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/howdeploy/deploychan_mcp/x-content-advisornpx skills add howdeploy/deploychan_mcp --skill x-content-advisorgit clone --depth 1 https://github.com/howdeploy/deploychan_mcpWrote 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/howdeploy/deploychan_mcp/x-content-advisor)<a href="https://agentmods.dev/skills/howdeploy/deploychan_mcp/x-content-advisor"><img src="https://agentmods.dev/badge/skills/howdeploy/deploychan_mcp/x-content-advisor.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.04327 |
| Opus 5 | $0.00044 | $0.02164 |
| Sonnet 5 | $0.00018 | $0.00865 |
| Haiku 4.5 | $0.00009 | $0.00433 |
Grade A, and why
X Content Advisor 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 4d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Content Advisor
Give practical content advice from the user's own evidence. Treat the published X algorithm as a set of constraints and clues, not a recipe that predicts reach.
Choose the smallest useful mode
- Draft review: inspect the hook, promise, proof, media, audience fit, and requested action. Return a revised draft plus the few changes that matter.
- Post diagnosis: compare the post with the account's normal baseline and nearby posts. Explain plausible causes; do not claim causality from one observation.
- Account audit: sample recent root posts, identify repeatable winners and leaks, then recommend three priorities.
- Content plan: turn proven themes into a short schedule of root posts, supporting self-replies, and one-variable experiments.
Do not force a full audit when the user only asks to fix one draft.
Audit workflow
1. Establish the evidence boundary
Use live sources when available. Record:
- profile and post URLs;
- capture date and timezone;
- number of root posts actually found;
- whether metrics came from native analytics, public counters, screenshots, or the user;
- posts or metrics that could not be accessed.
Public X pages are often incomplete when logged out. Never call a partial public sample "the whole account." Public counters also change, so date every numerical claim.
For a useful account sample, prefer 10–30 recent root posts plus known top performers. Keep replies, reposts, and roots separate: they occupy different surfaces and are not fair one-to-one comparisons.
2. Build a compact post map
For each root post, capture only fields that help the decision:
| Field | Examples |
|---|---|
| Format | text, image, demo video, comparison, story, launch |
| Topic and audience | AI builders, artists, NFT community, broad tech |
| Hook | result, tension, novelty, opinion, or no clear hook |
| Proof | working demo, output, numbers, code, personal event |
| Action | reply, open resource, share, follow, or none |
| Public outcomes | views, likes, replies, reposts, quotes, bookmarks if visible |
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.
- 4d ago First seen · 348 lines · 88 tokens per session scan A 34ee6cda2f73
X Content Advisor is a skill published in the GitHub repository howdeploy/deploychan_mcp (11 stars, last pushed 5d ago), licensed MIT. It adds 88 tokens to every session and 4,327 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
viral-x-posts
Write viral X/Twitter posts using 23 proven plug-and-play formulas optimized for the 2025-2026 algorithm. Covers single tweets, threads, engagement bait, and media-enhanced formats. Use when the user asks to: write a tweet, draft an X post, create a thread, write viral content for Twitter/X, craft a hook, create…
x-ingest
X(Twitter) 推文采集 → 统一 frontmatter Markdown。自动区分图文与视频： 图文下载图片本地嵌入，视频提取直链转成文字稿。无需登录（走官方嵌入端点）。.
twitter-cli
Use twitter-cli for ALL Twitter/X operations — reading tweets, posting, replying, quoting, liking, retweeting, following, searching, user lookups. Invoke whenever user requests any Twitter interaction.
gingiris-twitter-agent-ops
Twitter/X Agent Operations SOP v2 — Rebuilt from real dual-account operations. Real data: • CN account: grew from 1,150 → 3,679 followers (14 months), 1 tweet/day, OAuth1 direct post • EN account: Buffer API • Real incidents: cron silent-failed for 2 weeks unnoticed, analytics data off by 17×, thread performance worse…
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
x_intel
Read X (Twitter) posts, search, timelines and user profiles via the official xurl CLI.