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 agentmods add skills/nirholas/xactions/topic-managementnpx skills add nirholas/XActions --skill topic-managementgit clone --depth 1 https://github.com/nirholas/XActionsWhat 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 | $0.00044 | $0.00472 |
| Opus 5 | $0.00022 | $0.00236 |
| Sonnet 5 | $0.00009 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
topic-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 2d 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
Topic Management
Browser console script for managing X Topics — the interest categories that personalize your timeline.
Script Selection
| Goal | File | Navigate to |
|---|---|---|
| List, follow, unfollow, or discover X Topics | src/topicManager.js |
x.com/i/topics or x.com/settings/your_topics |
Quick Start
- Go to
x.com/i/topicsorx.com/settings/your_topics - Open DevTools (F12) → Console
- Set
actionin CONFIG - Paste
src/topicManager.js→ Enter
Configuration
const CONFIG = {
action: 'list',
// 'list' — list all currently followed topics
// 'follow' — follow topics matching keywords
// 'unfollow' — unfollow topics matching keywords
// 'unfollowAll' — unfollow all topics
// 'discover' — browse suggested topics
// For 'follow' / 'unfollow':
keywords: ['crypto', 'AI', 'startups'], // Topics to match
caseSensitive: false,
};
Controls
window.XActions.abort() // Stop the script
window.XActions.status() // Check progress
Notes
- Navigate to
x.com/i/topicsto browse all topics - Navigate to
x.com/settings/your_topicsto see topics you already follow - Topics directly influence your For You timeline recommendations
- Use
unfollowAllthenfollowwith specific keywords to reset your topic preferences
Related Skills
- algorithm-cultivation — Train your algorithm for a specific niche
- discovery-explore — Browse trending topics and explore
- analytics-insights — Analyze what content your current topics surface
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.
- 2d ago First seen · 63 lines · 44 tokens per session scan A a0e58ed6d0f5
topic-management is a skill published in the GitHub repository nirholas/XActions (496 stars, last pushed 5d ago), licensed Apache-2.0. It adds 44 tokens to every session and 472 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
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
browser-test
Validate a feature works by driving a real browser with Playwright MCP. No test files — just interactive verification.
browser-pair
Collaborative headed browser session for UI work. Launch Playwright Chromium visible to the user, handle auth, then interactively drive the browser while the user watches and gives real-time visual feedback. Edit code and refresh to verify fixes live. Use when the user says 'browser pair', 'paired browser', 'let's…
debug-frontend-with-browser
Frontend diagnosis extension for the acceptance skill. Use for intermittent rendering, ordering, stale-state, navigation, virtual-list, React/Zustand, optimistic-update, refresh-dependent, or browser-only failures where the first broken boundary may be DOM, component input, derived state, client cache, network data…
design-prototype
Produce an interactive single-file HTML design prototype using the REAL LobeHub design system (@lobehub/ui + antd + antd-style tokens) with production-style React — no build step, opens directly in a browser. Use when asked for a design prototype / interactive mockup / 交互原型 / 出个原型 / 设计稿 HTML for a page or flow, or to…
share
Use when a user needs a browser-accessible link to preview, present, or send Agent-generated workspace files, an entire project, or the current topic outside Super Magic—especially rendered output such as HTML that messaging or file-viewing channels cannot display directly—or when they need to find, reuse, change, or…