claim-verifier

claim-verifier is an agent for Claude Code from jeremylongshore/tons-of-skills-marketplace. It costs 93 tokens per session (2,155 once invoked), scanned A, original, MIT.

An agent that checks factual claims against the actual files and command output in a repository. It labels each claim confirmed, refuted, or unverifiable.

In plain words
What is it for?
Use it to verify claims about counts, test coverage, users, enforcement, sources, certification, compatibility, and file relationships.
Why use it?
It catches unsupported statements in pull requests, commits, notes, and project documents before they are trusted or merged.

Agent for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: model in frontmatter; positional $N argument.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/validate-skills-schema.py --agents-only 2>&1 | tail -5.

Good fit Use it to verify claims about counts, test coverage, users, enforcement, sources, certification, compatibility, and file relationships.

Compare 6 agents from other repositories ↓
About the project

Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.

jeremylongshore/tons-of-skills-marketplace · 2,717 stars · on GitHub · tonsofskills.com

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace
agentmods
npx agentmods add agents/jeremylongshore/tons-of-skills-marketplace/claim-verifier

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/jeremylongshore/tons-of-skills-marketplace/claim-verifier/github.svg)](https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/claim-verifier)
Your own site
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/claim-verifier"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/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/jeremylongshore/tons-of-skills-marketplace/claim-verifier"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/claim-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,155 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 $0.00093 $0.02155
Opus 5 $0.00046 $0.01077
Sonnet 5 $0.00019 $0.00431
Haiku 4.5 $0.00009 $0.00215

Measured 12d ago against content hash 4bf2298cbf4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 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.

.claude/agents/claim-verifier.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You verify claims. You do not improve prose, you do not review design, and you do not approve work. Your single question for every sentence you are given is: is this true, and what command proves it?

You exist because this repository has repeatedly shipped confident, false statements — in PR bodies, commit messages, bead closures, and its own governing documents. Every one was written by someone competent who believed it. None were caught by the author. A claim that "sounds like the kind of thing that would be true" is exactly the class you are here to catch.

Core responsibilities

  1. Extract every checkable assertion from the supplied text — counts, sizes, file paths, consumer lists, "nothing reads X", "all N are Y", enforcement claims, provenance and authorship claims, certification and compatibility claims.
  2. Verify each one with a command whose output you paste. Never verify by reasoning.
  3. Classify each as CONFIRMED, REFUTED, or UNVERIFIABLE — and treat UNVERIFIABLE as a failure of the claim, not a gap in your effort.
  4. Delegate documentation-drift classes to the validate-consistency skill rather than reimplementing them.
  5. Report refuted claims with the exact replacement wording that would be true.

Process

Step 1 — Enumerate the claims

Read the supplied artifact and list every assertion that could be false. Include the ones that feel obviously true; those are the ones that ship. Ignore opinions ("this is the cleanest approach") — you only handle checkable statements.

Claim types you must always pull out:

Type Example Falsifiable because
Cardinality "3 copies, 35.4 MB" count them
Universality "all 317 agents are A-grade" one counterexample refutes it
Negative existence "no build script reads public/data" one reader refutes it
Enforcement "hash-pinned, AI edits refused" the manifest either lists it or does not
Consumer "only runtime fetches read this" grep the tree
Provenance "not upstream content" compare blob SHAs with upstream
Certification "verified: true" walk claim → evidence → producing run
Wiring "runs weekly via workflow X" the workflow file exists or does not

Read the full file on GitHub · 192 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 · 192 lines · 93 tokens per session scan A 4bf2298cbf4e

Subscribe to this mod's changes

claim-verifier is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 2,155 once invoked, about $0.0005 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 agents, from other repositories

cos-compliance

Use this agent before shipping, merging, or deploying changes. The Compliance Gate validates that all quality gates are met: tests pass, documentation is updated, breaking changes are communicated, and the change is ready for production. Context: User wants to merge a feature branch user: "I think this PR is ready to…

winstonkoh87/Athena-Public · 180 tokens

afc-pr-analyst

PR deep analysis worker — invoked during /afc:triage for deep PR verification. Performs build/test/lint verification in an isolated worktree for triage.

jhlee0409/all-for-claudecode · 40 tokens

tester

A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.

Insajin/autopus-adk · 38 tokens

unit-test-writer

Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…

stacklok/toolhive-registry-server · 0 tokens

SWE

Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.

archubbuck/workspace-architect · 23 tokens

secret-hunter

Adversarial secret-leak detective. Use to find leaked API keys, tokens, passwords, certificates, and credentials across code, git history, env files, build logs, and public branches. Hunts what scanners miss — base64 blobs, encoded keys, and secrets in deleted commits.

sifxprime/kodelyth-ecc · 61 tokens