verify-claims

verify-claims is a skill for Claude Code, Codex from MadGraphTeam/MadAgents. It costs 23 tokens per session (763 once invoked), scanned A, original, MIT.

A workflow for finding factual claims in text and checking them through code execution, source inspection, or physics reasoning.

In plain words
What is it for?
Use it to extract individual claims, record them in a JSON file, and verify statements about commands, paths, parameters, outputs, and physics.
Why use it?
It reduces the risk of leaving unsupported or incorrect statements in documentation, reports, scripts, or other written work.

Skill for Claude CodeCodex

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 skills/madgraphteam/madagents/verify-claims
Any agent
npx skills add MadGraphTeam/MadAgents --skill verify-claims
Clone the repo
git clone --depth 1 https://github.com/MadGraphTeam/MadAgents

Made for: Claude Code, Codex.

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 verify-claims

README.md
[![agentmods](https://agentmods.dev/badge/skills/madgraphteam/madagents/verify-claims.svg)](https://agentmods.dev/skills/madgraphteam/madagents/verify-claims)
Your own site
<a href="https://agentmods.dev/skills/madgraphteam/madagents/verify-claims"><img src="https://agentmods.dev/badge/skills/madgraphteam/madagents/verify-claims.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 763 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 5.1 $0.00023 $0.00763
Opus 5 $0.00012 $0.00381
Sonnet 5 $0.00005 $0.00153
Haiku 4.5 $0.00002 $0.00076

Measured 5d ago against content hash af55698f0c00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

verify-claims 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.

legacy/madagents_v2/claude_code/.claude/skills/verify-claims/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Claims

Extract verifiable claims from a text and verify each one.

Input

$ARGUMENTS

If a file path was given, read it. If text was given, use it directly. If nothing was given, ask the user what to verify.

If the text references user-facing written artifacts (answer files, scripts, code, reports), read those artifacts and extract claims from them too — not just from the conversational response.

Step 1: Extract claims

Split the text into individual, self-contained factual claims. Write them to /workspace/verify/claims.json.

Rules:

  • Each claim should be a single, specific, verifiable statement.
  • Claims must be self-contained — understandable without reading the full source text.
  • Include claims about commands, parameter values, file paths, physics reasoning, expected outputs, and any other factual assertions.
  • Preserve qualifying language ("roughly", "approximately") — do not rephrase approximate guidance as hard facts.
  • Do NOT include subjective opinions or meta-commentary.

Output format — a JSON array, each object with a claim key:

[
  {"claim": "The MadGraph command to generate Drell-Yan at LO is: generate p p > e+ e-"},
  {"claim": "The default number of events in run_card.dat is 10000"}
]

Step 2: Verify each claim

For each claim, determine whether it is correct.

Environment

You may install any software needed for verification (e.g. MadGraph5_aMC@NLO, Pythia8, Delphes).

Evidence rules

Only the following count as evidence, and only when the result is unambiguous:

  • Execution output: Run a MG5 script or command that tests the claim. Observe the output.
  • Source code inspection: Read the relevant Python source files in the MadGraph installation directory.
  • Physics reasoning: Explicit derivation from established principles (conservation laws, symmetries, kinematics, coupling structure) showing every step of the proof. MadGraph's implementation may differ from textbook physics in conventions, approximations, and defaults — for any claim about how MadGraph actually behaves, use execution or source inspection instead.

Read the full file on GitHub · 76 lines

Files

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.

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 · 76 lines · 23 tokens per session scan A af55698f0c00

Subscribe to this mod's changes

verify-claims is a skill published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 763 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens