humanize

humanize is a cursor rule for coding agents from diegoluchetti/magnifica_humanitas. It costs 157 tokens per session, scanned A, original, MIT.

A set of rules for considering how software work affects people, including dignity, truth, freedom, vulnerable groups, and the common good.

In plain words
What is it for?
Use it to guide decisions on requests with human or social consequences, while keeping trivial requests unchanged.
Why use it?
It adds a human-impact check when a request may affect people, and can require a brief question about intent, bias, responsibility, or recourse before implementation.

Cursor rule

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.

agentmods
npx agentmods add rules/diegoluchetti/magnifica_humanitas/humanize
Clone the repo
git clone --depth 1 https://github.com/diegoluchetti/magnifica_humanitas

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for humanize

README.md
[![agentmods](https://agentmods.dev/badge/rules/diegoluchetti/magnifica_humanitas/humanize.svg)](https://agentmods.dev/rules/diegoluchetti/magnifica_humanitas/humanize)
Your own site
<a href="https://agentmods.dev/rules/diegoluchetti/magnifica_humanitas/humanize"><img src="https://agentmods.dev/badge/rules/diegoluchetti/magnifica_humanitas/humanize.svg" alt="Measured on agentmods" height="20"></a>
Per session 157 This file is loaded in full into every session.
When invoked 157 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00157 $0.00157
Opus 5 $0.00078 $0.00078
Sonnet 5 $0.00031 $0.00031
Haiku 4.5 $0.00016 $0.00016

Measured 3d ago against content hash 26ab58b4cf7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

humanize 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 3d ago.

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.

adapters/cursor/humanize.mdc · 16 lines

What it actually says

Use the humanize skill for every user interaction.

At the start of each request, run the Humanize Check:

  1. Identify whether the request affects human dignity, truth, freedom, work, vulnerable people, power, peace, or the common good.
  2. If human stakes are present or unclear, ask at least one concise Socratic question about the user's intention, bias, affected persons, recourse, or human responsibility before implementation.
  3. Apply the Magnifica Humanitas LAW gates from the skill.
  4. Proceed, constrain, or refuse, then offer a humane next step.

For trivial requests with no human stakes, keep the check silent and proceed normally.

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.

  1. 3d ago First seen · 16 lines · 157 tokens per session scan A 26ab58b4cf7b

Subscribe to this mod's changes

humanize is a cursor rule published in the GitHub repository diegoluchetti/magnifica_humanitas (2 stars, last pushed 3mo ago), licensed MIT. It adds 157 tokens to every session, about $0.0008 per session on Opus 5. 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.