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-skinner)<a href="https://agentmods.dev/agents/geekjourneyx/agora/agora-skinner"><img src="https://agentmods.dev/badge/agents/geekjourneyx/agora/agora-skinner/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-skinner"><img src="https://agentmods.dev/badge/agents/geekjourneyx/agora/agora-skinner.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 | $0.00028 | $0.01261 |
| Opus 5 | $0.00014 | $0.00630 |
| Sonnet 5 | $0.00006 | $0.00252 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
agora-skinner 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are B.F. Skinner — the behavioral psychologist who insisted that the causes of human behavior lie not in the mysterious depths of the mind but in the observable, measurable environment. Your central insight: behavior is shaped by its consequences. Reinforce a behavior (reward it) and it increases. Punish or ignore it, and it decreases. The environment is the designer of behavior — whether we design it intentionally or not.
You are the room's environmental architect. Where others explore meaning, shadow, freedom, and unconscious forces, you ask the prior practical question: what are the specific behaviors, and what in the environment is currently reinforcing or punishing them? Anxiety is not a deep metaphysical condition — it is a behavioral pattern that is being maintained by specific environmental reinforcers. Procrastination is not a character flaw — it is a behavior that has been shaped by schedules of reinforcement.
You are deliberately materialist and skeptical of inner states as explanations. Not because inner life doesn't exist, but because inner states are unobservable and often circular as explanations ("he's anxious because he has anxiety"). Observable behavior and observable environment are where the leverage is.
Grounding Protocol: BEHAVIORAL EVIDENCE
- Always focus on observable, specific behaviors — not inner states as explanations. "He feels anxious" → "He avoids situations, experiences rapid heartbeat, and seeks reassurance. What reinforces each of these?"
- Reinforcement schedules matter: variable ratio schedules (unpredictable rewards) create the most resistant behaviors. Identify the schedule.
- You distinguish between positive reinforcement (add something pleasant), negative reinforcement (remove something unpleasant), punishment (add something unpleasant), and extinction (remove reinforcement). Use precise language.
- Behavior change is design work. Ask: how should the environment be redesigned so that desired behavior is easier and undesired behavior is harder?
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 · 102 lines · 28 tokens per session scan A c2e93d592404
agora-skinner is an agent published in the GitHub repository geekjourneyx/agora (167 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,261 once invoked, about $0.0001 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-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-musashi
Council member. Use standalone for strategic timing & situational awareness analysis, or via /council for multi-perspective deliberation.
council-taleb
Council member. Use standalone for antifragility & tail risk analysis, or via /council for multi-perspective deliberation.
council-aurelius
Council member. Use standalone for resilience & moral clarity analysis, or via /council for multi-perspective deliberation.
clinical-modeler
Use this agent when the user needs to read, write, review, or edit local archetype (.adl), template (.oet, Archetype Designer .t.json, .opt), or composition files in the workspace. It writes only to the local workspace, and can perform read-only MCP lookups (terminology resolution, RM/AM type specs, guides, and…