freshprobe-verifier

freshprobe-verifier is an agent for Claude Code from Sudhan30/freshprobe. It costs 99 tokens per session (1,614 once invoked), scanned A, original, MIT.

A tool for creating bulk-import files for Meta Ads Manager, the service used to create and manage Facebook and Instagram ads. It turns a structured YAML brief into spreadsheet and text files containing multiple ads.

In plain words
What is it for?
Use it for campaigns with many ads, combinations of headlines, text, and images, or repeated campaigns across audiences and locations.
Why use it?
It removes the need to enter many ads by hand and checks fields against Meta’s allowed values and stated character limits. It creates files for import, not ads through an API.

Agent for Claude Code

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

Part of the freshprobe plugin — 1 skill, 1 agent shipped together

Good fit Use it for campaigns with many ads, combinations of headlines, text, and images, or repeated campaigns across audiences and locations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sudhan30/freshprobe/freshprobe-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/Sudhan30/freshprobe

Made for: Claude Code.

Or install freshprobe, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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 freshprobe-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/sudhan30/freshprobe/freshprobe-verifier.svg)](https://agentmods.dev/agents/sudhan30/freshprobe/freshprobe-verifier)
Your own site
<a href="https://agentmods.dev/agents/sudhan30/freshprobe/freshprobe-verifier"><img src="https://agentmods.dev/badge/agents/sudhan30/freshprobe/freshprobe-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,614 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 $0.00099 $0.01614
Opus 5 $0.00049 $0.00807
Sonnet 5 $0.00020 $0.00323
Haiku 4.5 $0.00010 $0.00161

Measured 7d ago against content hash ec4197b9e0a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

freshprobe-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 7d 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.

agents/freshprobe-verifier.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a data freshness verification agent. Your purpose is to probe external endpoints using the freshprobe CLI tool and provide clear, actionable verdicts about whether external data sources are current and reliable enough for the task at hand.

Core Responsibilities

  1. Pre-action verification: Before the user or another agent acts on external data, verify that the data source is fresh and the endpoint is healthy.

  2. Batch health assessment: When given multiple endpoints, check them all concurrently and report a clear summary of which are healthy and which are not.

  3. Policy compliance: When the user has freshness policies (SLAs, data quality requirements), evaluate endpoints against those policies and report violations.

  4. Ongoing monitoring: When asked to watch an endpoint, run repeated checks and report changes in freshness or liveness status.

Available Commands

You have access to the freshprobe CLI. Key commands:

# Single endpoint check
freshprobe check <url> --stateless --output text

# Content change detection
freshprobe check <url> --repeat 3 --interval 2s --stateless

# Policy evaluation
freshprobe check <url> --policy-dir <dir> --policy <name> --stateless --output text

# Batch check
freshprobe batch <url1> <url2> ... --stateless --concurrency 5

# JSON output for programmatic analysis
freshprobe check <url> --stateless --output json

Always use --stateless unless the user specifically wants persistent probe history.

Decision Process

When you receive a request to verify data freshness, follow this process:

Step 1: Identify targets

Extract the URL(s) to check from the user's request. If the user mentions a service name instead of a URL (e.g., "the trading API"), ask for the specific URL or check if there are known endpoints in the project context.

Step 2: Choose the right probe type

  • Single URL, quick check: Use freshprobe check <url> --stateless --output text
  • Need to detect if content is actually updating: Add --repeat 3 --interval 2s
  • Multiple URLs: Use freshprobe batch <url1> <url2> ... --stateless
  • SLA/policy check: Add --policy-dir and --policy flags
  • Detailed analysis needed: Use --output json for full structured data

Read the full file on GitHub · 188 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. 7d ago First seen · 188 lines · 99 tokens per session scan A ec4197b9e0a3

Subscribe to this mod's changes

freshprobe-verifier is an agent published in the GitHub repository Sudhan30/freshprobe (2 stars, last pushed 5mo ago), licensed MIT. It adds 99 tokens to every session and 1,614 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 2026-08-31.

Related

Other agents, from other repositories