recheck-liveness

recheck-liveness is a skill for Claude Code from leopu00/job-hunter-team. It costs 88 tokens per session (937 once invoked), scanned A, original, MIT.

A procedure for checking whether an online job posting is genuinely still open. It checks normal web pages and, when needed, pages whose status appears only after JavaScript runs or behind a LinkedIn login barrier.

In plain words
What is it for?
Rechecking job URLs, identifying open or closed postings, handling sites such as Ashby, Workday, Greenhouse, and LinkedIn, and returning an explicitly unverified result when the status cannot be confirmed.
Why use it?
A successful web request does not prove that a job is active, so this avoids marking expired or unverifiable postings as open.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Bash(python3 /app/shared/skills/recheck_liveness.py *), Bash(python3 /app/shared/skills/db_update.py *).

Good fit Rechecking job URLs, identifying open or closed postings, handling sites such as Ashby, Workday, Greenhouse, and LinkedIn, and returning an explicitly unverified result when the status cannot be confirmed.

Compare 6 skills from other repositories ↓
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/leopu00/job-hunter-team
agentmods
npx agentmods add skills/leopu00/job-hunter-team/recheck-liveness

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 recheck-liveness

README.md
[![agentmods](https://agentmods.dev/badge/skills/leopu00/job-hunter-team/recheck-liveness/github.svg)](https://agentmods.dev/skills/leopu00/job-hunter-team/recheck-liveness)
Your own site
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/recheck-liveness"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/recheck-liveness/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 recheck-liveness

Your own site · 80×15
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/recheck-liveness"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/recheck-liveness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 937 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00088 $0.00937
Opus 5 $0.00044 $0.00468
Sonnet 5 $0.00018 $0.00187
Haiku 4.5 $0.00009 $0.00094

Measured 12d ago against content hash 5c0dfda6e0f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

recheck-liveness scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Check whether a job posting is STILL OPEN without producing false-opens. Replaces the ad-hoc curl (HTTP 200 = "open") that does NOT see the expiry rendered in JavaScript (Ashby/Workday/Greenhouse) nor the Li
agents/_skills/recheck-liveness/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

recheck-liveness — "is the job still open?", done properly

Why it exists

The old recheck was an improvised curl (code=200 marker=none → open). curl only sees the RAW HTML, so on many ATS (Ashby/Workday/Greenhouse) and on LinkedIn the "expired/closed" status is rendered in JS or sits behind an authwall → curl does not see it → is_open=1 on jobs that are already CLOSED. Dirty data downstream (score, map).

How to use it

python3 /app/shared/skills/recheck_liveness.py "<url>" "[optional title]"

JSON output + exit code:

state exit meaning
OPEN 0 verified open
CLOSED 1 closed/expired (404/410 or closed-marker)
OPEN_UNVERIFIED 2 impossible to verify (JS/authwall host + browser down)

What it does (tiered)

  1. fast curl: HTTP code + scan for closed-markers (EN+IT) + 404/410.
  2. ATS-JS / LinkedIn host or ambiguous code → escalate to the BROWSER (Playwright render) and re-scan the markers on the RENDERED HTML.
  3. still uncertain → OPEN_UNVERIFIED — NEVER a false-open (resilience pattern).

Golden rule

  • is_open=1 ONLY if state == OPEN.
  • state == CLOSEDstatus='expired' + a note carrying the evidence.
  • state == OPEN_UNVERIFIEDleave is_open unchanged + an [OPEN_UNVERIFIED] note; do NOT pass it off as open.
  • The ad-hoc "200 = open" curl is forbidden as a way to decide liveness.

How to record the outcome

Record every check in the history, even when it changes nothing. last_checked only retains the latest date and overwrites the previous one; without an event, nobody can tell how many times a position was checked or how many attempts ended without a conclusion.

Map the probe state one-to-one to --outcome:

state command
OPEN --action liveness_check --outcome confirmed_open --is-open true
CLOSED --action liveness_check --outcome confirmed_closed --is-open false --status expired
OPEN_UNVERIFIED --action liveness_check --outcome inconclusive (no --is-open)

Read the full file on GitHub · 73 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. 12d ago First seen · 73 lines · 88 tokens per session scan A 5c0dfda6e0f2

Subscribe to this mod's changes

recheck-liveness is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 937 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agentcookie-install

Install agentcookie on a Mac source and a Linux or Mac sink so Chrome cookies sync continuously over Tailscale. Use when the user says "install agentcookie", "set up cookie sync", "share my Chrome sessions with my agent box", or "make my agent log in as me".

mvanhorn/agentcookie · 63 tokens

tauri-mcp-cli

Use the Tauri MCP CLI to start and recover driver sessions, automate Tauri webviews, capture UI state, debug IPC, and work with mobile or remote devices. Use whenever an agent needs to operate a Tauri v2 app from terminal commands.

hypothesi/mcp-server-tauri · 57 tokens

browser-automation

A browser-automation workflow that detects the terminal environment and chooses a browser control tool. It supports opening pages, taking snapshots, clicking, filling fields, and other checks.

Insajin/autopus-adk · 34 tokens

playwright-cli

Skill "playwright-cli" from Insajin/autopus-adk, covering browser automation with playwright-cli, quick start, commands, core and navigation.

Insajin/autopus-adk · 32 tokens

goofish-overview

An overview and entry point for goofish-cli, a tool package for helping an AI agent operate Xianyu, a Chinese second-hand marketplace. It covers account checks, listing items, buyer messages, risk checks, and shop diagnosis, and directs specific jobs to dedicated workflows.

fancyboi999/goofish-cli · 143 tokens

skill-constraints

Enforce browser automation safety constraints — tool usage order, anti-detection rules, screenshot discipline, and human-in-the-loop checks. Use when setting up or verifying browser/MCP tool operations, NOT for every skill execution.

rexleimo/aios · 48 tokens