cubetiq/loop
workflows/workflows/agent-environment-setup/platforms/codex/generated-skills/loop/SKILL.md
Run a bounded autonomous iteration loop that keeps executing, verifying, and tightening scope until the task is done or blocked.
$ install --global
skillsauthnpx skillsauth add cubetiq/cubis-foundry loopInstall 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 4, 2026, 10:00 AM4.5s1 file scanned
SKILL.md
- name:
- loop
- description:
- Run a bounded autonomous iteration loop that keeps executing, verifying, and tightening scope until the task is done or blocked.
- license:
- MIT
- author:
- cubis-foundry
- route-kind:
- workflow
- route-id:
- loop
- platform:
- Codex
- command:
- /loop
- compatibility:
- Codex
Loop Workflow
What this workflow does
Keeps a bounded execution cycle moving through small units of work, verifying each iteration before deciding whether to continue.
When to use
Use this for contained tasks that benefit from repeated tighten-and-verify passes, not for open-ended product exploration.
Agent chain
orchestrator
Step details
- Define the finish line and iteration limit.
- Execute a small slice of work.
- Verify, adjust scope, and continue until done or blocked.
Skill routing
- Load only the skills needed for the current slice.
- Add the owning language or framework skill for code-level verification.
- Add
web-testing,android-emulator-testing, orios-simulator-testingwhen the loop needs runtime evidence.
Context notes
Provide the target outcome, hard stop conditions, and any constraints on time or scope.
Verification
Each loop must end with evidence. If progress stalls, the workflow should stop rather than hiding failure.
Output contract
LOOP_WORKFLOW_RESULT:
iterations: <count>
completed:
- <item>
evidence:
- <verification>
stopped_reason: <done | blocked | limit-reached>
Follow-up items
Typical next step: /review or user escalation
Related Skills
cubetiq/deep-research
tools
VerifiedTrustedCommunity
Use when investigating latest vendor behavior, comparing tools or platforms, verifying claims beyond the repo, or gathering external evidence before implementation.
1SKILL.mdUpdated Apr 4, 2026
cubetiq/database-design
documentation
VerifiedTrustedCommunity
Use when designing database schemas, normalization strategies, indexing plans, query optimization, and migration workflows for relational, document, or hybrid data stores.
1SKILL.mdUpdated Apr 4, 2026
cubetiq/csharp-best-practices
development
VerifiedTrustedCommunity
Use when writing, reviewing, or refactoring modern C#/.NET code, including minimal APIs, records, async streams, pattern matching, DI lifetimes, and memory-efficient performance tuning.
1SKILL.mdUpdated Apr 4, 2026
cubetiq/code-review
development
VerifiedTrustedCommunity
Use when conducting code reviews, building review checklists, calibrating review depth, providing structured feedback, or establishing team review practices. Covers review methodology, feedback patterns, automated checks, and batch review strategies.
1SKILL.mdUpdated Apr 4, 2026