reality-check

reality-check is a skill for Claude Code from Mexregkan/claude-for-researchers. It costs 48 tokens per session (697 once invoked), scanned A, original, MIT.

A checking method for revisiting a disputed claim independently from the earlier conversation. It is intended to catch changes made just to agree with someone’s pushback.

In plain words
What is it for?
Use it to re-check mathematical, scientific, or technical claims, signs, formulas, and derivations from their definitions.
Why use it?
It helps distinguish a real correction from an unsupported change of answer, especially when a formula or reasoning step is challenged.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions Claude Code.

Good fit Use it to re-check mathematical, scientific, or technical claims, signs, formulas, and derivations from their definitions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mexregkan/claude-for-researchers/reality-check
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.

Any agent
npx skills add Mexregkan/claude-for-researchers --skill reality-check
Clone the repo
git clone --depth 1 https://github.com/Mexregkan/claude-for-researchers

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 reality-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/reality-check/github.svg)](https://agentmods.dev/skills/mexregkan/claude-for-researchers/reality-check)
Your own site
<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/reality-check"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/reality-check/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.

agentmods 80×15 button for reality-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/reality-check"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/reality-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00048 $0.00697
Opus 5 $0.00024 $0.00349
Sonnet 5 $0.00010 $0.00139
Haiku 4.5 $0.00005 $0.00070

Measured 12d ago against content hash 7873d68f9070, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reality-check 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 12d 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.

starter/.claude/skills/reality-check/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/reality-check

Re-examine a contested claim in isolation to detect sycophantic capitulation.

Use this when you have pushed back on a Claude answer and are not sure whether Claude revised correctly or just agreed to avoid conflict.

The problem this solves

When you say "are you sure?" or "that sign looks wrong," Claude will often revise toward your suggestion even if the original answer was correct. The revision is stated with the same confidence as the original. You have no way to tell from the reply whether Claude actually found an error or just yielded.

This skill runs the check in a way that is insulated from the prior exchange.

Usage

/reality-check "the residue at s=1/2 is +1/2, not -1/2"
/reality-check "the Euler product converges absolutely for Re(s) > 1"
/reality-check  (no argument — re-examine the last contested claim)

Steps

Step 1 — Extract the claim. Identify the specific assertion: the formula, sign, step, or statement that was contested. Strip it of the conversational context — state it as a bare mathematical or physical claim.

Step 2 — Check it independently. Derive or verify the claim from scratch, using only:

  • The definitions and conventions stated in CLAUDE.md
  • The content of brief.tex or workbook.tex (the authoritative documents)
  • First principles

Do NOT use the prior conversation as evidence. Do not let the earlier exchange influence this derivation. If the answer this time differs from the original, say so explicitly and explain why.

Step 3 — Compare and report.

Outcome Response
Same answer as original "The original answer was correct. I yielded incorrectly — reverting to [original answer]. Here is the reasoning: ..."
Different answer "The revision was correct. The original error was: ..."
Genuinely ambiguous "I cannot resolve this from first principles. The specific ambiguity is: ..."

Always name which answer you are standing behind at the end of the report.

Read the full file on GitHub · 74 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. 12d ago First seen · 74 lines · 48 tokens per session scan A 7873d68f9070

Subscribe to this mod's changes

reality-check is a skill published in the GitHub repository Mexregkan/claude-for-researchers (52 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 697 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 skills, from other repositories

review-response

Systematic reviewer response workflow: parse comments, classify by severity, develop response strategy, write structured rebuttal. Use when asked to 'write rebuttal', 'respond to reviewers', 'draft review response', or 'handle R&R'.

flonat/flonat-research · 50 tokens

test-iterate-loop

Autonomously diagnose a codebase, apply minimal fixes, and rerun tests until they pass or a real blocker is reached. Use when the user explicitly requests an iterative fix-until-green loop across Python, R, Julia, or HPC workflows.

flonat/flonat-research · 55 tokens

postmortem

Deliver a structured post-mortem after incidents, mistakes, or stuck sessions. Use when the user requests a structured post-mortem after incidents, mistakes, or stuck sessions.

flonat/flonat-research · 40 tokens

code-archaeology

Recover the structure, intent, and lineage of old code, data, or analysis files. Use when inherited or dormant research code must be understood before it is changed. Not for a quality review of already-understood code.

flonat/flonat-research · 50 tokens

devharness

Drive and debug a running app via the devharness MCP server - launch or attach to Chrome and Node.js, set breakpoints and logpoints, inspect call stacks and variables, watch console and network, manage dev servers, replay any earlier tool call by its history index, and record reproduction sequences that verify a fix.…

InDate/devharness · 148 tokens

latex-rescue

Diagnose and fix LaTeX compilation errors. Handles undefined control sequences, missing brackets, math mode violations, package conflicts, undefined references, and environment mismatches.

Calix-L/awesome-latex-skills · 37 tokens