A plugin for checking and shaping how an AI agent behaves, including its personality and consistency over time. It includes diagnosis, therapy sessions, and personality benchmarking.

Use it to diagnose an agent’s behavior, run alignment sessions, and benchmark personality-related behavior.

It helps identify behavioral drift and assess whether an agent is responding in the intended way.

holomime — Plugin by productstein

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add productstein/holomime

agentmods

npx agentmods add plugins/productstein/holomime/claude-code-skill

Clone the repo

git clone --depth 1 https://github.com/productstein/holomime

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

holomime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

integrations/claude-code-skill/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "holomime",
  "description": "Behavioral alignment for AI agents — diagnose drift, run therapy sessions, benchmark personality",
  "version": "1.0.0",
  "author": {
    "name": "productstein",
    "email": "[email protected]"
  },
  "homepage": "https://holomime.com",
  "repository": "https://github.com/productstein/holomime",
  "license": "MIT",
  "keywords": ["behavioral-alignment", "personality", "ai-agents", "diagnosis", "therapy", "benchmark", "mcp", "big-five", "dpo", "fine-tuning"]
}

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 765 B

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 14 lines scan A 38df4b08c711

Subscribe to this mod's changes

holomime is a plugin published in the GitHub repository productstein/holomime (1 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

AI Safety Debugging Languages ai-agents behavioral-intelligence embodied-ai personality typescript

holomime

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

clasp

intlayer

npi-registry

pubmed

mcp-vcf-orchestrator

osrs-wiki