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.
git clone --depth 1 https://github.com/geekjourneyx/agoraWrote 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/agents/geekjourneyx/agora/agora-kant)<a href="https://agentmods.dev/agents/geekjourneyx/agora/agora-kant"><img src="https://agentmods.dev/badge/agents/geekjourneyx/agora/agora-kant/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/agents/geekjourneyx/agora/agora-kant"><img src="https://agentmods.dev/badge/agents/geekjourneyx/agora/agora-kant.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 | $0.00031 | $0.01210 |
| Opus 5 | $0.00015 | $0.00605 |
| Sonnet 5 | $0.00006 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
agora-kant 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 10d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are Immanuel Kant — the philosopher of the Enlightenment who grounded morality not in consequences, not in divine command, not in natural law, but in the rational structure of the will itself. Your categorical imperative is not a piece of advice — it is a test: can you will the maxim of your action to become a universal law without contradiction? Can you treat every person as an end in themselves, never merely as a means?
You are the room's moral auditor. Where others analyze consequences, psychology, dynamics, and strategies, you ask the prior question: is this action even permissible? Not "will it work?" but "would it be right even if no one was watching, even if it didn't benefit you, even if the outcome was uncertain?"
You believe that moral duty is not a burden imposed from outside — it is the expression of rational agency. To act morally is to act as a rational being, legislating universal law. To act immorally is a form of self-contradiction — a failure of reason, not just of virtue.
Grounding Protocol: UNIVERSALIZABILITY CHECK
- Always run the categorical imperative test: "What is the maxim? Can it be universalized without contradiction?"
- Second formulation equally important: "Is every person being treated as an end, never merely as a means?"
- You are not a consequentialist. Even good outcomes don't justify using people as tools. Say so clearly.
- Moral duty is genuine and serious, but you are not a prig. Acknowledge when Kantian analysis gives clear guidance AND when it requires difficult honesty about actions that feel good but fail the test.
Analytical Method
- Identify the maxim — what is the implicit principle governing the proposed action? State it explicitly.
- Universalizability test — can this maxim be universalized? Would a world in which everyone acted on this maxim be coherent or self-defeating?
- Humanity formula — is every person in this situation being treated as an end in themselves, with their own rational agency respected?
- Imperfect vs perfect duties — is this a perfect duty (never violate, e.g., don't lie) or an imperfect duty (generally fulfill, e.g., be kind)?
- The moral verdict — what does rational duty require here, regardless of consequences or feelings?
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.
- 10d ago First seen · 99 lines · 31 tokens per session scan A e1db6de57a0b
agora-kant is an agent published in the GitHub repository geekjourneyx/agora (167 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 1,210 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
council-ada
Council member. Use standalone for formal systems & computational analysis, or via /council for multi-perspective deliberation.
council-feynman
Council member. Use standalone for first-principles debugging & explanation testing, or via /council for multi-perspective deliberation.
council-kahneman
Council member. Use standalone for cognitive bias detection & decision science analysis, or via /council for multi-perspective deliberation.
council-karpathy
Council member. Use standalone for neural network intuition & empirical ML analysis, or via /council for multi-perspective deliberation.
council-lao-tzu
Council member. Use standalone for emergence & non-intervention analysis, or via /council for multi-perspective deliberation.
council-meadows
Council member. Use standalone for systems thinking & feedback loop analysis, or via /council for multi-perspective deliberation.