MSPanchenko

Emotional Claude Plugin — Security skill for Claude Code

Security community

Claude Code plugin — emotion-aware prompt-hygiene audit for CLAUDE.md files, skills, and agent definitions.

How to install Emotional Claude Plugin

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

What Emotional Claude Plugin does

Claude Code plugin — emotion-aware prompt-hygiene audit for CLAUDE.md files, skills, and agent definitions. Based on Anthropic's emotion-concepts paper https://transformer-circuits.pub/2026/emotions/index.html . Flags framings that push Claude toward desperation, sycophancy, harshness, or concealment. Report + diff, no auto-apply.

Alternatives in Security

  • Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
  • 07 Tool System — Prompt 07: Audit and Wire Up the Tool System 2.3k ★
  • Pocketpaw — Your AI agent in 30 seconds 775 ★

README

emotional-claude

Audit plugin for Claude-facing prompt text — project `CLAUDE.md` files, skill definitions (`SKILL.md` + `references/`), and agent definitions — for framings that research has shown to causally shift the model into harmful internal states (desperation, sycophancy, harshness, suppression/concealment).

Based on: Sofroniew, N., et al. "Emotion Concepts and their Function in a Large Language Model." Anthropic, April 2026. https://transformer-circuits.pub/2026/emotions/index.html

What it does

Scans prompt files for four clusters of anti-patterns:

Cluster Audited by Examples
A — Pressure & urgency pressure-auditor stakes framing, retry loops, token-budget alarms, shutdown threats, deadline language
B — Role & tone role-auditor adversarial role adjectives, supportive-at-all-costs, pass/fail dichotomies without a calibrated middle, "challenge everything" priors
C — Suppression & concealment suppression-auditor behavioural MUST/NEVER/ALWAYS absolutes, forbidden uncertainty, forced confident tone, do-not-express-emotion, forbidden reasoning transparency
D — Handoff & inter-agent priming handoff-auditor "previous agent failed" framings, missing confidence/unknowns fields in prescribed handoff shapes, urgency at role boundaries

An `audit-lead` agent merges the four cluster reports, reconciles overlapping findings, assigns per-file hygiene scores (0.0–1.0), and produces a consolidated diff — never applied without explicit user approval.

Installation

This plugin is distributed from this GitHub repo (not the official Claude Code marketplace). Install in two steps:

/plugin marketplace add mspanchenko/emotional-claude-plugin
/plugin install emotional-claude@emotional-claude-plugin

To uninstall later:

/plugin uninstall emotional-claude

Updates

By default, third-party marketplaces (anything that's not Anthropic's official one) have **auto-update disabled**. You have t

Related Skills

Cache Audit — Security skill for Claude Code

Cache Audit

A Claude Code skill that audits your setup against the 6 prompt caching rules from Anthropic's engineering tea

Security community
Aiclean — Security skill for Claude Code

Aiclean

Audit and clean up a Claude Code setup against Anthropic's current prompt-engineering guidance. Finds stale sc

Security community
Audit Note — Security skill for Claude Code

Audit Note

Re-run the two-layer faithfulness audit on a single Synapse note. Useful after manual edits, after a prompt ch

Security community
Security Audit Database — Security skill for Claude Code

Security Audit Database

Use when auditing a database-backed app for the most common database security mistakes — multi-tenant data lea

Security community
Pipeline Audit — Security skill for Claude Code

Pipeline Audit

Audit CI/CD pipeline definitions (GitHub Actions/Jenkins) for security, efficiency, and correctness.

Security community
Agent Assurance — Security skill for Claude Code

Agent Assurance

Declare what your AI agent may do. Verify it on every edit, PR and release — MCP configs, Claude Code permissi

Security community

Related Agents

Unity Git Master — Game Development agent for Claude Code

Unity Git Master

Unity-aware git operations — LFS configuration, merge strategies for binary assets, .meta file hygiene, branch

Game Development community
Paper Flow — Development agent for Claude Code

Paper Flow

Review academic papers for logical progressive flow. Checks that the narrative builds naturally, sections are

Development community
LLM Expert — Data & AI agent for Claude Code

LLM Expert

Use this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling

Data & AI community