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/resciencelab/opc-skills/twitternpx skills add ReScienceLab/opc-skills --skill twittergit clone --depth 1 https://github.com/ReScienceLab/opc-skillsWhat 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 | $0.00042 | $0.00760 |
| Opus 5 | $0.00021 | $0.00380 |
| Sonnet 5 | $0.00008 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
twitter 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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twitter/X Skill
Get user profiles, tweets, replies, followers/following, communities, spaces, and trends from Twitter/X via twitterapi.io.
Prerequisites
Set API key in ~/.zshrc:
export TWITTERAPI_API_KEY="your_api_key"
Quick Check:
cd <skill_directory>
python3 scripts/get_user_info.py elonmusk
Commands
All commands run from the skill directory.
User Endpoints
python3 scripts/get_user_info.py USERNAME
python3 scripts/get_user_about.py USERNAME
python3 scripts/batch_get_users.py USER_ID1,USER_ID2
python3 scripts/get_user_tweets.py USERNAME --limit 20
python3 scripts/get_user_mentions.py USERNAME --limit 20
python3 scripts/get_followers.py USERNAME --limit 100
python3 scripts/get_following.py USERNAME --limit 100
python3 scripts/get_verified_followers.py USERNAME --limit 20
python3 scripts/check_relationship.py USER1 USER2
python3 scripts/search_users.py "query" --limit 20
Tweet Endpoints
python3 scripts/get_tweet.py TWEET_ID [TWEET_ID2...]
python3 scripts/search_tweets.py "query" --type Latest --limit 20
python3 scripts/get_tweet_replies.py TWEET_ID --limit 20
python3 scripts/get_tweet_quotes.py TWEET_ID --limit 20
python3 scripts/get_tweet_retweeters.py TWEET_ID --limit 50
python3 scripts/get_tweet_thread.py TWEET_ID
python3 scripts/get_article.py TWEET_ID
List Endpoints
python3 scripts/get_list_followers.py LIST_ID --limit 20
python3 scripts/get_list_members.py LIST_ID --limit 20
Community Endpoints
python3 scripts/get_community.py COMMUNITY_ID
python3 scripts/get_community_members.py COMMUNITY_ID --limit 20
python3 scripts/get_community_moderators.py COMMUNITY_ID
python3 scripts/get_community_tweets.py COMMUNITY_ID --limit 20
python3 scripts/search_community_tweets.py "query" --limit 20
Other Endpoints
python3 scripts/get_space.py SPACE_ID
python3 scripts/get_trends.py --woeid 1 # Worldwide
Search Query Syntax
# Basic search
python3 scripts/search_tweets.py "AI agent"
# From specific user
python3 scripts/search_tweets.py "from:elonmusk"
# Date range
python3 scripts/search_tweets.py "AI since:2024-01-01 until:2024-12-31"
# Exclude retweets
python3 scripts/search_tweets.py "AI -filter:retweets"
# With media
python3 scripts/search_tweets.py "AI filter:media"
# Minimum engagement
python3 scripts/search_tweets.py "AI min_faves:1000"
What ships with it
29 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.
- .claude-plugin/plugin.json 547 B
- scripts/batch_get_users.py 632 B runs code
- scripts/check_relationship.py 856 B runs code
- scripts/credential.py 364 B runs code
- scripts/get_article.py 992 B runs code
- scripts/get_community_members.py 889 B runs code
- scripts/get_community_moderators.py 798 B runs code
- scripts/get_community_tweets.py 855 B runs code
- scripts/get_community.py 962 B runs code
- scripts/get_followers.py 958 B runs code
- scripts/get_following.py 960 B runs code
- scripts/get_list_followers.py 849 B runs code
- scripts/get_list_members.py 835 B runs code
- scripts/get_space.py 1.0 KB runs code
- scripts/get_trends.py 1.5 KB runs code
- scripts/get_tweet_quotes.py 843 B runs code
- scripts/get_tweet_replies.py 850 B runs code
- scripts/get_tweet_retweeters.py 877 B runs code
- scripts/get_tweet_thread.py 760 B runs code
- scripts/get_tweet.py 652 B runs code
- scripts/get_user_about.py 1.3 KB runs code
- scripts/get_user_info.py 541 B runs code
- scripts/get_user_mentions.py 855 B runs code
- scripts/get_user_tweets.py 1.0 KB runs code
- scripts/get_verified_followers.py 1.1 KB runs code
- scripts/search_community_tweets.py 882 B runs code
- scripts/search_tweets.py 1.0 KB runs code
- scripts/search_users.py 810 B runs code
- scripts/twitter_api.py 4.7 KB runs code
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.
- yesterday First seen · 100 lines · 42 tokens per session scan A aee0659da20b
twitter is a skill published in the GitHub repository ReScienceLab/opc-skills (1,710 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42 tokens to every session and 760 once invoked, about $0.0002 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
context-okf-llm-ingest
Use when extracting a codebase's implementation decisions into Metatron with an LLM/agent instead of metatron ingest — authoring candidate decisions as Open Knowledge Format (OKF) markdown files locally for review.
context-okf-promote-candidates
Use when promoting reviewed Metatron candidate decisions to canonical in a git/CI flow — moving Open Knowledge Format (OKF) files from candidate/ to decisions/. The agent performs only human-named moves; it never decides what to promote.
live-audit
Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…
live-audit
Repo-specific playbook, for any agent/model working on this repo (not tied to a particular harness — see AGENTS.md's own framing). Use it when asked to test/audit/smoke-test the published tmdb-mcp package, hunt for bugs or edge cases, or repeat "the same kind of testing as before.".
prompt-check
Live-test every MCP Prompt in src/tools/prompts.ts through the real MCP protocol (not a static read) across every argument combination. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.
prompt-check
Live-test every MCP Prompt in src/prompts.ts through the real MCP protocol (not a static read) across every argument combination, including every enum value. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.