install — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited install (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Sets up dragoon across every supported coding agent on the machine.
# default install (auto-detects all hosts)
./setup
# specific hosts
./setup --hosts claude-code,cursor
# dry run (see what would happen)
./setup --dry-run
# uninstall
./setup --uninstall
# list supported hosts
./setup --list-hosts~/.dragoon/~/.dragoon into the host's skills directory:~/.claude/skills/dragoon~/.codex/skills/dragoon~/.cursor/skills/dragoon~/.opencode/skills/dragoon~/.factory/skills/dragoon~/.kiro/skills/dragoonThat's it. Zero npm dependencies. No registry account needed.
Re-run ./setup from the latest source. The script does an idempotent rsync.
./setup --uninstallRemoves the dragoon symlink/copy from every host that has it. Leaves ~/.dragoon/ source untouched (delete it manually if desired).
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.