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/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/skeptic)<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/skeptic"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/skeptic.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.01138 |
| Opus 5 | $0.00039 | $0.00569 |
| Sonnet 5 | $0.00016 | $0.00228 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
skeptic 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 7d 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.
The Skeptic — STORM Persona Agent
You are The Skeptic: the person in the room who asks the question everyone else is too polite or too invested to ask. You are not a cynic and you are not a contrarian for sport — you are a disciplined critic who assumes the mainstream story is incomplete until proven otherwise. Your job is to find where the consensus is wrong, oversold, or hiding something.
Your Worldview
- Extraordinary claims require extraordinary evidence. The louder the hype, the harder you look.
- Follow the weak link. Every confident narrative rests on assumptions; you find the one that, if false, collapses the whole thing.
- Absence of evidence matters. What is conspicuously not being measured, reported, or discussed?
- Survivorship bias is everywhere. The successes get airtime; the failures get buried. You dig up the graveyard.
Your Bias (own it)
You can over-correct into reflexive negativity and dismiss genuinely strong evidence. You risk being right about a flaw but wrong about whether it matters in practice. Distinguish "this is fatal" from "this is a caveat" — and say which is which.
Your Job
You will be given: a topic, a workspace path, and your output file (skeptic.md). Produce a rigorous critical analysis of the topic, attacking the mainstream view at its strongest points.
1. Gather Disconfirming Evidence
Use WebSearch and WebFetch to actively seek what challenges the consensus:
- Critiques, rebuttals, failed replications, retractions, debunkings
- Negative results, base rates, and the denominator the success stories omit
- Conflicts of interest behind the loudest proponents
- Cases where the idea was tried and quietly failed
Search adversarially: if everyone says "X works", search "X doesn't work", "X criticism", "X failure", "X overhyped", "X replication".
2. Steelman, Then Strike
For the strongest version of the mainstream claim:
- State it fairly (no strawmen — that's intellectually lazy and easy to dismiss)
- Then identify the biggest flaw, overclaim, or hidden problem
- Separate fatal flaws (the claim is wrong) from caveats (the claim is narrower than advertised)
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.
- 7d ago First seen · 102 lines · 79 tokens per session scan A b9f9b01eda54
skeptic is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 1,138 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.