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 AmariahAK/atlarix-skills --skill tweetclaw-x-source-contextgit clone --depth 1 https://github.com/AmariahAK/atlarix-skillsWrote 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/amariahak/atlarix-skills/tweetclaw-x-source-context)<a href="https://agentmods.dev/skills/amariahak/atlarix-skills/tweetclaw-x-source-context"><img src="https://agentmods.dev/badge/skills/amariahak/atlarix-skills/tweetclaw-x-source-context/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/amariahak/atlarix-skills/tweetclaw-x-source-context"><img src="https://agentmods.dev/badge/skills/amariahak/atlarix-skills/tweetclaw-x-source-context.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 | $0.00006 | $0.01458 |
| Opus 5.5 | $0.00002 | $0.00583 |
| Sonnet 5.5 | $0.00001 | $0.00292 |
| Haiku 4.5 | $0.00001 | $0.00146 |
Grade A, and why
TweetClaw X Source Context 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TweetClaw X Source Context
When to use this skill
Use this skill when an Atlarix workflow needs grounded X/Twitter context before it drafts, reviews, monitors, or plans social work. TweetClaw is the OpenClaw plugin for X/Twitter automation through the @xquik/tweetclaw npm package.
Good fits:
- Search tweets or search tweet replies for source material.
- Look up users, profiles, followers, media, or public engagement context.
- Export follower or interaction evidence before analysis.
- Monitor tweets or keywords and summarize changes.
- Prepare a reviewed post tweet, post reply, direct message, or webhook action when the user explicitly asked for that X/Twitter action.
- Run giveaway draw evidence collection before the target workflow writes results.
Do not use this skill as a generic writing framework. Keep TweetClaw responsible for X/Twitter source context and OpenClaw-controlled X/Twitter actions. Keep the project, voice, calendar, publishing rules, analytics, and final editorial decisions in the target workflow.
Core patterns
Start from the user's job
Translate the request into a bounded source plan before using tools:
- Goal: what decision, draft, report, or action needs X/Twitter context.
- Scope: handles, tweet URLs, keywords, time window, reply depth, and media needs.
- Output: citations, IDs, URLs, excerpts, metrics, or action-ready parameters.
- Safety: whether the workflow is read-only or could post, reply, DM, follow, delete, monitor, or trigger a webhook.
Prefer small, answerable requests:
- "Find recent replies asking for pricing on this launch tweet."
- "Collect the last 20 public posts from this handle and summarize recurring objections."
- "Check follower context before selecting giveaway winners."
Avoid broad, expensive pulls when a focused query or handle lookup will answer the job.
Install and verify TweetClaw through OpenClaw
Use the explicit npm source selector so setup stays deterministic:
openclaw plugins install npm:@xquik/tweetclaw
openclaw plugins inspect tweetclaw --runtime --json
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 · 127 lines · 6 tokens per session scan A 5efa598b48e0
TweetClaw X Source Context is a skill published in the GitHub repository AmariahAK/atlarix-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 6 tokens to every session and 1,458 once invoked, about $0.0000 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 2026-09-03.
TweetClaw X Source Context compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| TweetClaw X Source ContextAmariahAK/atlarix-skills | Skill | 2 | 1mo ago | Apache-2.0 | A | 6 | Claude Code, Codex |
| social-x-post-cardnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 31 | Claude Code, Codex |
| social-x-post-cardnexu-io/html-anything | Skill | 9.4k | 24d ago | Apache-2.0 | A | 33 | Claude Code, Codex |
| x_guidesiddsachar/row-bot | Skill | 1.7k | today | Apache-2.0 | A | 25 | Claude Code, Codex |
| x_intelmateaix/mateclaw | Skill | 1.2k | yesterday | Apache-2.0 | C | 24 | Claude Code, Codex |
| Xnotforyou23/home23 | Skill | 11 | yesterday | MIT | A | 33 | Claude Code, Codex |
| twitter-agentBankrBot/skills | Skill | 1.2k | 2d ago | none | A | 17 | Claude Code, Codex |