verify-claim

verify-claim is a command for Claude Code from MattArtzAnthro/gephi-ai. It costs 26 tokens per session (287 once invoked), scanned A, original, Apache-2.0.

A command for independently checking a plain-language claim about a graph loaded in Gephi, a desktop tool for exploring network data. It returns whether the claim is confirmed, refuted, or impossible to determine, along with the measured number.

In plain words
What is it for?
Use it to verify structural claims about a Gephi graph, report the metric and evidence nodes, check whether the result was verified against the live graph, and record the finding.
Why use it?
It reduces the risk of accepting an untested graph claim or presenting an estimate as a verified result. The check runs separately and can save a JSON record for a methods appendix.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the gephi-network-analysis plugin — 1 skill, 11 commands, 4 agents, 1 hook, 1 MCP server shipped together

Good fit Use it to verify structural claims about a Gephi graph, report the metric and evidence nodes, check whether the result was verified against the live graph, and record the finding.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mattartzanthro/gephi-ai/verify-claim
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/MattArtzAnthro/gephi-ai

Made for: Claude Code.

Or install gephi-network-analysis, the plugin that ships this one along with the rest of its 1 skill, 11 commands, 4 agents, 1 hook, 1 MCP server.

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-claim

README.md
[![agentmods](https://agentmods.dev/badge/commands/mattartzanthro/gephi-ai/verify-claim/github.svg)](https://agentmods.dev/commands/mattartzanthro/gephi-ai/verify-claim)
Your own site
<a href="https://agentmods.dev/commands/mattartzanthro/gephi-ai/verify-claim"><img src="https://agentmods.dev/badge/commands/mattartzanthro/gephi-ai/verify-claim/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 verify-claim

Your own site · 80×15
<a href="https://agentmods.dev/commands/mattartzanthro/gephi-ai/verify-claim"><img src="https://agentmods.dev/badge/commands/mattartzanthro/gephi-ai/verify-claim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 287 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 $0.00026 $0.00287
Opus 5 $0.00013 $0.00143
Sonnet 5 $0.00005 $0.00057
Haiku 4.5 $0.00003 $0.00029

Measured 9d ago against content hash eb923546aa38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

verify-claim 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.

plugins/claude-code/commands/verify-claim.md · 26 lines

What it actually says

Verify a structural claim

Dispatch the claim-verifier agent to check the claim in $ARGUMENTS against the graph currently loaded in Gephi.

The agent runs in its own context (so its measurement runs don't clutter this conversation) and, importantly, verifies independently — it is not invested in the claim being true. It returns a verdict: confirmed / refuted / can't-tell, with the actual number and an honest caveat.

Pass the claim verbatim, and the export path if one was given (the agent passes it to gephi_claim_record, which writes the record as JSON for a methods appendix). If $ARGUMENTS is empty, ask the user what claim they want checked (one sentence), then dispatch.

When the agent returns, relay the record plainly: the verdict, the metric and the numbers, the evidence nodes by label, and whether the receipts were verified against the live graph. Don't soften a "refuted" or a "can't-tell." If the record says verified: false, say so and do not present the numbers as checked.

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 · 26 lines · 26 tokens per session scan A eb923546aa38

Subscribe to this mod's changes

verify-claim is a command published in the GitHub repository MattArtzAnthro/gephi-ai (22 stars, last pushed 7d ago), licensed Apache-2.0. It adds 26 tokens to every session and 287 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 2026-08-30.