Run it in Claude Code once Auditor Skill is installed (plugin, script or the Solana AI Kit; see Auditor Skill):
No install: tell your agent
audit.md
Open .mdauditor-skill — Full Audit
Arguments: $ARGUMENTS
Run the auditor-skill end-to-end:
- Read
OUTPUT-RULES.md(mandatory output format, severity 1-10, the Rule 5b validation gate). - Follow
FULL-AUDIT.mdtop to bottom, honoring scope-gated loading (Rule 0): discover the repo, declare scope, load only in-scope checklists/vectors on demand. - Delegate: spawn
context-builder(Phase 0.5) first, thenvuln-hunterfor the item-by-item walk,economic-analystfor checklist 06 + economic vectors, andaudit-reporterto assemble the report. - Every in-scope checklist item and phase-triggered vector gets an explicit verdict (
[PASS]/[FAIL-N]/[PARTIAL]/[N/A]). Findings with N≥6 must pass the Rule 5b validation gate or be downgraded to[PARTIAL]/[UNCONFIRMED]. - Emit
audit_<n>/REPORT.md: executive summary (safe-to-deploy verdict), Scope Coverage table, findings, Phase 4.5 maturity scorecard, remediation roadmap.
If the bundled Trail of Bits tooling is present (test -d "${CLAUDE_PLUGIN_ROOT}/vendor/trailofbits/plugins" — the installation’s copy, never a relative vendor/ path, which would resolve inside the audited repo), use it for SAST / harnesses / coverage per references/orchestration/boundary-map.md; otherwise fall back to the native discovery/grep-commands.md scanners and note the tooling gap.
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