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 donvito/skillsbento --skill x-for-you-growthgit clone --depth 1 https://github.com/donvito/skillsbentoWrote 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/donvito/skillsbento/x-for-you-growth)<a href="https://agentmods.dev/skills/donvito/skillsbento/x-for-you-growth"><img src="https://agentmods.dev/badge/skills/donvito/skillsbento/x-for-you-growth/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/donvito/skillsbento/x-for-you-growth"><img src="https://agentmods.dev/badge/skills/donvito/skillsbento/x-for-you-growth.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 | $0.00087 | $0.03576 |
| Opus 5 | $0.00044 | $0.01788 |
| Sonnet 5 | $0.00017 | $0.00715 |
| Haiku 4.5 | $0.00009 | $0.00358 |
Grade A, and why
x-for-you-growth 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X For You Growth
Turn the open-source X For You algorithm (xai-org/x-algorithm) into practical drafting, posting, and engagement coaching. Prefer primary sources (repo README + home-mixer/params/param.rs) over third-party blogs. Production defaults are mirrored into the repo on a cadence; re-check weights before giving numeric advice.
This skill does not post, spam, buy engagement, or game safety systems. It drafts and coaches. Confirm before any live publish.
When to Use
- User wants more reach, impressions, followers, or replies on X/Twitter
- User asks how the X / For You / Phoenix algorithm works for creators
- Drafting hooks, threads, reply strategy, or a posting cadence for X
- Auditing a draft or account against ranking signals
- Comparing formats (text, image, video, quote, thread, link)
Don't use for: LinkedIn-only growth, ad buying playbooks, engagement pods/bots, mass follow-unfollow, or circumventing visibility/safety labels.
Prerequisites
- Optional: fetch latest weights from the public repo before numeric claims
- https://raw.githubusercontent.com/xai-org/x-algorithm/main/home-mixer/params/param.rs
- https://raw.githubusercontent.com/xai-org/x-algorithm/main/README.md
- Scoring math:
home-mixer/scorers/ranking_scorer.rs
- See also
references/param-baselines-2026-08.mdin this skill (snapshot; may go stale)
Core model (what actually ranks)
Sources (parallel)
Thunder → in-network (accounts viewer follows), recent posts
Phoenix retrieval→ out-of-network two-tower similarity
SimClusters → community / engagement-cluster OON
↓
Pre-filters (age ≤ ~48h, blocks/mutes, muted keywords, already seen/served, duplicates, OON retweet/reply rules, …)
↓
Phoenix ranker → P(favorite), P(reply), P(repost), P(quote), P(share…), P(dwell…), P(follow), P(negatives…)
↓
Final Score ≈ Σ (weight_i × P(action_i))
↓
Adjustments: author diversity decay · OON discount · new-author/cold-start boost · VM-ranker diversity reorder
↓
Visibility filtering can DROP / interstitial after rank (spam, safety, labels)
What ships with it
3 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 · 267 lines · 87 tokens per session scan A 65ae5fd02367
x-for-you-growth is a skill published in the GitHub repository donvito/skillsbento (2 stars, last pushed 29d ago), licensed Apache-2.0. It adds 87 tokens to every session and 3,576 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 2026-08-31.
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…