Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From crucible
Run the Final Oracle evidence audit independently against the current evidence/ tree. Convenes 3 Oracle auditors, computes quorum, writes decision.md. Idempotent — safe to re-run. PRD §1.16.2 CMD-3.
How this command is triggered — by the user, by Claude, or both
Slash command
/crucible:auditThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# /crucible:audit Standalone runner for the Final Oracle evidence audit per PRD §1.13.8 (FR-ORACLE-1..4) and §3.13. Re-runnable against any well-formed `evidence/` tree. ## Pipeline 1. Verify `evidence/reviewer-consensus/decision.md` exists with PASS verdict (per §3.11) 2. Spawn 3 Oracle auditor subagents in parallel via Task tool: - `agents/oracle-auditor-1.md` — Completeness + Citation - `agents/oracle-auditor-2.md` — Structural Integrity - `agents/oracle-auditor-3.md` — Adversarial Skepticism 3. Each Oracle writes its raw verdict to `evidence/final-oracle-evidence-audit/oracl...
Standalone runner for the Final Oracle evidence audit per PRD §1.13.8 (FR-ORACLE-1..4) and §3.13. Re-runnable against any well-formed evidence/ tree.
evidence/reviewer-consensus/decision.md exists with PASS verdict (per §3.11)agents/oracle-auditor-1.md — Completeness + Citationagents/oracle-auditor-2.md — Structural Integrityagents/oracle-auditor-3.md — Adversarial Skepticismevidence/final-oracle-evidence-audit/oracle-N.mddecision.mdblockers/<oracle-id>-<msc>-<timestamp>.mdRe-running this command does NOT overwrite prior verdicts; new runs are appended with timestamps.
PRD §1.26 OQ-3: "Should /crucible:audit be runnable independently of execution mode?" — RESOLVED in v0.2: yes.
npx claudepluginhub krzemienski/crucible --plugin crucible/auditLogs and labels agent interactions as append-only JSONL entries. Supports recording prompts, responses, tool calls, and attaching labels with reasons.
/auditPerforms a security audit of the codebase covering dependency vulnerabilities, secrets scanning, OWASP Top 10, input validation, and auth. Produces a severity-ranked findings report with actionable fixes.
/auditRuns heavy-weight security and safety audits on Rust projects via os-checker tools. Supports security, safety, concurrency, and full audit modes. Checks for CVEs, unsafe code, undefined behavior, and concurrency bugs.
/auditAnalyzes iOS project structure and launches targeted audits for code quality, performance, security, and architecture. Accepts optional area argument to run a specific audit.
/auditScans a codebase for security vulnerabilities across dependencies, auth, input validation, data exposure, configs, and secrets. Produces prioritized findings with remediation steps.