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 agentrhq/agent-automation-skills --skill x-twitter-viral-radargit clone --depth 1 https://github.com/agentrhq/agent-automation-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/agentrhq/agent-automation-skills/x-twitter-viral-radar)<a href="https://agentmods.dev/skills/agentrhq/agent-automation-skills/x-twitter-viral-radar"><img src="https://agentmods.dev/badge/skills/agentrhq/agent-automation-skills/x-twitter-viral-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/agentrhq/agent-automation-skills/x-twitter-viral-radar"><img src="https://agentmods.dev/badge/skills/agentrhq/agent-automation-skills/x-twitter-viral-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 | $0.00112 | $0.03050 |
| Opus 5 | $0.00056 | $0.01525 |
| Sonnet 5 | $0.00022 | $0.00610 |
| Haiku 4.5 | $0.00011 | $0.00305 |
Grade B, and why
x-twitter-viral-radar 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.
chmod 600 ~/.viral-radar/config.env How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X/Twitter Viral Radar
X/Twitter Viral Radar installs a user-owned cron job on this machine. Everything under
~/.viral-radar/ belongs to the user, and the scheduled runs execute plain
local Python only — they never invoke an LLM, an agent, or this skill. Your job
is to set that automation up correctly (or inspect, tune, and remove it), then
get out of the way.
Files the automation uses:
| Path | Purpose |
|---|---|
~/.viral-radar/viral-timeline.py |
The scan script (copied from scripts/viral-timeline-template.py) |
~/.viral-radar/config.env |
Settings + webhook URL (mode 0600) |
~/.viral-radar/state.sqlite3 |
Delivery log used for deduplication |
~/.viral-radar/output/ |
One JSON evidence file per run |
~/.viral-radar/logs/ |
viral-radar.log (stdout) and viral-radar.err (stderr) |
Route by what the user needs:
- Set it up → Install
- "Is it working?" → Verify
- Change schedule, thresholds, or destination → Update
- Errors, missed alerts, duplicates, cron not firing → read
references/troubleshooting.md - Uninstall → Removal
How detection works
Understanding the detector lets you explain alerts and tune thresholds with the user instead of treating the numbers as magic.
Each run fetches up to VIRAL_RADAR_LIMIT posts from the For You timeline and
keeps those newer than VIRAL_RADAR_CUTOFF_HOURS. Each post gets an
engagement score weighted toward signals that indicate genuine conversation:
engagement = likes + 3*retweets + 9*replies + 7*quotes + 5*bookmarks
normalized_score = engagement / views ^ VIRAL_RADAR_VIEW_EXPONENT
Dividing by views^exponent rewards posts whose engagement is high relative
to reach — a fast-moving post from a small account outranks a celebrity post
with passive views. A post alerts when its normalized score exceeds
VIRAL_RADAR_THRESHOLD. Posts younger than VIRAL_RADAR_FRESH_HOURS are all
eligible; if none qualify, only the single newest older qualifier is sent, so
a backlog never floods the webhook.
What ships with it
4 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.
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 · 257 lines · 112 tokens per session scan B a2d670b152ea
x-twitter-viral-radar is a skill published in the GitHub repository agentrhq/agent-automation-skills (2 stars, last pushed 24d ago), licensed MIT. It adds 112 tokens to every session and 3,050 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…