Moltis is a persistent personal agent server written in Rust that runs on hardware controlled by its user. It provides an AI agent with sandboxed command execution, model-provider connections, memory, voice, scheduling, messaging integrations, browser automation, and MCP tools. Its catalogue add-ons extend the agent’s workflows and available tools.
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 moltis-org/moltis --skill birdclawgit clone --depth 1 https://github.com/moltis-org/moltisWrote 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/moltis-org/moltis/birdclaw)<a href="https://agentmods.dev/skills/moltis-org/moltis/birdclaw"><img src="https://agentmods.dev/badge/skills/moltis-org/moltis/birdclaw/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/moltis-org/moltis/birdclaw"><img src="https://agentmods.dev/badge/skills/moltis-org/moltis/birdclaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01000 |
| Opus 5.5 | $0.00017 | $0.00400 |
| Sonnet 5.5 | $0.00008 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
birdclaw 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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
birdclaw — Twitter/X Local Workspace
birdclaw is a local-first Twitter workspace that archives, manages, and triages Twitter data (tweets, DMs, likes, bookmarks, mentions) in a self-hosted SQLite database. Includes a web UI for triage.
This complements the xurl skill — xurl is for interacting with the X API (posting, searching, engaging); birdclaw is for archiving and triaging your Twitter data locally.
Secret Safety (MANDATORY)
- birdclaw delegates API access to
xurlwhen configured — same secret safety rules apply. - Never read, print, or send
~/.birdclaw/config.jsonor~/.xurlto LLM context. - Never ask the user to paste API credentials into chat.
- Optional OpenAI API key for inbox AI scoring — set via
OPENAI_API_KEYenv var or Moltis credential store.
One-Time User Setup
birdclaw works in multiple modes:
- Local-only (no auth): Import Twitter archive ZIPs, search local data
- With xurl (recommended): Full API access for syncing timeline, mentions, DMs
- With bird CLI (cookie-based): Read-only access via browser cookies
For full API access, set up xurl first (see the xurl skill), then:
birdclaw setup
birdclaw doctor
Health Check
birdclaw doctor
Import Twitter Archive
birdclaw import /path/to/twitter-archive.zip
Sync via API
birdclaw sync # Sync all (timeline, mentions, DMs, likes, bookmarks)
birdclaw sync --timeline # Just timeline
birdclaw sync --mentions # Just mentions
birdclaw sync --dms # Just DMs
birdclaw sync --likes # Just likes
birdclaw sync --bookmarks # Just bookmarks
Search
birdclaw search "query"
birdclaw search "query" --limit 20 --json
birdclaw search "query" --from @handle
birdclaw search "query" --after 2026-01-01
Triage (CLI)
birdclaw inbox # Show untriaged items
birdclaw inbox --json
birdclaw inbox score # Run AI scoring on inbox items
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.
- 1mo ago First seen · 131 lines · 42 tokens per session scan A b27a6c42ed28
birdclaw is a skill published in the GitHub repository moltis-org/moltis (2,904 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,000 once invoked, about $0.0002 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.
Other skills, from other repositories
schedule-meeting
Schedule, book or set up a meeting, call, coffee, lunch, dinner, event or appointment on my calendar.
weekly-brief
Weekly or daily brief: what's on my week or my day, what to focus on, catch me up, morning briefing, day look-ahead.
telegram-userbot
A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.
watch
A monitoring and briefing workflow that checks unread Telegram messages, email, failed checks, and failed scheduled units, then decides what needs the owner's attention. It can also explain actions such as creating a task, delaying a reminder, ignoring an item, or fixing a failure.
insight
A scheduled daily practice that looks for a repeated manual task, builds and tests a small tool for it, and suggests the result. It can instead report a development issue when the agent cannot solve its own problem.
brief
Brief — the owner's day in review: tasks, calendar, mail, Telegram, every Connection and plugin, goals from CORE, weather. Load in a scheduled Brief turn (08:30 and 14:00 by default), on /digest, and when the owner asks for a day plan, a review of the day or their open tasks.