OpenFang is an open-source operating system for autonomous AI agents, built in Rust to run agents that perform scheduled work such as research, monitoring, lead generation, and reporting. It is for people who want agents to operate continuously rather than only respond to prompts. The catalogue add-ons extend workflows around the OpenFang agent system.
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/rightnow-ai/openfang/twitternpx skills add RightNow-AI/openfang --skill twittergit clone --depth 1 https://github.com/RightNow-AI/openfangWrote 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/rightnow-ai/openfang/twitter)<a href="https://agentmods.dev/skills/rightnow-ai/openfang/twitter"><img src="https://agentmods.dev/badge/skills/rightnow-ai/openfang/twitter.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 | $0.00030 | $0.03259 |
| Opus 5 | $0.00015 | $0.01630 |
| Sonnet 5 | $0.00006 | $0.00652 |
| Haiku 4.5 | $0.00003 | $0.00326 |
Grade A, and why
twitter-hand-skill scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twitter/X Management Expert Knowledge
Twitter API v2 Reference
Authentication
Twitter API v2 uses OAuth 2.0 Bearer Token for app-level access and OAuth 1.0a for user-level actions.
Bearer Token (read-only access + tweet creation):
Authorization: Bearer $TWITTER_BEARER_TOKEN
Environment variable: TWITTER_BEARER_TOKEN
Core Endpoints
Get authenticated user info:
curl -s -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
"https://api.twitter.com/2/users/me"
Response: {"data": {"id": "123", "name": "User", "username": "user"}}
Post a tweet:
curl -s -X POST "https://api.twitter.com/2/tweets" \
-H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
-H "Content-Type: application/json" \
-d '{"text": "Hello world!"}'
Response: {"data": {"id": "tweet_id", "text": "Hello world!"}}
Post a reply:
curl -s -X POST "https://api.twitter.com/2/tweets" \
-H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
-H "Content-Type: application/json" \
-d '{"text": "Great point!", "reply": {"in_reply_to_tweet_id": "PARENT_TWEET_ID"}}'
Post a thread (chain of replies to yourself):
- Post first tweet → get
tweet_id - Post second tweet with
reply.in_reply_to_tweet_id= first tweet_id - Repeat for each tweet in thread
Delete a tweet:
curl -s -X DELETE "https://api.twitter.com/2/tweets/TWEET_ID" \
-H "Authorization: Bearer $TWITTER_BEARER_TOKEN"
Like a tweet:
curl -s -X POST "https://api.twitter.com/2/users/USER_ID/likes" \
-H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
-H "Content-Type: application/json" \
-d '{"tweet_id": "TARGET_TWEET_ID"}'
Get mentions:
curl -s -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
"https://api.twitter.com/2/users/USER_ID/mentions?max_results=10&tweet.fields=public_metrics,created_at,author_id"
Search recent tweets:
curl -s -H "Authorization: Bearer $TWITTER_BEARER_TOKEN" \
"https://api.twitter.com/2/tweets/search/recent?query=QUERY&max_results=10&tweet.fields=public_metrics"
What ships with it
1 file 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.
- 5d ago First seen · 362 lines · 30 tokens per session scan A b6cbc97e8336
twitter-hand-skill is a skill published in the GitHub repository RightNow-AI/openfang (18,166 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 3,259 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
testing-skill
Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.
channels-setup
Use when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams — "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding…