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.
git clone --depth 1 https://github.com/leopu00/job-hunter-teamnpx agentmods add skills/leopu00/job-hunter-team/recheck-livenessWrote 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.
[](https://agentmods.dev/skills/leopu00/job-hunter-team/recheck-liveness)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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 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)
- fast curl: HTTP code + scan for closed-markers (EN+IT) + 404/410.
- ATS-JS / LinkedIn host or ambiguous code → escalate to the BROWSER (Playwright render) and re-scan the markers on the RENDERED HTML.
- still uncertain →
OPEN_UNVERIFIED— NEVER a false-open (resiliencepattern).
Golden rule
is_open=1ONLY ifstate == OPEN.state == CLOSED→status='expired'+ a note carrying theevidence.state == OPEN_UNVERIFIED→ leaveis_openunchanged + 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) |
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.
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.
- 12d ago First seen · 73 lines · 88 tokens per session scan A 5c0dfda6e0f2
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.
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".
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.
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.
playwright-cli
Skill "playwright-cli" from Insajin/autopus-adk, covering browser automation with playwright-cli, quick start, commands, core and navigation.
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.
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.