freshprobe-check

freshprobe-check is a skill for Claude Code from Sudhan30/freshprobe. It costs 100 tokens per session (824 once invoked), scanned A, original, MIT.

A command-line skill for checking whether a web endpoint is healthy, reachable, current, and responding quickly. It can inspect freshness, repeated content changes, DNS, TLS certificates, latency, and policy thresholds.

In plain words
What is it for?
Use it to probe one or more URLs, repeat checks to detect changes, measure response performance, validate TLS and DNS, or apply freshness policies.
Why use it?
It helps distinguish current data from stale data and healthy endpoints from degraded ones before relying on an API or website. It can also report uncertain results when there is not enough evidence.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

Good fit Use it to probe one or more URLs, repeat checks to detect changes, measure response performance, validate TLS and DNS, or apply freshness policies.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Sudhan30/freshprobe
Claude Code
/plugin install 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-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/sudhan30/freshprobe/freshprobe-check/github.svg)](https://agentmods.dev/skills/sudhan30/freshprobe/freshprobe-check)
Your own site
<a href="https://agentmods.dev/skills/sudhan30/freshprobe/freshprobe-check"><img src="https://agentmods.dev/badge/skills/sudhan30/freshprobe/freshprobe-check/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 freshprobe-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/sudhan30/freshprobe/freshprobe-check"><img src="https://agentmods.dev/badge/skills/sudhan30/freshprobe/freshprobe-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 824 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 $0.00100 $0.00824
Opus 5 $0.00050 $0.00412
Sonnet 5 $0.00020 $0.00165
Haiku 4.5 $0.00010 $0.00082

Measured 9d ago against content hash f36f547645c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

freshprobe-check 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.

The scan reads SKILL.md. This mod also ships 4 executable files (examples/batch-check.sh, examples/fingerprint-check.sh, examples/health-check.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/freshprobe-check/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Freshprobe: Data Freshness Verification

Requires freshprobe binary in PATH. Install: go install github.com/Sudhan30/freshprobe/cmd/freshprobe@latest

Commands

Single 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 ${CLAUDE_PLUGIN_ROOT}/policies --policy <name> --stateless --output text

Batch check:

freshprobe batch <url1> <url2> ... --stateless --concurrency 5

Flags

--output text|json, --repeat N, --interval 2s, --timeout 10s, --skip-tls, --skip-dns, --policy <name>, --policy-dir <path>, --stateless

Verdicts

  • FRESH: Data is current, endpoint healthy. Safe to proceed.
  • STALE: Old data or degraded endpoint. Consider retry or fallback.
  • UNKNOWN: Insufficient signals. Use --repeat 3 for fingerprinting.
  • Confidence: 0.0 (no data) to 1.0 (high certainty).

Built-in Policies

Policy Max Staleness Min Freshness Max P95
api-realtime 60s 0.8 500ms
api-standard 5m 0.6 2000ms
static-content 24h 0.3 2000ms
financial-data 30s 0.9 200ms

Common Workflows

"Is this API fresh?" Run freshprobe check <url> --stateless --output text. Check the verdict line.

"Check all endpoints before a batch job" Run freshprobe batch <urls> --stateless. Filter for non-FRESH verdicts.

"Does this meet our SLA?" Run with --policy-dir and --policy. Check Policy: PASS/FAIL line.

"Is content actually updating?" Run with --repeat 3 --interval 2s. Check content_changed_since_last_probe.

"Check TLS certificate" Run basic check. The tls section shows valid, days_remaining, ocsp_status.

Troubleshooting

  • "command not found": Run go install github.com/Sudhan30/freshprobe/cmd/freshprobe@latest and ensure $HOME/go/bin is in PATH.
  • "policy not found": Error lists available policies. Check --policy-dir path.
  • Freshness score 0.5: Endpoint has no cache headers. Add --repeat 3 for fingerprinting.

Read the full file on GitHub · 84 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 84 lines · 100 tokens per session scan A f36f547645c2

Subscribe to this mod's changes

freshprobe-check is a skill published in the GitHub repository Sudhan30/freshprobe (2 stars, last pushed 5mo ago), licensed MIT. It adds 100 tokens to every session and 824 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.