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 skills add apify/awesome-skills --skill apify-job-boardsgit clone --depth 1 https://github.com/apify/awesome-skillsWrote 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/apify/awesome-skills/apify-job-boards)<a href="https://agentmods.dev/skills/apify/awesome-skills/apify-job-boards"><img src="https://agentmods.dev/badge/skills/apify/awesome-skills/apify-job-boards/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/apify/awesome-skills/apify-job-boards"><img src="https://agentmods.dev/badge/skills/apify/awesome-skills/apify-job-boards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00184 | $0.03300 |
| Opus 5 | $0.00092 | $0.01650 |
| Sonnet 5 | $0.00037 | $0.00660 |
| Haiku 4.5 | $0.00018 | $0.00330 |
Grade A, and why
apify-job-boards 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job boards to one table
Disclosure: the author of this skill owns both Actors it routes to (flash_scraper/multi-jobboard-scraper and flash_scraper/remote-job-aggregator). They are pay-per-result Actors on the Apify Store; no referral or tracking parameters are used anywhere in this skill.
Turn "I need job postings" into one validated, deduplicated dataset by routing the request to the right multi-board Actor, sizing the run so the user knows the cost before it starts, checking the returned locations and vacancy identities, and returning the rows with the board each job was found on. Treat the Actor output as raw input to these checks, not as proof that its location filtering or deduplication succeeded.
Example prompts
Prompts this skill handles:
- "Scrape software engineer jobs in Austin from LinkedIn, Indeed and Glassdoor into one spreadsheet, no duplicates."
- "Give me remote Python developer jobs posted this week across the remote job boards, with salary where listed."
- "Watch Stripe's and OpenAI's careers pages and only tell me about new roles."
For the Austin request, try all three requested boards, then validate each returned location and vacancy identity before delivery. If Glassdoor returns only wrong-city or unverifiable rows, deliver the qualified LinkedIn and Indeed rows as a partial result and report Glassdoor's raw, qualified and deduplicated counts as a board failure. Do not claim three-board coverage merely because Glassdoor returned rows.
Out of scope (the boundary):
- "Apply to these jobs for me" or anything that needs a logged-in account, CAPTCHA solving, or personal data of applicants. This skill only reads public postings; for candidate profiles send the user to the LinkedIn workflows in apify/agent-skills ultimate-scraper.
Prerequisites
- Apify account (sign up)
- Authentication via one of:
apify login(OAuth, if using the Apify CLI)APIFY_TOKENenvironment variable- Token from Apify Console → Settings → Integrations
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 · 168 lines · 184 tokens per session scan A 4ab5c18b645d
apify-job-boards is a skill published in the GitHub repository apify/awesome-skills (251 stars, last pushed yesterday), licensed Apache-2.0. It adds 184 tokens to every session and 3,300 once invoked, about $0.0009 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 2026-09-10.
Other skills, from other repositories
run-task
Execute a single Todo task through In Progress to Review, meeting every acceptance criterion with tests and vibe-lint checks. Refuses Planning-status tasks. Invoked as /agiflow:run-task . Uses gettask, updatetask, createtaskcomment.
agent-phase-closeout
A Chinese-language process for closing out a completed work stage and recording its state. It summarizes finished work, preserves decisions, freezes completed interfaces, and writes a resume checkpoint.
orchestrate
Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.
sync
Re-synchronizes the vault with external sources. In default mode, scans the sources field of all entities, deduplicates URLs, fetches updated content from each source (Confluence, GDocs, GitHub, Markdown), performs incremental diff and delegates writing to /bedrock:preserve. With --people, scans actor repositories via…
preserve
Single write point for the vault. Centralizes entity detection, textual matching, entity creation/update, and bidirectional linking. Accepts structured input (list of entities), free-form input (text, meeting notes, session context), or graphify output (graph.json + obsidian markdown from /graphify pipeline). Use…
vidseeds-projects
Use for VidSeeds MCP project workflows - create a project from YouTube, list/get/snapshot, regenerate metadata (sync or async), translate metadata, apply thumbnails, and update per-platform config before publish.