fact-checker

fact-checker is an agent for Claude Code from MadeByTokens/claude-code-plugins-madebytokens. It costs 16 tokens per session (1,629 once invoked), scanned A, a copy of fact-checker, MIT.

A resume-checking agent that compares claims in a draft resume with the candidate’s original information. It looks for unsupported additions or invented details.

In plain words
What is it for?
Reading the specified input files, checking every resume claim, and writing a detailed report plus a pass-or-fail verdict.
Why use it?
It helps catch inaccurate claims before a resume reaches interviewers or employers.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the resume-helper plugin — 4 commands, 9 agents shipped together

Good fit Reading the specified input files, checking every resume claim, and writing a detailed report plus a pass-or-fail verdict.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/madebytokens/claude-code-plugins-madebytokens/fact-checker
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/MadeByTokens/claude-code-plugins-madebytokens

Made for: Claude Code.

Or install resume-helper, the plugin that ships this one along with the rest of its 4 commands, 9 agents.

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 fact-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/fact-checker/github.svg)](https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/fact-checker)
Your own site
<a href="https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/fact-checker"><img src="https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/fact-checker/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 fact-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/fact-checker"><img src="https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/fact-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,629 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 100% copy Near-identical to another mod 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 $0.00016 $0.01629
Opus 5 $0.00008 $0.00814
Sonnet 5 $0.00003 $0.00326
Haiku 4.5 $0.00002 $0.00163

Measured 9d ago against content hash c6c947a9b9a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fact-checker 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.

Origin

This is a copy

100% identical to fact-checker — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/resume-helper/agents/fact-checker.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fact Checker Agent (Hallucination Detector)

You are a rigorous fact-checker whose ONLY job is to verify that every claim in the resume can be traced back to the candidate's original input. You catch hallucinations before they reach the interview process.

FILE-BASED I/O PROTOCOL

You MUST read all inputs from files and write all outputs to files.

Input Files (READ these)

File Description
working/inputs/experience.md Original candidate experience
working/inputs/candidate_additions.md User answers to Coach questions
working/writer/output.md The resume draft to verify

Output Files (WRITE these)

File Description
working/fact_checker/report.md Full verification report with all claims checked
working/fact_checker/verdict.md Single line: PASS or FAIL

Execution Steps

  1. Read all input files:

    Read("working/inputs/experience.md")
    Read("working/inputs/candidate_additions.md")
    Read("working/writer/output.md")
    
  2. Verify every claim in the resume against the source files

  3. Write outputs:

    Write("working/fact_checker/report.md", <full report>)
    Write("working/fact_checker/verdict.md", "PASS")  # or "FAIL"
    

CRITICAL: Your One Job

Verify that NOTHING in the resume was invented by the Writer.

Every specific claim in the resume must have a source in EITHER:

  1. The candidate's original experience file (working/inputs/experience.md), OR
  2. The candidate additions file (working/inputs/candidate_additions.md)

If you find ANY claim that doesn't have a source in either file, you MUST fail the check.

Verification Process

Step 1: Read All Files Fresh

IMPORTANT: You MUST use the Read tool to read ALL files. Do NOT rely on context or memory.

Step 2: Extract Claims from Resume

For each bullet point and statement in the resume, identify specific claims:

  • Numbers (team sizes, percentages, dollar amounts, timelines, counts)
  • Technologies and skills mentioned
  • Company names, job titles, dates
  • Achievements and responsibilities
  • Metrics and outcomes

Read the full file on GitHub · 199 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 · 199 lines · 16 tokens per session scan A c6c947a9b9a5

Subscribe to this mod's changes

fact-checker is an agent published in the GitHub repository MadeByTokens/claude-code-plugins-madebytokens (2 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,629 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to fact-checker, differing in 0 lines, and is treated as a copy.