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 unfollow-managementgit 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/unfollow-management)<a href="https://agentmods.dev/skills/nirholas/xactions/unfollow-management"><img src="https://agentmods.dev/badge/skills/nirholas/xactions/unfollow-management/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/unfollow-management"><img src="https://agentmods.dev/badge/skills/nirholas/xactions/unfollow-management.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 | $0.00076 | $0.00942 |
| Opus 5 | $0.00038 | $0.00471 |
| Sonnet 5 | $0.00015 | $0.00188 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
unfollow-management 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unfollow Management
Browser console scripts for managing who you follow on X/Twitter. All scripts run in DevTools console.
Script Selection
| Goal | File | Navigate to |
|---|---|---|
| Unfollow ALL accounts | src/unfollowEveryone.js |
x.com/USERNAME/following |
| Unfollow only non-followers | src/unfollowback.js |
x.com/USERNAME/following |
| Unfollow non-followers + download log | src/unfollowWDFBLog.js |
x.com/USERNAME/following |
| Time-based smart unfollow with whitelist | src/automation/smartUnfollow.js |
x.com/USERNAME/following |
| Detect who unfollowed you | src/detectUnfollowers.js |
x.com/USERNAME/followers |
| Monitor follow/following ratio + plan | src/followRatioManager.js |
x.com/USERNAME |
| Remove specific followers from YOUR list | src/removeFollowers.js |
x.com/USERNAME/followers |
Script Details
For detailed algorithms, controls, configurations, and DOM selectors for each script, see references/script-details.md.
Rate Limiting & Safety
- Default delay: 1–2 seconds between unfollows (gaussian randomized)
- Batch delay: 2–3 seconds between scroll batches
- Rate limit detection: Scripts check for
[data-testid="toast"]warning banners - Backoff: If rate limited, scripts wait 30–60 seconds before retrying
- Daily limit guidance: X may restrict after ~400 unfollows/day; spread over multiple sessions
- Recovery: If action-restricted, wait 12–24 hours
Strategy Guide
Cleaning a bloated following list
- Run
src/followRatioManager.json your profile to assess current ratio - Use
XActions.plan()to see how many unfollows are needed - Run
src/unfollowback.jsto remove non-followers first (safest) - If more cleanup needed, use
src/unfollowEveryone.jswith abort when satisfied - Re-check ratio with
XActions.track()
Maintaining a healthy ratio over time
- Set up periodic runs of
src/detectUnfollowers.jsto track losses - Use
src/followRatioManager.jsweekly to monitor trends - Run
src/unfollowback.jsmonthly to remove non-reciprocal follows - Keep a whitelist in
smartUnfollow.jsfor accounts you always want to follow
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.
- 9d ago First seen · 80 lines · 76 tokens per session scan A e9772a90e959
unfollow-management is a skill published in the GitHub repository nirholas/XActions (515 stars, last pushed 2d ago), licensed Apache-2.0. It adds 76 tokens to every session and 942 once invoked, about $0.0004 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
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.
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.
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…
browser-automation-studio
Reference for using Browser Automation Studio (BAS) to execute browser workflows, validate UI behavior, and debug automation failures.
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.