12-lens engine-verified audit (loop + memory modes), x-ray-grade pre-audit recon, native and Echidna/Medusa stateful fuzzing, dependency-supply-chain review, key hygiene, and on-chain incident response for EVM · Solana · Move · Soroban. Findings map to CWE, SWC, OWASP Smart Contract Top 10 and DASP.
Plugin truent from marketplace truent in Emmyhack/Truent. Commands read from the repo's manifest — 3 days ago.
truent-auditEngine-first smart-contract security audit across EVM, Solana, Move and Soroban. Truent's compiled engine runs first (static detectors on every chain, a real revm invariant fuzzer on the EVM) and is the ground truth; twelve LLM attacker lenses then hunt the residual, and every property they state is
truent-depsSupply-chain security review of a smart-contract project's dependencies and CI. Finds forked/drifted libraries, unpinned submodules and package versions, and CI workflows that leak deploy keys — then runs Truent's engine over the dependency code that is actually compiled into your contracts, because
truent-fuzzStateful invariant fuzzing for smart contracts on EVM, Solana, Move and Soroban. Default path runs Truent's native revm-backed fuzzer — auto-detected invariants, user-written .invar properties, adversarial call sequences, and minimal-PoC shrinking in one binary, no external toolchain. On demand it g
truent-irOn-chain incident response for a live or past smart-contract exploit. Scopes the damage from the exploit transaction, reproduces the attack against the deployed bytecode with Truent's revm-backed fuzzer to identify the exact broken invariant, and separates confirmed mechanism from speculation before
truent-keysKey custody and deploy-safety review for a smart-contract project. Finds plaintext private keys in source, scripts, history and CI; then runs Truent's engine over the on-chain side of the same question — single-EOA admins, multisig thresholds too low to matter, unprotected initializers and upgrade p
truent-reconPre-audit reconnaissance for a smart-contract codebase, engine-verified. Produces a recon/ folder (recon.md readiness report with threat model, entry-point map, full invariant map, architecture diagram, git-history risk mining, test and doc gaps, verdict) and, unlike a report-only recon, feeds the s
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
hooks
Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
1 skill · 4 agents · hooks
Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails
3 skills · 1 command · 1 agent
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Install the "AAS Security Engineer" editorial skill bundle for Claude Code.
12 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.