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.
git clone --depth 1 https://github.com/cyn-zhang/job-radarWrote 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/commands/cyn-zhang/job-radar/job-setup)<a href="https://agentmods.dev/commands/cyn-zhang/job-radar/job-setup"><img src="https://agentmods.dev/badge/commands/cyn-zhang/job-radar/job-setup/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/commands/cyn-zhang/job-radar/job-setup"><img src="https://agentmods.dev/badge/commands/cyn-zhang/job-radar/job-setup.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 | $0.00011 | $0.02127 |
| Opus 5 | $0.00005 | $0.01064 |
| Sonnet 5 | $0.00002 | $0.00425 |
| Haiku 4.5 | $0.00001 | $0.00213 |
Grade A, and why
job-setup 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 10d 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the JobRadar setup wizard. Guide the user through creating their config.yaml step by step. Be conversational, friendly, and concise. Show one section at a time — never dump all questions at once.
Step 0 — Check for existing config
Check if config.yaml exists in the current directory.
If it exists:
✅ config.yaml already exists.
Current settings:
Name: {hunter.name}
Level: {hunter.level}
Roles: {hunter.roles joined by ", "}
Locations: {hunter.locations joined by ", "}
Industry: {hunter.industry joined by ", "}
University:{hunter.university or "not set"}
Want to:
1) Keep it as-is and start scanning → /job-scan
2) Edit specific settings → tell me what to change
3) Reset and redo setup → say "reset config"
Stop here and wait for the user's choice.
Step 1 — Welcome
If no config.yaml exists, greet the user:
👋 Welcome to JobRadar! Let's set up your personal config — takes about 2 minutes.
First, what's your name?
Wait for their answer. Save as {name}.
Step 2 — Email
What email should we send your daily job digest to?
Wait. Save as {email}.
Step 2.5 — Alumni networking profile
Ask these three short questions. These fields power /job-network; users may skip them and add them later.
For alumni networking, what university or school should I search from?
Example: University of Melbourne
Press Enter to skip for now.
Wait. Save as {university}. If skipped, save as an empty string.
What majors or fields of study should count as close matches?
Examples: Computer Science, Software Engineering, Information Technology
Press Enter to skip for now.
Wait. Parse into a list as {majors}. If skipped, save as an empty list.
What graduation year should I search around?
Example: 2025
Press Enter to skip for now.
Wait. Save as {graduation_year} as an integer if provided. If skipped, save as null.
Step 3 — Career level
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.
- 10d ago First seen · 315 lines · 11 tokens per session scan A 12cf857e7e17
job-setup is a command published in the GitHub repository cyn-zhang/job-radar (3 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 2,127 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
replay
Summarize one Agent Monitor session by id — header plus a concise transcript recap.
firm
Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved.
ship-an-mcp-server
Workflow recipe — make your product agent-usable by chaining 4 skills, spec to pricing.
ship-a-feature
Workflow recipe — take a feature idea from fuzzy brief to launch plan by chaining 5 skills.
rescue-an-account
Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
setup-context
Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you.