Reasoning Harness

Reasoning Harness is an AI Engineering skill for Claude Code, published by jeremylongshore in claude-code-plugins-plus-skills.

2.6K stars384 forkson jeremylongshore/claude-code-plugins-plus-skillsAdded 2026/08/12Repository updated 2026/08/12

View source on GitHub Download repo ZIP

agent-skillsaiai-agentsanthropicautomationclaude-codeclaude-code-pluginsdeveloper-toolsdevopsllmmarketplacemcpplugin-marketplaceplugin-systemsaasskills

Install in seconds

Install Reasoning Harness

Copy Reasoning Harness into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/main/plugins/community/ejentum-reasoning ~/.claude/skills/ejentum-reasoning

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/jeremylongshore/claude-code-plugins-plus-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/community/ejentum-reasoning/SKILL.md in jeremylongshore/claude-code-plugins-plus-skills
Installs to: ~/.claude/skills/ejentum-reasoning
Collection: One of 53 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Reasoning Harness does

Reasoning Harness calls an MCP reasoning tool before answering analytical, diagnostic, planning, or tradeoff-heavy questions. It is used to build a scaffold for multi-step judgments and reduce premature conclusions.

Reasoning Harness is cataloged under AI Engineering on DirSkills. Reasoning Harness comes from a repository tagged agent-skills, ai, ai-agents, anthropic and automation.

Documentation

README

Excerpt

Reasoning Harness

When this skill triggers, call the reasoning tool from the ejentum MCP server. Pass a 1-2 sentence framing of WHAT you are reasoning about as the query argument. Be specific about the task, not what tool you want.

Good query: diagnose why a microservice returns 503s under load Bad query: help me think

The tool returns a structured scaffold containing:

[NEGATIVE GATE]: failure pattern to avoid
[PROCEDURE]: steps to follow
[REASONING TOPOLOGY]: decision flow with gates and traps
[TARGET PATTERN]: correct shape your reasoning should take
[FALSIFICATION TEST]: self-check criterion
Amplify: signals to engage
Suppress: failure modes to block

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Reasoning Harness

What else does jeremylongshore publish alongside Reasoning Harness?
Reasoning Harness is one of 53 skills that DirSkills catalogs from jeremylongshore/claude-code-plugins-plus-skills, the repository it ships in. Its siblings there include Agency OS, Anti-Deception and Audit. Each one is a separate skill with its own page in this directory, installs the same way Reasoning Harness does, and is maintained by jeremylongshore in that same repository. The rest of the collection is listed on the jeremylongshore/claude-code-plugins-plus-skills page.
How does Reasoning Harness compare to other AI Engineering skills?
Reasoning Harness ranks #771 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Reasoning Harness against them. Open each page to compare what they document and how they install.