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 SELAT-AI/selat-skills --skill twitter-researchgit clone --depth 1 https://github.com/SELAT-AI/selat-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/selat-ai/selat-skills/twitter-research)<a href="https://agentmods.dev/skills/selat-ai/selat-skills/twitter-research"><img src="https://agentmods.dev/badge/skills/selat-ai/selat-skills/twitter-research/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/selat-ai/selat-skills/twitter-research"><img src="https://agentmods.dev/badge/skills/selat-ai/selat-skills/twitter-research.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 | $0.00169 | $0.02339 |
| Opus 5.5 | $0.00068 | $0.00936 |
| Sonnet 5.5 | $0.00034 | $0.00468 |
| Haiku 4.5 | $0.00017 | $0.00234 |
Grade A, and why
twitter-research 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 22d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
twitter-research
A read-only research toolkit for Twitter/X, backed by SELAT's own first-party
Twitter API (catalog.selat.ai). The manifest wires 9 GET reads at $0.001
each. selat skill run always runs all 9 (about $0.009). When a request needs
only one or two reads, the agent pays just those with individual selat-pay
calls. No API keys, keyless pay-per-call.
When To Use
Use for read/lookup tasks on X: profiling an account, pulling someone's recent posts, seeing who mentions or follows them, analyzing how a specific tweet landed (replies + retweeters), searching for a topic/keyword, or checking regional trends. Read-only — it does not post, like, or follow, and cannot see protected/private accounts.
Workflow
selat skill run twitter-researchruns all 9 steps, every time. The runner has no step-selection flag. Any param you don't pass falls back to its default (openai,AI agents, tweet20, worldwide trends), so a full run also pays for reads you didn't ask about. Pick the path that fits the request.
- Install:
selat skill install twitter-research - Map the request to the reads it needs (table below), then tell the user the cost and wait for a yes — "this is N SELAT-native Twitter reads, about $0.00N — go ahead?"
- Run it one of two ways:
- All 9 reads (~$0.009): use this for a broad sweep, or when the request
touches most of the table. Pass every param so no default leaks in:
selat skill run twitter-research --handle <handle> --query "<query>" --tweetId <id> --woeid <woeid> - Only the reads you need ($0.001 each): pay each selected URL from the
table in
references/endpoints.mdwith its ownselat-paycall. For example:selat-pay GET "https://catalog.selat.ai/twitter/user/info?userName=<handle>" --chain <chain holding your Gateway balance> --max-amount 0.01A paidselat-paycall needs an armed session budget (selat budget start). Its--chainnames the chain holding your Gateway balance; don't hardcode one.
- All 9 reads (~$0.009): use this for a broad sweep, or when the request
touches most of the table. Pass every param so no default leaks in:
- Synthesize for the user in plain language: give the answer, not the JSON. Lead with the finding and the dollar cost. Keep endpoint URLs, wallet addresses, and tweet IDs out of what you relay.
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.
- 22d ago Changed · +22 lines · +2 tokens per session 15ac33912cf7
- 1mo ago First seen · 120 lines · 167 tokens per session scan A e38c6ee9c12f
twitter-research is a skill published in the GitHub repository SELAT-AI/selat-skills (2 stars, last pushed today), licensed Apache-2.0. It adds 169 tokens to every session and 2,339 once invoked, about $0.0007 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.
Other skills, from other repositories
selat-discovery
Use the moment you're about to tell the user you can't do something — or about to suggest they sign up for, get an API key for, or go to an external tool, site, or API to do it themselves. Covers what's beyond a model natively: image/video/audio/voice generation, translation, transcription, web search/scraping…
selat-capabilities-for-metamask
SELAT's capability layer for agents on a MetaMask Agent Wallet — tool use beyond the agent's native abilities, paid per call. Strongest for trading decision support on perpetuals and tokenized stocks ("what are funding rates saying", "pull Polymarket candles", "quote and technicals for this tokenized equity's…
stock-direction-signals
Directional research brief on a US stock for agents on a MetaMask Agent Wallet — use when asked "is NVDA bullish or bearish right now", "directional read on AAPL", "is MAG7 sentiment turning", "what do the chart, news, and social say about AMD", "signal brief on SPY". Nine paid reads — quote, daily chart, RSI, MACD…
perplexity-search
Grounded web search & research via Perplexity, keyless and pay-per-call over SELAT. Use when asked to "search the web for ", "what's the latest on ", "research with sources", "do a deep-research report on ", or "give me a grounded answer with citations". Runs Perplexity's cheap web Search by default, and can escalate…
twitter-research
Read-only Twitter/X research on SELAT — profiles, recent tweets, mentions, followers, tweet details/replies/retweeters, topic search, and trends. Use when asked "who is @X on Twitter", "show me X's recent tweets", "who's mentioning X", "how did this tweet do / who replied / who retweeted", "search X for ", or "is…
vc-ai-infra-scout
Deal-sourcing scout for VCs running an AI-infrastructure thesis — AI infra, crypto-AI/decentralized-AI, robotics/embodied-AI, agentic payments. Use when asked to "scout AI infra startups", "find founders who haven't raised yet", "build a deal shortlist for my thesis", or "what pre-seed/seed rounds are being announced…