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 YuxuanSha/openceph --skill hn-radargit clone --depth 1 https://github.com/YuxuanSha/opencephWrote 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/yuxuansha/openceph/hn-radar)<a href="https://agentmods.dev/skills/yuxuansha/openceph/hn-radar"><img src="https://agentmods.dev/badge/skills/yuxuansha/openceph/hn-radar/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/yuxuansha/openceph/hn-radar"><img src="https://agentmods.dev/badge/skills/yuxuansha/openceph/hn-radar.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 | $0.00052 | $0.00811 |
| Opus 5 | $0.00026 | $0.00405 |
| Sonnet 5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
hn-radar 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 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.
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.
What it actually says
HN Radar
General-purpose Hacker News monitoring tentacle. Fetches latest posts by default, runs each through LLM-powered smart screening, and reports worthy items to Brain for user notification.
Works Out of the Box
- Default data source:
newest(all latest posts, no score threshold) - Default filtering: LLM-powered smart evaluation (
USE_LLM_FILTER=true) - Works immediately after deployment, no additional configuration needed
Custom Modes
- Traditional mode:
USE_LLM_FILTER=false+HN_MIN_SCORE=50+HN_MIN_COMMENTS=20 - Multiple data sources:
HN_FEEDS=newest,frontpage,search - High-frequency scanning:
HN_INTERVAL_SECONDS=60
What ships with it
18 files 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.
- docs/hn-api-reference.md 116 B
- prompt/CONSULTATION.md 1.2 KB
- prompt/SYSTEM.md 1.4 KB
- prompt/TOOLS.md 872 B
- README.md 2.7 KB
- src/__pycache__/db.cpython-314.pyc 3.4 KB
- src/__pycache__/filter_engine.cpython-314.pyc 6.3 KB
- src/__pycache__/hn_fetcher.cpython-314.pyc 6.4 KB
- src/__pycache__/hn_tools.cpython-314.pyc 14 KB
- src/__pycache__/ipc_client.cpython-314.pyc 5.9 KB
- src/__pycache__/main.cpython-314.pyc 6.6 KB
- src/filter_engine.py 6.8 KB runs code
- src/hn_fetcher.py 2.7 KB runs code
- src/hn_tools.py 7.8 KB runs code
- src/main.py 17 KB runs code
- src/requirements.txt 41 B
- tests/dry_run.py 653 B runs code
- tools/tools.json 2.9 KB
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 · 87 lines · 52 tokens per session scan A 60fdc3ed9223
hn-radar is a skill published in the GitHub repository YuxuanSha/openceph (11 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 811 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
gmail-email
Send emails via Gmail SMTP using App Password authentication.
example-skill
Example skill that demonstrates the gitagent skills system. Use this to test skill loading and script execution.
cron
Schedule reminders and recurring tasks.
docx
Create, read, and edit Word documents — research papers, reports, proposals, and manuscripts. Use when the user asks to generate, modify, or analyze .docx files, convert .doc to .docx, or work with tracked changes and comments.
xlsx
Create, edit, and analyze Excel spreadsheets — research data, experimental results, statistical analysis, and data visualization. Use when the user asks to build, modify, or analyze .xlsx files, create financial models, work with formulas, or generate data reports.
dingtalk-channel-connect
Use a visible browser to automatically set up ResearchClaw's DingTalk channel integration — creating an enterprise app, configuring the bot, and publishing. Use when the user wants to connect DingTalk, create a DingTalk bot, or configure DingTalk channel credentials.