/docs/commands

Slash commands.

All 45 Rugproof commands, generated from source.

Which command?

I want to…
├─ audit my whole repo ............... /audit            (deep: /audit-deep, paranoid: /audit-strict)
├─ quick pre-commit check ............ /quick-scan
├─ audit a deployed contract ......... /audit-live <chain> <addr>
├─ audit only my git changes ......... /audit-changes
├─ check dependency versions ......... /audit-deps
├─ compare a contract across chains .. /audit-multi-chain <addr> <chains>
├─ know if a token can rug me ........ /rug-check
├─ prove a property formally ......... /prover
├─ turn a finding into a PoC ......... /exploit <id>   (live: /exploit-live)
├─ generate a patch .................. /remediate <id>
├─ produce a shareable report ........ /report   (card only: /card)
└─ pre-launch go/no-go ............... /pre-deploy

All commands

CommandArgumentsWhat it does
/audit[file-or-dir] (omit to audit entire repo per .rugproof.yml)Full security audit of a Solidity/Vyper/Rust contract or directory. Runs the entire vuln-skills library and dispatches DeFi specialist subagents based on detected protocol type.
/audit-changes[base-branch] (default: main)Audit only the git diff vs main (or specified base). Optimized for PR review.
/audit-deep[file-or-dir]Deep audit — same as /audit but spawns more parallel subagents, runs multi-pass review, and chases exploit chains across files.
/audit-deps[file-or-dir]Audit third-party dependencies — resolve installed versions, cross-reference known-vulnerable releases, and flag vendored code that has diverged from upstream.
/audit-diff<old-report.json> <new-report.json>Diff two Rugproof audit reports (before vs after) to track regressions — what's new, what's fixed, and whether the grade moved.
/audit-history<address-or-protocol-name>Pull past public audits (Code4rena, Sherlock, Spearbit, etc.) for a deployed contract or known protocol.
/audit-live<address> [--chain ethereum] [--block latest]Audit a deployed contract on a live chain. Pulls verified source from the block explorer, optionally forks the chain for live-state simulation.
/audit-multi-chain<address> <chain1,chain2,...>Diff the on-chain configuration of one contract deployed across multiple chains — owner, oracle, fees, timelock, pause state, proxy impl — and flag the chain that drifted.
/audit-strict[file-or-dir]Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.
/bounty<finding-id> [--target immunefi|protocol|seal911]Generate a responsible-disclosure bounty submission from a confirmed finding — Immunefi / protocol bounty / SEAL 911 formats.
/bounty-submit<finding-id> [--platform immunefi|cantina|protocol]Submit a finding to a bug-bounty platform (Immunefi, Cantina) automatically.
/card[--out <path>] [--style classic|bear|hacker|minimal]Generate a shareable PNG audit card from the latest /audit. Optimized for social media.
/coverageRun forge coverage, identify untested branches, generate tests to close gaps.
/demo[reentrancy|oracle|flash-loan|inflation|replay|vyper|all]Run Rugproof against the bundled vulnerable example contracts — first-run "wow moment".
/diff-audit<file> --reference <openzeppelin|solady|uniswap-v3|...>Diff the contract against a canonical reference implementation (OZ, Solady, Uniswap V3, etc.) and flag suspicious deltas.
/dismiss<finding-id> <reason>Mark a finding as a false positive (or accepted risk). Future audits won't re-report it.
/explain<finding-id> [--audience=beginner|engineer|exec]Explain a finding in plain English, with examples. Optionally tailored to a beginner audience.
/exploit<finding-id> [--framework foundry|hardhat] [--story]Generate a working Foundry PoC that exploits a specific finding. Compiles and passes.
/exploit-chain<finding-id-1> <finding-id-2> [...]Chain multiple findings into a single multi-step exploit. Produces a Foundry test that proves the chain works.
/exploit-live<chain> <address> <finding-id>Generate an exploit against a *deployed* contract on a fork. Validates the exploit works on live state.
/fuzz<Contract.function>Generate property-based fuzz tests for a specific function.
/gas<file-or-contract>Gas profile — find expensive operations and suggest optimizations with before/after numbers.
/invariant<contract-or-file>Generate Foundry invariant tests for property-based fuzzing. The high-value command for serious teams.
/mint-cert[--chain berachain] [--ipfs-pin]Mint a soulbound Audit Certificate NFT on Berachain (or other supported chain) for a completed audit.
/monitor[address] [--chain ethereum]Set up post-deployment monitoring — recommend which on-chain events to alert on and scan recent activity for high-severity changes.
/mythril[file]Run Mythril (symbolic execution) and have Claude triage its findings — turn symbolic counter-examples into Foundry PoCs.
/notify-discord[--webhook-url <url>] [--severity-filter critical|high|medium]Post the latest /audit results to a Discord channel via webhook.
/notify-slack[--webhook-url <url>] [--severity-filter critical|high|medium]Post the latest /audit results to a Slack channel via incoming webhook.
/pre-deploy[dir]Interactive pre-launch security checklist — walk the operational and code-safety gates and produce a final GO / NO-GO with each item PASS / FAIL / N-A.
/prover[contract] [property]Formal verification entrypoint — prove a property holds for all inputs with Halmos (symbolic, offline) or Certora (CVL) using ready-made property templates.
/quick-scan[file-or-dir]Fast pre-commit-grade scan. Only catches Critical and High. Optimized for hooks.
/remediate<finding-id>... [--apply]Generate code patches that fix one or more findings. Outputs as a unified diff and (optionally) applies it.
/replay-incident<chain> <tx-hash>Replay a historical exploit tx (by tx hash) on a fork. Explains step-by-step what the attacker did.
/report[--format markdown|html|pdf|json|png|all] [--out <dir>]Render the latest audit as a deliverable report in Markdown / HTML / PDF / JSON / PNG.
/rug-check[file-or-address] [--chain <c>]Fast owner-power / rugability scan — score how much unilateral control the deployer holds and return a 0-100 rug-risk verdict.
/rugproof-init60-second onboarding — set up .rugproof.yml, choose severity profile, configure hooks, pick supported chains.
/score[file-or-dir]Compute a Rugproof grade (A+ → F) for the contract or repo based on findings from /audit.
/simulate<chain> [<address>] [--block latest]Multi-actor, multi-block simulation against a live fork. Stateful attack sequences across many txs.
/slither[file-or-dir]Run Slither and have Claude triage its findings — separate true positives from false positives, write PoCs for real bugs.
/symbolic<contract-or-function>Symbolic execution via Halmos. For paths that fuzzing cannot reach.
/test-gen<file-or-function>Generate a Foundry test suite — happy path + edge cases + adversarial tests — for a contract or function.
/tweet[--auto] [--include-card] [--text \"custom prefix\"]Compose a tweet from the latest audit. Either auto-posts (if Twitter API creds set) or generates a one-click intent URL.
/upgrade-safety<old-impl-path-or-address> <new-impl-path-or-address>Check storage compatibility, initializer changes, and admin-function deltas between two implementations of an upgradeable contract.
/verify-deploy<chain> <address>Verify deployed bytecode matches the source you have, with correct constructor args.
/verify-finding<finding-id>Second-opinion mode — re-check a specific finding with deeper analysis. Triages true vs false positives.