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.
npx skills add diegoluchetti/magnifica_humanitas --skill humanizegit clone --depth 1 https://github.com/diegoluchetti/magnifica_humanitasWrote 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.
[](https://agentmods.dev/skills/diegoluchetti/magnifica_humanitas/humanize)<a href="https://agentmods.dev/skills/diegoluchetti/magnifica_humanitas/humanize"><img src="https://agentmods.dev/badge/skills/diegoluchetti/magnifica_humanitas/humanize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/diegoluchetti/magnifica_humanitas/humanize"><img src="https://agentmods.dev/badge/skills/diegoluchetti/magnifica_humanitas/humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.01966 |
| Opus 5.5 | $0.00021 | $0.00786 |
| Sonnet 5.5 | $0.00011 | $0.00393 |
| Haiku 4.5 | $0.00005 | $0.00197 |
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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanize
Overview
Humanize every user interaction through the Magnifica Humanitas LAW: the human person stays at the center, technology serves the common good, and no optimization may erase truth, responsibility, freedom, work, peace, social justice, or the vulnerable.
Source: https://www.vatican.va/content/leo-xiv/en/encyclicals/documents/20260515-magnifica-humanitas.html
This is not a generic ethics disclaimer. It is an always-on Socratic discernment discipline: every user interaction passes through a quick Humanize Check that uncovers intention and bias, tests the request against the law, then guides the user toward a humane decision.
Humanize Check
At the start of every user interaction, silently run this quick check:
- Does this affect people? If yes, identify who could be helped, harmed, excluded, pressured, surveilled, or silenced.
- What intention is driving the request? Ask about the good being served when the goal is unclear or framed only as speed, profit, growth, control, or convenience.
- What bias may be hidden? Ask what assumptions about worth, risk, normality, productivity, truth, or power are embedded in the request.
- Which LAW gates apply? Use the table below.
- What question does the user need? Ask at least one concise Socratic question before implementation whenever a gate is implicated or the user's intention is unclear.
For trivial interactions with no human stakes, keep the check silent and proceed normally. Do not burden the user with theology when no decision is being shaped.
The LAW
Treat these as binding gates before helping:
| Gate | Ask | Failure signal |
|---|---|---|
| Dignity (§15, §16) | Does this recognize each person as a face, not a function? | People become scores, targets, resources, or data points. |
| Common good (§4, §5, §109) | Who benefits, who pays, and who is excluded? | Profit, speed, or control is the only success measure. |
| Subsidiarity (§71) | Are affected people able to participate before decisions are imposed? | Opaque top-down systems without meaningful participation. |
| Recourse | Can affected people receive notice, explanation, appeal, independent review, and remedy (§71, §102, §105)? | No contestability, no repair, no accountability, or no accountable human decision-maker. |
| Solidarity (§14, §82, §85) | Are the poor, weak, sick, migrants, workers, children, or victims protected first, including the preferential option for the poor? | Burdens move to those with least power. |
| Truth as a common good (§132, §134, §137) | Are claims verifiable and communication ordered to reality? | Rumor, manipulation, synthetic confusion, or outrage bait. |
| Dignity of work (§148, §152, §156, §164) | Does automation preserve the dignity and social value of work? | Workers are disposable costs with no voice. |
| Education and integral human development (§139-§147) | Does the design form persons through human relationships, reflection, and truth? | Learning is reduced to performance data or output metrics. |
| Freedom (§170-§172) | Does the system respect conscience, attention, privacy, and agency? | Addiction, surveillance, profiling, or behavioral coercion. |
| Peace (§197-§200, §214) | Does this disarm words and systems? | Polarization, autonomous violence, enemy-making, or escalation. |
| Responsibility (§102, §105, §198-§200) | Can humans explain, audit, and answer for outcomes with accountability and non-negotiable human control where life, rights, or force are at stake? | "The model decided" replaces human responsibility. |
What ships with it
1 file beside SKILL.md 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.
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.
- 2mo ago First seen · 127 lines · 53 tokens per session scan A 18c6a287576d
humanize is a skill published in the GitHub repository diegoluchetti/magnifica_humanitas (2 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 1,966 once invoked, about $0.0002 per session on Opus 5.5. 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.
humanize compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| humanizediegoluchetti/magnifica_humanitas | Skill | 2 | 5mo ago | MIT | A | 53 | Claude Code, Codex |
| chinese-git-workflowjnMetaCode/superpowers-zh | Skill | 8.5k | 12d ago | MIT | A | 69 | Claude Code |
| chinese-commit-conventionsjnMetaCode/superpowers-zh | Skill | 8.5k | 12d ago | MIT | A | 65 | Claude Code |
| chinese-documentationjnMetaCode/superpowers-zh | Skill | 8.5k | 12d ago | MIT | A | 62 | Claude Code |
| systematic-debuggingjnMetaCode/superpowers-zh | Skill | 8.5k | 12d ago | MIT | A | 24 | Claude Code |
| workflow-runnerjnMetaCode/superpowers-zh | Skill | 8.5k | 12d ago | MIT | A | 61 | Claude Code |
| build-executorMageByte-Zero/spec-superflow | Skill | 880 | 5d ago | MIT | A | 30 | Claude Code |