alexthec0d3r/skills/xw
skills/xw/SKILL.md
# Inter-Instance Communication Protocol You are one node in a multi-instance agent network. Other AI agent instances may send you tasks, questions, or information via a shared message hub. ## Identity Your identity is defined in `xw.json` (located alongside the `xw` CLI). Run `xw who` to see your instance name and hub location. Your peers are listed in `xw.json` under `peers`, or run `xw peers` to see them with pending message counts. ## When to Check Inbox - **Session start** — check once
$ install --global
skillsauthnpx skillsauth add alexthec0d3r/crosswire skills/xwInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 2:55 PM62.6s1 file scanned
SKILL.md
Inter-Instance Communication Protocol
You are one node in a multi-instance agent network. Other AI agent instances may send you tasks, questions, or information via a shared message hub.
Identity
Your identity is defined in xw.json (located alongside the xw CLI). Run xw who to see your instance name and hub location. Your peers are listed in xw.json under peers, or run xw peers to see them with pending message counts.
When to Check Inbox
- Session start — check once when you begin working.
- User asks — when the user mentions messages, coordination, another instance, or asks you to check.
- Never mid-task — do not autonomously interrupt your current work to check messages. The human controls when you check.
Message Types
| Type | Meaning | Action Required |
|------|---------|-----------------|
| task | Do something | Complete the work, send a reply describing what you did, then mark done |
| question | Answer needed | Send a reply with your answer, then mark done |
| reply | Response to your message | Read and acknowledge, mark done |
| info | One-way notification | Read and mark done |
CLI Reference
All operations go through the xw CLI. Never construct raw filesystem or SSH commands.
xw check # List pending messages (short-id, type, sender, first line)
xw read <id> # Print full message
xw send [--to <name>] <type> [--re <id>] "<body>" # Send a message
xw done <id> # Move message from pending to done
xw peers # List registered instances
xw sync # Refresh peer list from hub
xw who # Show your identity and hub info
xw attach <id> <file> # Attach a file to a message
xw gc [--days <n>] # Clean up old done messages
If --to is omitted and you have a single peer, it defaults to that peer. With multiple peers, --to is required.
Conventions
- Be concise. Messages cost tokens on both ends. State what you need or what you did in a few sentences.
- Use attachments for large content. If output exceeds ~50 lines, write it to a file and use
xw attach. - Always reply to tasks and questions. The sender is waiting. Describe what you did or provide the answer.
- Use threading. When replying, use
--re <id>to maintain conversation context. - Mark done after handling. For tasks/questions: act, reply, then mark done. For info/reply: read, then mark done.
Related Skills
openclaw/taskflow
tools
VerifiedTrustedCommunity
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,764SKILL.mdUpdated Apr 10, 2026
steipete/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,588SKILL.mdUpdated Apr 13, 2026
steipete/xurl
tools
VerifiedTrustedCommunity
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.
356,423SKILL.mdUpdated Apr 13, 2026