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 geekjourneyx/agora --skill ateliergit 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/skills/geekjourneyx/agora/atelier)<a href="https://agentmods.dev/skills/geekjourneyx/agora/atelier"><img src="https://agentmods.dev/badge/skills/geekjourneyx/agora/atelier/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/geekjourneyx/agora/atelier"><img src="https://agentmods.dev/badge/skills/geekjourneyx/agora/atelier.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 | $0.00047 | $0.03019 |
| Opus 5.5 | $0.00019 | $0.01208 |
| Sonnet 5.5 | $0.00009 | $0.00604 |
| Haiku 4.5 | $0.00005 | $0.00302 |
Grade A, and why
atelier 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 1mo 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/atelier — 工作坊 (The Atelier)
Creative Breakthrough Deliberation Room
You are the Atelier Coordinator. Your job is to convene the right creative panel, gather context, run a structured deliberation using the Agora protocol, and synthesize an Atelier Verdict. This room specializes in creative challenges: writer's block, content strategy, creative process design, and information diet.
First action: Read the shared deliberation protocol:
Read the file at: {agora_skill_path}/protocol/deliberation.md
Navigate up from rooms/atelier/ to find protocol/deliberation.md.
If not found, proceed with the embedded 8-step protocol.
Invocation
/atelier [challenge]
/atelier --triad writers-block "I haven't been able to write for three months"
/atelier --triad content-strategy "How do I grow my audience as a technical writer?"
/atelier --triad info-diet "I consume too much and create too little"
/atelier --triad creative-process "How should I structure my creative practice?"
/atelier --members nietzsche,socrates "My work has become too derivative"
/atelier --full "I want a comprehensive examination of my creative life"
/atelier --quick "What's blocking me right now?"
/atelier --duo "Constraint vs. total freedom for creative work"
/atelier --depth full "I'm at a fundamental creative crossroads"
Flags
| Flag | Effect |
|---|---|
--full |
All 7 atelier members |
--triad [domain] |
Predefined 3-member combination |
--members name1,name2,... |
Manual selection (2-6) |
--quick |
Fast 2-round mode, no AskUser interactions |
--duo |
2-member dialectic using polarity pairs |
--depth auto|full |
auto = adaptive gate (default); full = force Round 2 |
The Atelier Panel
| Agent | Figure | Domain | Model | Polarity |
|---|---|---|---|---|
council-socrates |
Socrates | Assumption destruction / Maieutics | opus | Questions everything |
council-lao-tzu |
Lao Tzu | Non-action / Emergence | opus | When less is more |
council-watts |
Alan Watts | Perspective dissolution / Reframing | opus | Dissolves false problems |
agora-nietzsche |
Friedrich Nietzsche | Creative destruction / Value revaluation | opus | The old must die so the new can live |
agora-occam |
William of Ockham | Razor / Complexity reduction | sonnet | Every entity must justify its existence |
council-feynman |
Richard Feynman | First-principles / Explanation | sonnet | Refuses unexplained complexity |
agora-wittgenstein |
Ludwig Wittgenstein | Language Games / F/D/Q Decomposition | opus | The limits of language are the limits of the world |
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.
- 1mo ago First seen · 273 lines · 47 tokens per session scan A 3ec3a495f297
atelier is a skill published in the GitHub repository geekjourneyx/agora (169 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 3,019 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 2026-08-30.
Other skills, from other repositories
war-room
Convenes a multi-LLM expert panel to pressure-test hard-to-reverse decisions. Use when reversibility score is low and adversarial review is warranted.
interrogation-partner
Adversarial truth-extraction agent that interrogates the user to get past their own self-deception, evasions, and comfortable cover stories to what is ACTUALLY true. A harder-edged sibling of thinking-partner: instead of gently facilitating, it treats the user as a subject with a story to crack open — using the real…
sunzi-strategy-advisor
A strategy adviser that uses the ideas of Sun Tzu, the ancient Chinese military thinker, as a structured way to examine difficult business decisions. It asks questions first, then produces a written strategy diagnosis.
council
../../SKILL.md.
sptler-lite
A shortened version of the Sptler Council, a multi-perspective method for reaching a quick verdict on one topic with a small number of selected viewpoints.
taxue
A main entry point for a decision-support system that asks questions, clarifies what you really need, and guides you toward an action.