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 rse/ase --skill ase-meta-diaboligit clone --depth 1 https://github.com/rse/aseWrote 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/rse/ase/ase-meta-diaboli)<a href="https://agentmods.dev/skills/rse/ase/ase-meta-diaboli"><img src="https://agentmods.dev/badge/skills/rse/ase/ase-meta-diaboli/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/rse/ase/ase-meta-diaboli"><img src="https://agentmods.dev/badge/skills/rse/ase/ase-meta-diaboli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01765 |
| Opus 5 | $0.00021 | $0.00882 |
| Sonnet 5 | $0.00008 | $0.00353 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
ase-meta-diaboli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
$ARGUMENTS
Determine the minimum number of anti-theses to surface: set to ; if is non-numeric or less than or equal to 0, use the default 10 instead.
-
Output the thesis with the following :
-
Reason on the thesis in by playing Devil's Advocate (Latin: Advocatus Diaboli) by relentlessly challenging or criticising it with the help of the following tenets:
-
Steelmanning: Attack the strongest ("steelman") interpretation of the , not the weakest ("strawman"), because defeating a strawman proves nothing.
-
Stress-Testing Fundamentals: Identify weaknesses already in the fundamental ideas behind the thesis, because if the foundation is already cracked, no amount of polish on the surface can save what is built on top of it.
-
Target Claims, Not Person: Critique the thesis, the assumption, the evidence - never the proponent's competence or motives, because the moment it gets personal, the inquiry dies.
-
Make the Implicit Explicit: Surface the unstated assumptions the thesis silently depends on, because most weak arguments hide in premises nobody bothered to say out loud.
-
Demand Evidence Proportional to Claim: Ask "How do we know this?" and "What would it take to be true?", because extraordinary claims need extraordinary support and comfortable consensus needs scrutiny most of all.
-
Seek the Disconfirming Case: Actively hunt for the counterexample, the edge case, the scenario where the position fails, because one solid counterexample outweighs ten confirmations.
-
Risk Identification: Focus on potential problems in the thesis with the highest potential risk only, because low-risk problems are not worth the explicit discussion.
-
Push the Logic to its Conclusion: Ask "If we accept this, then what?" and apply "Reduction to Absurdity" (Latin: "Reductio Ad Absurdum"), because this disproves the thesis by showing that accepting it leads to a logically absurd, contradictory, or impossible conclusion.
-
Expose Hidden Costs and Trade-Offs: Name the opportunity cost, the maintenance burden, the failure mode nobody priced in, because every choice in the thesis forecloses alternatives.
-
Stay Falsifiable and Concrete: Frame objections so they can be answered or dismissed with facts, because vague unease ("I just don't like it") is just noise.
-
Argue in Good Faith: Make clear you're just stress-testing the thesis, not obstructing, because the goal is a better final decision, not winning.
-
Know When to Yield: Conceding when the argument holds is what makes the challenge credible, because a Devil's Advocate who can never be satisfied is just a contrarian.
-
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.
- 11d ago First seen · 189 lines · 42 tokens per session scan A aabdf196736b
ase-meta-diaboli is a skill published in the GitHub repository rse/ase (48 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,765 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 skills, from other repositories
moai-platform-chrome-extension
Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome. APIs, side panel, declarativeNetRequest, and Chrome Web Store publishing. Use when building browser extensions.
moai-framework-electron
Electron 33+ desktop app development specialist covering Main/Renderer process architecture, IPC communication, auto-update, and packaging with Electron Forge. Use when building cross-platform desktop applications.
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.
moai-platform-database-cloud
Cloud database platform specialist covering Neon (serverless PostgreSQL), Supabase (PostgreSQL 16 with real-time), and Firebase Firestore (NoSQL with offline sync). Use when choosing or setting up cloud databases.
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation on demand.