jamesaphoenix/tx-cycle
apps/cli/src/templates/claude/skills/tx-cycle/SKILL.md
Run a tx cycle scan — sub-agent swarm for automated codebase issue discovery. Use when the user mentions "cycle", "scan", or "find issues".
$ install --global
skillsauthnpx skillsauth add jamesaphoenix/tx tx-cycleInstall 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 17, 2026, 2:17 AM20.8s1 file scanned
SKILL.md
- name:
- tx-cycle
- description:
- Run a tx cycle scan — sub-agent swarm for automated codebase issue discovery. Use when the user mentions "cycle", "scan", or "find issues".
- disable-model-invocation:
- true
tx cycle — Sub-Agent Swarm Issue Discovery
Before running tx cycle, ask the user these questions to build the right command:
Required
- Task prompt (
--task-prompt): What area of the codebase should agents review?- Examples: "Review core services", "Audit API endpoints", "Check error handling"
Optional (with defaults)
-
Scan prompt (
--scan-prompt): What should agents look for?- Default: "Find bugs, anti-patterns, missing error handling, weak EARS requirement coverage, integration-test gaps in critical flows, OTEL non-blocking risks, and performance/infra issues."
-
Number of agents (
--agents N): How many parallel scan agents per round?- Default: 3
-
Fix mode (
--fix): Should a fix agent run between scan rounds?- Default: off (scan-only)
-
Dry run (
--dry-run): Report findings without writing to the database?
Building the Command
Once you have the user's answers, construct and run:
tx cycle \
--task-prompt "User's task prompt" \
--scan-prompt "User's scan prompt" \
--agents 3
Add --fix for auto-fixing. Add --dry-run for a dry run.
How It Works
- Scan: N parallel agents scan the codebase based on the prompts
- Dedup: Findings are deduplicated against existing tx tasks
- Convergence: When no new significant findings appear, the cycle stops
- Fix (optional): A fix agent addresses issues between rounds
- New issues are created as tx tasks in the normal
tx readyworkflow
Important
- This is a sub-agent swarm, NOT a Claude Code team
- Do NOT use TeamCreate, SendMessage, or any built-in team tools
- The cycle command spawns its own agents internally
- Results feed back into the normal
tx readyworkflow
Related Skills
jamesaphoenix/verify-invariants
development
VerifiedTrustedCommunity
Implement and verify design doc invariants by annotating tests and source code with [INV-*] / @spec tags, then driving tx spec coverage from BUILD toward HARDEN (100% FCI). Works with any design doc that has an invariants block.
2SKILL.mdUpdated Apr 17, 2026
jamesaphoenix/task-spec-loop
data-ai
VerifiedTrustedCommunity
Link tasks to paired PRD/design specs, export all open work to markdown, and keep Ralph-style loops moving by creating tasks, subtasks, and dependency updates through tx primitives.
2SKILL.mdUpdated Apr 17, 2026
jamesaphoenix/skills-sync
development
VerifiedTrustedCommunity
Refresh bundled tx Claude Code and Codex skills in a project from the canonical tx source without manual copy and paste.
2SKILL.mdUpdated Apr 17, 2026
jamesaphoenix/ralph-loop
development
VerifiedTrustedCommunity
Run Ralph against either the full repo queue or tasks linked to one design doc, with injected task/spec/queue context for Codex or Claude runtimes.
2SKILL.mdUpdated Apr 17, 2026