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.
npx agentmods add skills/treymorgan/jobsearch-apply-mcp/job-scrapernpx skills add treymorgan/jobsearch-apply-mcp --skill job-scrapergit clone --depth 1 https://github.com/treymorgan/jobsearch-apply-mcpWhat 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 | $0.00063 | $0.04982 |
| Opus 5 | $0.00032 | $0.02491 |
| Sonnet 5 | $0.00013 | $0.00996 |
| Haiku 4.5 | $0.00006 | $0.00498 |
Grade A, and why
scrape 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 today.
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.
fields manually. If it returns HTTP 403, retry with browser headers via curl per This is a copy
92% identical to scrape — 50 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Scraper
How It Works
This skill searches job portals using the installed portal-search CLIs in
.agents/skills/ (plus WebSearch as a fallback), using queries from jobsearch.config.json.
It deduplicates against previously seen jobs and the application tracker, and
presents new matches with a quick fit assessment.
Invocation
The user triggers this skill by saying things like:
- "Find new jobs"
- "Scrape for jobs"
- "Any new positions?"
- "/scrape"
Optional arguments:
- A focus area, e.g. "/scrape data science" or "/scrape geophysics"
- "broad" to run all search categories, e.g. "/scrape broad"
- "health" to run the portal health check only (Step 4.75), without searching, deduplicating, or presenting jobs - e.g. "/scrape health", or "/scrape health freehire" to probe one portal even if disabled
Execution Steps
Step 0: Load State
- Read
job_scraper/seen_jobs.json(create if missing - start with{"seen": {}}) - Read
job_search_tracker.csvto extract already-applied companies+roles - Read
jobsearch.config.jsonfor the configured search market, query list, filters, and deal-breakers - Read
search-queries.md(this directory) for the search strategy guide
Step 1: Search
Read jobsearch.config.json for the actual query terms and market settings. Read search-queries.md (this directory) only for guidance on structuring and expanding those terms. By default, run the configured search.queries in priority order. If the user said "broad", include lower-priority configured queries and any safe fallback templates from the guide. If the user specified a focus area (e.g. "data science"), prioritize configured queries that match that focus and generate 2-3 focus-specific variants.
Use the installed CLI tools as the primary search mechanism. Fall back to WebSearch only for portals that do not have a CLI skill, or if bun is unavailable on the system.
1a. Check bun availability
bun --version
If this fails (bun not installed), skip to 1c (WebSearch fallback) for all portals and note the fallback in the Step 5 output.
What ships with it
1 file 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.
- today First seen · 271 lines · 63 tokens per session scan A b0388d0d7e51
scrape is a skill published in the GitHub repository treymorgan/jobsearch-apply-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 4,982 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 92% identical to scrape, differing in 50 lines, and is treated as a copy.
Other skills, from other repositories
pilot
One autonomous Pilot cycle - fetch the agenda, execute the top item, journal, exit. Injected by the terminal host - not for manual invocation loops.
apply
Apply to a single job (URL or pasted page) with fit review, or score and apply the job links pasted into an apply campaign when no argument is given.
tanstack-form-composition
Migrate a React @tanstack/react-form codebase from the prop-drilled useForm + erased-form-type pattern to the official createFormHook composition API (useAppForm / withForm / field.X). Use when a project threads a form object (often cast to an any-erased type like ReactFormExtendedApi ) through field-wrapper…
auto-apply
Search a job board and autonomously apply to matching jobs one at a time, until paused, exhausted, or the max-applications cap is hit.
networking
Find a hiring manager/recruiter for a role (or company) and send a personalized message via cold email or LinkedIn, with per-campaign channels and autonomy.
teaser-video
Film, cut, and deliver a short teaser/demo video of any app by driving it with Playwright and editing with ffmpeg - storyboard, authenticated capture, PII review, animated title cards, MP4 + GIF. Use for "make a teaser", "record a demo video", "product launch video", "screen recording for the README".