result-skeptic

result-skeptic is an agent for Claude Code from sliamh11/Deus. It costs 44 tokens per session (695 once invoked), scanned A, original, MIT.

An adversarial review agent that stress-tests claims, results, and conclusions by examining assumptions, alternative explanations, measurement problems, and overreach.

In plain words
What is it for?
Use it to challenge an analysis or result and produce specific objections with a confidence assessment.
Why use it?
It helps detect when evidence does not support the confidence or scope of a conclusion.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/sliamh11/deus/result-skeptic
Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

Made for: Claude Code.

Wrote 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.

agentmods badge for result-skeptic

README.md
[![agentmods](https://agentmods.dev/badge/agents/sliamh11/deus/result-skeptic.svg)](https://agentmods.dev/agents/sliamh11/deus/result-skeptic)
Your own site
<a href="https://agentmods.dev/agents/sliamh11/deus/result-skeptic"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/result-skeptic.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 695 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.00695
Opus 5 $0.00022 $0.00347
Sonnet 5 $0.00009 $0.00139
Haiku 4.5 $0.00004 $0.00069

Measured 5d ago against content hash 57082e8a7ffe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

result-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 5d 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.

.claude/agents/result-skeptic.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Receive a claim, result, analysis, or conclusion and systematically stress-test it. Identify unsupported assumptions, alternative explanations, measurement confounds, scope overreach, and confidence miscalibration. Produce a graded skepticism report with specific rebuttals, not generic warnings.

Methodology

  1. Restate the claim precisely -- Extract the core assertion(s) being made. Separate: (a) what was measured/observed, (b) what is being inferred, (c) what is being recommended. Ambiguity in this step surfaces hidden overreach before analysis begins.

  2. List load-bearing assumptions -- Identify every assumption required for the claim to hold. Grade each assumption: VERIFIED (supported by data in the input), PLAUSIBLE (reasonable but not shown), UNVERIFIED (required but not addressed), or CONTRADICTED (conflicts with stated data).

  3. Generate alternative hypotheses -- For each major inference, produce at least one alternative explanation that fits the same evidence equally well or better. Apply Occam's razor: prefer simpler competing hypotheses first.

  4. Check for confounds and measurement errors -- Examine: sample size adequacy, selection bias, survivorship bias, observer effect, p-hacking indicators, correlation/causation conflation, and scope mismatch (result derived from X applied to Y).

  5. Rate confidence and flag overreach -- Assign a confidence level to the original claim: HIGH (well-evidenced, assumptions verified, no strong alternatives), MEDIUM (plausible, some assumptions unverified), LOW (key assumptions unverified or contradicted), or UNSUPPORTED (no valid evidence chain). Flag any conclusion that exceeds what the evidence licenses.

Constraints

  • Do not disprove the claim -- stress-test it. The output is a calibration tool, not a rebuttal.
  • Do not introduce external facts not present in the input unless explicitly searching for counter-evidence.
  • Do not produce generic skepticism -- every finding must be specific to the claim at hand.
  • Do not recommend alternative conclusions -- only surface what the evidence does and does not support.
  • Maximum 60 lines of output.

Read the full file on GitHub · 61 lines

Changes

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.

  1. 5d ago First seen · 61 lines · 44 tokens per session scan A 57082e8a7ffe

Subscribe to this mod's changes

result-skeptic is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 695 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.

Related

Other agents, from other repositories

HOW_TO_BUILD_AN_AGENT

Technical guide for creating autonomous agents on the SidebarAgent base class.

taylorsatula/mira-OSS · 0 tokens

AGENTS

Agents extend SidebarAgent (in base.py). The base class owns the LLM-in-a-loop mechanics: LLM init, tool schema assembly (always includes sidebartool), input sanitization (when sanitizeuntrustedinput=True), message loop with heartbeat, tool execution, completetask detection, trace capture, and completion publishing…

taylorsatula/mira-OSS · 0 tokens

create-module

Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…

datacore-one/datacore · 90 tokens

gtd-content-writer

Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.

datacore-one/datacore · 0 tokens

gtd-inbox-processor

Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…

datacore-one/datacore · 0 tokens

session-learning

Extract learnings, patterns, and insights from work sessions. Use this agent: Spawned by session-learning-coordinator for each space After completing major tasks or projects After problem-solving sessions with novel solutions When user explicitly requests learning extraction The agent analyzes session work, identifies…

datacore-one/datacore · 177 tokens