audit-changes
CommandAudit only the git diff vs main (or specified base). Optimized for PR review.
Verify deployed bytecode matches the source you have, with correct constructor args.
> /plugin marketplace add omermaksutii/RugProof> /plugin install rugproof@rugproof
description: Verify deployed bytecode matches the source you have, with correct constructor args. argument-hint: "<chain> <address>" allowed-tools: Read, Bash, Agent, mcp__block-explorer__*, mcp__forge-runner__*
Compare deployed bytecode at `<chain>:<address>` with the local source + constructor args.
mcp__block-explorer__get_runtime_code(chain=<chain>, address=<addr>)
mcp__forge-runner__build()
Pull the runtime bytecode for the matching contract.
Solidity appends a CBOR metadata blob at the end of the runtime bytecode containing the IPFS / Swarm hash of the source. Strip it for comparison:
Detect: bytecode ends with `0x...a26469706673...` (CBOR) Length: last 53 bytes
Byte-wise compare the stripped runtime code.
mcp__block-explorer__get_constructor_args(chain=<chain>, address=<addr>)
Compare with the expected args from your deploy script.
Three cases:
**Match:**
✓ Deployed bytecode matches local source. Constructor args: match. Metadata hash: QmXabc... (matches IPFS-pinned source)
**Mismatch:**
✗ Bytecode mismatch. Local compiled: 32K bytes Deployed runtime: 31.8K bytes Diff: 5 byte regions differ (likely compiler settings) Likely cause: optimizer runs (200 vs 999999), Solidity version, library linking.
**Metadata-only difference:**
⚠ Runtime bytecode matches; metadata hash differs. This is normal if the local source is at a different commit than the deployment. Consider this a soft match.
Rugproof your code before someone else does. 🌐 Live site: omermaksutii.github.io/RugProof 📦 Latest: v1.0.0 — 45 commands · 23 agents · 45 skills · 13 MCP servers · tested, offline-first, with rule packs, a benchmark, non-EVM coverage, and post-deploy
Audit only the git diff vs main (or specified base). Optimized for PR review.
Deep audit — same as /audit but spawns more parallel subagents, runs multi-pass review, and chases exploit chains across files.
Audit third-party dependencies — resolve installed versions, cross-reference known-vulnerable releases, and flag vendored code…
Diff two Rugproof audit reports (before vs after) to track regressions — what's new, what's fixed, and whether the grade moved.
Pull past public audits (Code4rena, Sherlock, Spearbit, etc.) for a deployed contract or known protocol.
Audit a deployed contract on a live chain. Pulls verified source from the block explorer, optionally forks the chain for…
Audit a file, directory, or whole repo for insecure default configuration: fallback secrets, default credentials, fail-open…
Check text against AGT prompt-injection, context-poisoning, and MCP threat detectors.
Show which external bug-bounty tools are installed on this machine and print install hints for the missing ones. Curated from…