mherod/swiz-continue
plugins/swiz-core/skills/swiz-continue/SKILL.md
Run swiz continue to resume the agent's self-directed loop. Picks up the next task from the backlog or generates a new one based on ambition mode. Use when resuming autonomous work, continuing after a pause, or triggering the next iteration of the agent loop.
$ install --global
skillsauthnpx skillsauth add mherod/swiz swiz-continueInstall 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: May 18, 2026, 5:51 AM161.9s1 file scanned
SKILL.md
- name:
- swiz-continue
- description:
- Run swiz continue to resume the agent's self-directed loop. Picks up the next task from the backlog or generates a new one based on ambition mode. Use when resuming autonomous work, continuing after a pause, or triggering the next iteration of the agent loop.
- category:
- workflow
- allowed-tools:
- Bash
- argument-hint:
- [arguments]
Run the swiz continue command to resume or advance the self-directed agent loop.
Usage
/swiz-continue— resume the default continue flow/swiz-continue --pick-issue— pick a specific issue to work on next
Step 1: Run the Command
If $ARGUMENTS is empty: Run swiz continue.
If $ARGUMENTS is present: Run swiz continue $ARGUMENTS.
Step 2: Report Results
Summarize key output: what task was selected, what the agent will work on next, and report any errors clearly.
Failure Handling
If continue fails: Report the error and suggest checking swiz status for the current agent state.
If no tasks available: Report that the backlog is empty and suggest using swiz idea to generate new work items.
Related Skills
mherod/plugins/swiz-core/skills/swiz-task-governance
tools
VerifiedTrustedCommunity
Understand and comply with swiz task governance enforcement
3SKILL.mdUpdated May 22, 2026
mherod/swiz-configure
data-ai
VerifiedTrustedCommunity
Configure swiz settings with presets or individual changes. Supports workflow presets (backlog, creative, quiet), collaboration modes (solo, team), and safety presets (lockdown, relaxed). Use when changing agent behavior, switching workflow modes, or adjusting safety gates.
3SKILL.mdUpdated Apr 19, 2026
mherod/swiz-cleanup
tools
VerifiedTrustedCommunity
Run swiz cleanup to remove stale hook configurations, orphaned dispatch entries, and temporary files. Use when hooks are out of sync, after uninstalling plugins, or when swiz state needs a reset.
3SKILL.mdUpdated Apr 19, 2026
mherod/enable-auto-continue
testing
VerifiedTrustedCommunity
Enable swiz auto-continue globally or for a specific session. Allows the agent to automatically continue working after task completion. Use when starting autonomous workflows, enabling backlog processing, or scoping auto-continue to a specific session.
3SKILL.mdUpdated Apr 19, 2026