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 Epistates/sparX --skill engagegit clone --depth 1 https://github.com/Epistates/sparXWrote 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/epistates/sparx/engage)<a href="https://agentmods.dev/skills/epistates/sparx/engage"><img src="https://agentmods.dev/badge/skills/epistates/sparx/engage/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/epistates/sparx/engage"><img src="https://agentmods.dev/badge/skills/epistates/sparx/engage.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 | $0.00050 | $0.02612 |
| Opus 5.5 | $0.00020 | $0.01045 |
| Sonnet 5.5 | $0.00010 | $0.00522 |
| Haiku 4.5 | $0.00005 | $0.00261 |
Grade A, and why
engage 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 2mo 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engage — Conversation Velocity via Browser
Manage replies on your X posts to activate the 75–150× author reply conversation multiplier. This skill surfaces comments worth replying to, drafts high-quality replies, and posts them with your approval.
Why this matters: Author replies to comments create conversation threads — the single highest-weight signal in the Phoenix algorithm at 75–150× a like. A post with 5 author reply threads massively outperforms one with none.
Input
The user provides one of:
- A post URL — engage with replies on that specific post
- "notifications" — review recent mentions and replies across all posts
- "replies" — same as notifications, focused on reply tab
- Nothing — defaults to notifications
Process
Step 1 — Get Browser Context
mcp__claude-in-chrome__tabs_context_mcp(createIfEmpty: true)
Step 2 — Navigate
For a specific post:
mcp__claude-in-chrome__navigate(url: "<post_url>", tabId: <tab>)
mcp__claude-in-chrome__computer(action: "wait", duration: 3, tabId: <tab>)
For notifications:
mcp__claude-in-chrome__navigate(url: "https://x.com/notifications", tabId: <tab>)
mcp__claude-in-chrome__computer(action: "wait", duration: 3, tabId: <tab>)
Take a screenshot to verify state:
mcp__claude-in-chrome__computer(action: "screenshot", tabId: <tab>)
If not logged in, stop and tell the user to log in manually.
Step 3 — Collect Comments / Mentions
On a specific post:
- Scroll through the replies section below the post:
mcp__claude-in-chrome__get_page_text(tabId: <tab>)
- Use JavaScript to extract reply content:
mcp__claude-in-chrome__javascript_tool(action: "javascript_exec", text: "
const articles = document.querySelectorAll('article');
const replies = Array.from(articles).slice(1).map((article, i) => {
const text = article.innerText;
const ariaLabels = Array.from(article.querySelectorAll('[aria-label]'))
.map(el => el.getAttribute('aria-label'));
return { index: i, text: text.substring(0, 300), meta: ariaLabels.slice(0, 5) };
});
JSON.stringify(replies.slice(0, 15), null, 2);
", tabId: <tab>)
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.
- 2mo ago First seen · 258 lines · 50 tokens per session scan A 2c15df688513
engage is a skill published in the GitHub repository Epistates/sparX (4 stars, last pushed 7mo ago), licensed MIT. It adds 50 tokens to every session and 2,612 once invoked, about $0.0002 per session on Opus 5.5. 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.
engage compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| engageEpistates/sparX | Skill | 4 | 7mo ago | MIT | A | 50 | Claude Code |
| x402browser-use/browser-use | Skill | 120k | yesterday | MIT | A | 175 | Claude Code |
| browser-usebrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 57 | Claude Code, Codex |
| remote-browserbrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 22 | Claude Code |
| cloudbrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 177 | Claude Code |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| opencli-browserjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 43 | Claude Code |