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 chandrudp29/skillhub --skill yc-job-trackergit clone --depth 1 https://github.com/chandrudp29/skillhubWrote 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/chandrudp29/skillhub/yc-job-tracker)<a href="https://agentmods.dev/skills/chandrudp29/skillhub/yc-job-tracker"><img src="https://agentmods.dev/badge/skills/chandrudp29/skillhub/yc-job-tracker/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/chandrudp29/skillhub/yc-job-tracker"><img src="https://agentmods.dev/badge/skills/chandrudp29/skillhub/yc-job-tracker.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 | $0.00038 | $0.00726 |
| Opus 5.5 | $0.00015 | $0.00290 |
| Sonnet 5.5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
yc-job-tracker 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 1mo 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.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YC Job Tracker
Automates daily job discovery on workatastartup.com — finds AI/ML engineering roles at YC startups, scores them for fit, and alerts you to new postings.
When to Use
- "Show me AI/ML jobs at YC startups"
- "What new jobs posted today match my profile?"
- "Track jobs at YC startups daily"
- Job searching at YC/startup companies
Setup
git clone https://github.com/chandrudp29/yc-jobs-tracker
cd yc-jobs-tracker
pip install -r requirements.txt
cp .env.example .env
# Add your HYPERBROWSER_API_KEY to .env
Daily Use
# Fetch today's jobs and show top AI/ML matches
python fetch_today.py
# Filter for India/Bengaluru roles only
python fetch_today.py --india
# Load from yesterday's cache (no network request)
python fetch_today.py --load
Start the API
uvicorn api:app --port 8765
Endpoints:
GET /jobs/ai— top AI/ML matches with scoresGET /jobs/new— jobs posted since yesterdayPOST /jobs/fetch— trigger a fresh scrape in background
Scoring System
Jobs are scored on relevance:
| Signal | Points |
|---|---|
| "AI Engineer" / "ML Engineer" in title | 10 |
| "Founding AI Engineer" in title | 12 |
| India / Bengaluru location | 6 |
| LangChain / LangGraph / PyTorch in description | 3 |
| OpenAI / Claude / Bedrock mentioned | 2 |
| Remote | 2 |
Score ≥ 15 = PERFECT match (🟢) Score ≥ 10 = Strong match (🔵)
Daily Automation (9 AM IST)
# Runs daily at 3:30 AM UTC = 9 AM IST
python -c "from scheduler import start; start()"
Cookie Authentication (for full 438-company listing)
Without authentication, workatastartup.com shows ~30 preview listings. For all 438:
- Log in to workatastartup.com in Chrome
- Install "Cookie-Editor" extension
- Export all cookies as JSON
- Save as
cookies.jsonin the project root
The scraper auto-detects cookies.json and injects the session.
Configuration
Edit config.py to customize:
TITLE_BOOST— which job titles to prioritizeLOCATION_BOOST— which locations to weightTECH_BOOST— which tech keywords to score
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.
- 1mo ago First seen · 99 lines · 38 tokens per session scan A f1abe49b15f3
yc-job-tracker is a skill published in the GitHub repository chandrudp29/skillhub (14 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 726 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
cron-task-creator
A scheduler for recurring octo agent tasks. Each task contains a schedule and a prompt, so octo can run an agent turn automatically at the specified times.
workflow-creator
Turn a repeatable multi-step task into a runnable, reusable saved workflow through guided conversation, in either of two shapes — chaining existing skills/recordings (wiring each one's output into the next's input), or composing the workflow script's own primitives (agent/parallel/pipeline) directly when the task…
resume-crafting
A career-writing aid for turning a résumé or cover letter into clear evidence of results. It uses measurable outcomes and adapts the wording to a job description and applicant-tracking systems, or ATS tools that scan applications for relevant terms.
mentor-patterns
The six patterns the Mentor hunts in the records to decide WHEN to speak. Silence is the default; only a real, recurring pattern earns a word. This skill gives the canonical detection method for each pattern (DB query + threshold) so the Mentor never speaks from a single data point. Read-only — never writes to the DB.…
onboarding-flow
Conversational protocol the Assistente follows to onboard the user — first message, iterative one-question-per-turn pacing, blocking checklist (the floor that unlocks the dashboard) vs rich checklist (what makes Writers actually useful), settore-agnostic question style (NEVER assume IT), and the mandatory checkpoint…
apply-flow
How the CLOSER runs one authorised application with applyflow.py — the checkpointed state machine (detect, fill, uploadcv, screening, review, submit), the mandatory receipt without which applied is never written, and what to do on each result, blockedhuman first of all. Use it for every position taken from the queue.…