subagent-driven-development
What this skill does
A development methodology that uses subagents to implement and review tasks in a structured, isolated manner. It focuses on task isolation, quality assurance, and efficient iteration.
github/jnmetacode - System Command Execution - 7.6k stars
Threat analysis
Skill info
pkg:github/jnMetaCode/superpowers-zh@441d024?skill=subagent-driven-developmentAssessments (1)
System Command Execution
System Command Execution via local-llm-review
scripts/review-package
The script uses 'git clean -fdx' which can recursively delete all files in the current directory, potentially leading to data loss if executed without proper safeguards.Badge
Add the Anomity scan badge for subagent-driven-development to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of subagent-driven-development? Report an issue or request a rescan.
