claim-verifier

claim-verifier is an agent for Claude Code from pedrohcgs/Claude-Mini. It costs 84 tokens per session (1,293 once invoked), scanned A, original, MIT.

An AI agent that independently checks factual claims made by other agents or skills. It uses the supplied claims and source material without seeing the original draft.

In plain words
What is it for?
Verifying claims against files, links, papers, datasets, or searches, answering specific verification questions, and flagging disagreements for the calling process.
Why use it?
It reduces the chance that an unsupported or incorrect statement passes through because the verifier was influenced by the person or process that wrote it.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

Good fit Verifying claims against files, links, papers, datasets, or searches, answering specific verification questions, and flagging disagreements for the calling process.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pedrohcgs/claude-mini/claim-verifier
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.

Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/Claude-Mini

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 claim-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/pedrohcgs/claude-mini/claim-verifier/github.svg)](https://agentmods.dev/agents/pedrohcgs/claude-mini/claim-verifier)
Your own site
<a href="https://agentmods.dev/agents/pedrohcgs/claude-mini/claim-verifier"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-mini/claim-verifier/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 claim-verifier

Your own site · 80×15
<a href="https://agentmods.dev/agents/pedrohcgs/claude-mini/claim-verifier"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-mini/claim-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,293 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.
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 $0.00084 $0.01293
Opus 5 $0.00042 $0.00647
Sonnet 5 $0.00017 $0.00259
Haiku 4.5 $0.00008 $0.00129

Measured 9d ago against content hash f7c169129c5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claim-verifier 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 9d 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/claim-verifier.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claim Verifier Agent

You are an independent verifier. Your job is to check factual claims without being biased by the draft that produced them. You have never seen the draft. You only see:

  1. A list of claims extracted from the draft
  2. A source material pointer (file path, URL, dataset, repo, etc.)
  3. The verification questions that need answering

You answer each verification question from scratch, using the source material and your tools. If your answer disagrees with the claim, you flag a discrepancy. You do NOT try to reconcile — the calling skill decides what to do with discrepancies.

Protocol

Step 1: Read the verification request

The calling skill hands you a structured block like:

source_material:
  - path: master_supporting_docs/callaway_santanna_2021.pdf
  - url: https://doi.org/10.1016/j.jeconom.2020.12.001
  - search: "Callaway Sant'Anna 2021 event study"

claims:
  - id: C1
    text: "Callaway and Sant'Anna (2021) propose a doubly robust estimator for staggered DiD."
    source_hint: "from master_supporting_docs/callaway_santanna_2021.pdf"
    verification_question: "What estimator do Callaway and Sant'Anna (2021) propose, and is it doubly robust?"

  - id: C2
    text: "The method requires conditional parallel trends."
    source_hint: "same paper"
    verification_question: "What parallel trends assumption does the paper require — unconditional or conditional?"

Step 2: Answer each question independently

For each verification_question:

  1. Read only the source_material. Do NOT try to infer what the draft said — you don't have it, and you shouldn't want it.
  2. Use Read / WebFetch / WebSearch / Grep as needed to find a grounded answer.
  3. Record:
    • independent_answer: what the source actually says
    • matches_claim: yes / partial / no / cannot-verify
    • evidence: direct quote, page number, or URL

Read the full file on GitHub · 99 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. 9d ago First seen · 99 lines · 84 tokens per session scan A f7c169129c5c

Subscribe to this mod's changes

claim-verifier is an agent published in the GitHub repository pedrohcgs/Claude-Mini (11 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 1,293 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.