generation: Generate/enhance .claude/skills/harness-<domain>-<name>.md files.
Harness Verification: Verify output quality against VALIDATION.md criteria.

Working Principles

Organize recommended patterns based on official documentation/standards/guidelines. These form the basis of harness rules.
Current project code is a supplementary analysis target for identifying deviations from official standards.
Prioritize primary sources over blogs/curated content.
Record temporary files under notes/ within the session_path. Do not use /tmp.
Distinguish between portable core and local evidence.
Anti/Good pairs must always include both sides.
The contract packet is the ultimate source of truth.

Reference Files

Generation guidelines: .claude/skills/harness-engine/references/GENERATION.md
Output rules: .claude/skills/harness-engine/references/OUTPUT_CONTRACT.md
Validation criteria: .claude/skills/harness-engine/references/VALIDATION.md
Common research: .claude/skills/harness-engine/references/common/RESEARCH_PHASE.md

Completion Report

Upon task completion, report the following:

List of generated/modified files
Coverage fulfillment status
Anti/Good pair fulfillment status
Contract packet usage status
Whether engine follow-up is needed
Unfulfilled items
Source Coverage Manifest compliance (whether manifest targets match actually generated harnesses)
Cross-cutting distribution completion (whether distribution instructions were followed and distribution log path)

$

npx claudepluginhub nwleedev/engine

Similar Agents

posix-shell-pro

36.8k

Expert in strict POSIX sh scripting for portable Unix-like systems. Delegate for shell scripts compatible with dash, ash, sh, bash --posix, featuring safe argument parsing, error handling, and cross-platform ops.

all tools

shell-scripting

View posix-shell-pro

tdd-workflows-code-reviewer

36.8k

Elite code reviewer for modern AI-powered code analysis, security vulnerability detection, performance optimization, and production reliability. Masters static analysis tools and security scanning.

all tools

View tdd-workflows-code-reviewer

comment-analyzer

30.2k

Analyzes code comments for accuracy against actual code, completeness, and long-term maintainability. Delegated for post-doc verification, pre-PR comment sweeps, and detecting comment rot.

all tools

pr-review-toolkit

View comment-analyzer