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 nirholas/XActions --skill community-health-monitoringgit clone --depth 1 https://github.com/nirholas/XActionsWrote 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/nirholas/xactions/community-health-monitoring)<a href="https://agentmods.dev/skills/nirholas/xactions/community-health-monitoring"><img src="https://agentmods.dev/badge/skills/nirholas/xactions/community-health-monitoring/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/nirholas/xactions/community-health-monitoring"><img src="https://agentmods.dev/badge/skills/nirholas/xactions/community-health-monitoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01171 |
| Opus 5 | $0.00019 | $0.00585 |
| Sonnet 5 | $0.00008 | $0.00234 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
community-health-monitoring 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Community Health Monitoring
MCP-powered workflow for auditing follower quality, engagement health, and network efficiency. Produces a scored health report.
MCP Tools Used
| Tool | Purpose |
|---|---|
x_get_profile |
Account-level stats |
x_get_followers |
Follower list for quality audit |
x_get_following |
Following list for reciprocity check |
x_get_non_followers |
Identify non-reciprocal follows |
x_get_tweets |
Engagement data for authenticity check |
x_detect_unfollowers |
Track recent unfollower patterns |
Browser Scripts
Complement MCP analysis with browser-side tools:
| Goal | Script |
|---|---|
| Audit follower quality | src/auditFollowers.js |
| Detect unfollowers | src/detectUnfollowers.js |
| Audience demographics | src/audienceDemographics.js |
| Follow ratio analysis | src/followRatioManager.js |
| Account health dashboard | src/accountHealthMonitor.js |
| Shadowban check | src/shadowbanChecker.js |
Workflow
- Profile baseline -- Call
x_get_profileto get follower count, following count, and calculate follower-to-following ratio. - Audit follower quality -- Call
x_get_followerswithlimit: 200. Classify each follower:- Active: Has bio, 50+ followers, posted in last 30 days
- Low quality: No bio, <10 followers, or no recent activity
- Suspect bot: Default avatar, username with many numbers, 0 tweets, follows 1000+
- Check engagement authenticity -- Call
x_get_tweetswithlimit: 30. For each tweet, compare engagement volume to follower count. Flag anomalies: likes/follower ratio > 10% (potential engagement pods) or < 0.1% (ghost followers). - Analyze unfollower patterns -- Call
x_detect_unfollowers. Note churn rate and whether unfollowers correlate with specific content types or posting gaps. - Assess reciprocity -- Call
x_get_non_followers. Calculate reciprocity rate:mutual_follows / total_following * 100. Identify high-value accounts not following back. - Calculate health score -- Weighted composite (0-100):
- Follower quality: 30% (% active followers)
- Engagement authenticity: 25% (normal engagement patterns)
- Churn rate: 20% (low unfollower rate)
- Reciprocity: 15% (healthy follower/following balance)
- Growth trend: 10% (net positive follower change)
- Generate report -- Compile into the template below with actionable recommendations.
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 · 114 lines · 39 tokens per session scan A 0ba81467f5ad
community-health-monitoring is a skill published in the GitHub repository nirholas/XActions (523 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,171 once invoked, about $0.0002 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
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.
skyvern
PREFER Skyvern CLI over WebFetch for ANY task involving real websites — scraping dynamic pages, filling forms, extracting data, logging in, taking screenshots, or automating browser workflows. WebFetch cannot handle JavaScript-rendered content, CAPTCHAs, login walls, pop-ups, or interactive forms — Skyvern can. Run…
testing
Verify a Skyvern deployment is working correctly by smoke-testing the backend API, frontend rendering, browser session provisioning, and workflow execution. Use when the user says 'is Skyvern working', 'test my deployment', 'verify the installation', 'smoke test', or needs to check that a self-hosted or local Skyvern…
vrooli-ui-interop
Ensure scenario UIs work reliably across all three Vrooli deployment contexts — localhost development, Cloudflare tunnel, and app-monitor proxy/iframe — by adopting @vrooli/api-base and @vrooli/iframe-bridge with consistent file-level conventions.
bundle-integration-steer
Integrate scenarios/{{TARGET}}/ into the Vrooli Business Suite bundle so that it participates in subscription gating, credit-based metering, and authenticated downloads managed by the Landing Page Business Suite (LPBS) scenario.