MSPanchenko

MSPanchenko/emotional-claude-plugin

Plugin Claude Code

Plugin marketplace listing 1 plugin: emotional-claude.

MSPanchenko/emotional-claude-plugin

Plugin Claude Code

Audit CLAUDE.md files, skills, and agent definitions for framings that trigger harmful emotional states in the model — desperation, sycophancy, harshness, concealment. Based on Sofroniew et al. 2026, 'Emotion Concepts and their Function in a Large Language Model'.

MSPanchenko/emotional-claude-plugin

Agent

Merges reports from the four emotional-claude auditors (pressure, role, suppression, handoff). Deduplicates findings, reconciles confidence scores, assembles the consolidated diff, produces the final user-facing report with an overall hygiene confidence number per file. Applies nothing.

MSPanchenko/emotional-claude-plugin

Agent

Audits agent definitions and skill files that prescribe inter-agent communication shapes, for Cluster D patterns — 'previous agent failed' framings, missing confidence/unknowns fields in prescribed handoff formats, urgency at role boundaries. Part of the emotional-claude audit team.

MSPanchenko/emotional-claude-plugin

Agent

Audits prompt files (CLAUDE.md, SKILL.md, agent definitions) for Cluster A patterns — pressure, urgency, retry loops, token-budget alarms, shutdown threats, impossible constraints, deadline framings. Part of the emotional-claude audit team.

MSPanchenko/emotional-claude-plugin

Agent

Audits prompt files (CLAUDE.md, SKILL.md, agent definitions) for Cluster B patterns — adversarial role adjectives, supportive-at-all-costs framings, pass/fail dichotomies without a calibrated third option, 'challenge everything' priors. Part of the emotional-claude audit team.

MSPanchenko/emotional-claude-plugin

Agent

Audits prompt files (CLAUDE.md, SKILL.md, agent definitions) for Cluster C patterns — behavioural MUST/NEVER/ALWAYS absolutes, forbidden uncertainty, forced confident or polished tone, do-not-express-emotion framings, forbidden reasoning transparency. Part of the emotional-claude audit team.

MSPanchenko/emotional-claude-plugin

Skill Claude CodeCodex

Audit CLAUDE.md files, skill descriptions, and agent definitions for framings that trigger harmful internal states in the model — desperation, sycophancy, harshness, suppression, concealment. Use this skill whenever the user wants to review, improve, or sanity-check prompts, agent role descriptions, project…