Run it in Claude Code once Auditor Skill is installed (plugin, script or the Solana AI Kit; see Auditor Skill):
/auditor:quick-scan
No install: tell your agent
Read https://kit.superteam.codes/s/auditor-skill/commands/quick-scan.md and follow it for this task:
quick-scan.md
Open .mdauditor-skill — Quick Scan
Arguments: $ARGUMENTS
- Discover the repo and declare scope (
OUTPUT-RULES.mdRule 0). - If the bundled Trail of Bits plugins are present (
test -d "${CLAUDE_PLUGIN_ROOT}/vendor/trailofbits/plugins"), runstatic-analysis(SAST) over in-scope languages; otherwise run thediscovery/grep-commands.mdscanners. Any analyzer that builds the target runs in the execution mode recorded at intake (OUTPUT-RULES.mdRule 11a). - Evaluate only CRITICAL / HIGH known-vectors for the detected domains — not the full set.
- Report findings with severity +
file:line. State clearly this is a triage pass, not a complete audit, and point to/auditor:auditfor full coverage. - As a CI gate on a public repository (
OUTPUT-RULES.mdRule 11d): post pass/fail only — no finding counts, total or per severity — in PR comments, check annotations, the job log and uploaded artifacts alike, since anyone signed in to GitHub can read all of them. Send finding details through a private channel (private vulnerability reporting, a draft security advisory, or a private repository). If that channel is unavailable, fail the job; never fall back to printing findings in the log.
One install for the whole kit
Superteam Brasil builds these skills as part of the Solana AI Kit, its open-source Claude Code and Codex kit for Solana. 15 specialist agents, 32 commands, 4 MCP servers and 46 skill packs, behind a firewall that keeps agents away from wallet keypairs.
- Specialist agents
- 15
- Commands
- 32
- Skill packs
- 46
- MCP servers
- 4
$ curl -fsSL https://aikit.superteam.codes | bash