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 oyi77/1ai-skills --skill job-huntergit clone --depth 1 https://github.com/oyi77/1ai-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/oyi77/1ai-skills/job-hunter)<a href="https://agentmods.dev/skills/oyi77/1ai-skills/job-hunter"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/job-hunter/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/oyi77/1ai-skills/job-hunter"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/job-hunter.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 | $0.00041 | $0.03943 |
| Opus 5 | $0.00020 | $0.01972 |
| Sonnet 5 | $0.00008 | $0.00789 |
| Haiku 4.5 | $0.00004 | $0.00394 |
Grade B, and why
job-hunter scanned grade B 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **System deps**: `sudo apt install libreoffice-writer` (converts .docx for ATS re-parsing) or `brew install pandoc` How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Hunter
When to Use
Trigger phrases:
- "job hunter"
- "Help me with job hunter"
Use cases:
- When the task matches this skill's domain expertise
When NOT to use:
- For tasks outside this skill's scope
I am an advanced, state-aware job hunting agent. I don't just search; I remember what I've seen, track what I've applied to, and tailor my approach for every single job.
When NOT to Use
- For one-off tasks that will never repeat
- When the process requires human judgment at every step
- When the cost of automation exceeds the cost of manual execution
Overview
Job Hunter automates workflow automation to reduce manual effort and increase reliability.
The modern job search is a funnel: discover → score → tailor → submit → follow up → analyze. Each stage has measurable KPIs — response rate per platform, interview conversion, offer rate — that compound when optimized systematically. A human juggling 20+ applications across LinkedIn, Indeed, and Glassdoor cannot track this state manually without errors and missed follow-ups.
An autonomous job-hunting agent maintains persistent state across the entire search. It remembers every job it has seen, scored, applied to, followed up on, and where each stands. This state prevents duplicate effort (the same job posted on LinkedIn and Indeed is caught once), enables trend analysis (which role titles convert best, which platforms yield the highest response rate), and powers automated follow-up sequences that increase callback rates by 30-50% over no follow-up.
The core technical stack involves web scraping or API-based integration with job platforms, a text-similarity scorer (TF-IDF or embedding-based) to match job descriptions against the target profile, a document generation engine for tailored resumes and cover letters, and a state database (SQLite, JSON-backed) for cross-session persistence. Optional additions include email open tracking (via tracking pixel) for follow-up analytics and a lightweight classifier to score job fit beyond simple keyword matching.
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 · 290 lines · 41 tokens per session scan B 7b39efc7e518
job-hunter is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 3,943 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-creator
Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
workflow-automation
Automate complex workflows and repetitive tasks using AI agents and tool integration. Use when user wants to create automated pipelines, integrate multiple services, or build task-specific agents.
hourly-rate-time
A time-management method based on assigning a high personal value to each hour. It treats time as a limited resource and uses that value to decide which tasks to do, outsource, or skip.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.