Solve constrained optimization problems using Z3. Supports minimization and maximization of objective functions over integer, real, and bitvector domains.

Run AddressSanitizer and UndefinedBehaviorSanitizer on the Z3 test suite to detect memory errors, undefined behavior, and leaks. Logs each finding to z3agent.db.

Parse and interpret Z3 output for human consumption. Handles models, unsat cores, proofs, statistics, and error messages. Translates solver internals into plain-language explanations.

Park interesting ideas for later consideration, resurface them periodically, and promote to commitments when ready.

Cloud infrastructure enumeration — AWS S3 buckets, Azure blob storage, GCP buckets, cloud metadata endpoints, IAM misconfigurations, CDN origin detection.

Queries and triages open GitHub issues that need attention. Helps identify issues needing milestones, labels, or investigation.

Review trust boundaries, auth/authz, injection, secrets, filesystem/network exposure, dependencies, and exploitability without pretending a shallow lint is an audit.

Scaffold a local Codewhale plugin bundle with a versioned manifest, namespaced Skills, and an explicit trust review.

Phishing / social-engineering catalog for the Phisher agent. Use ONLY when the engagement RoE authorizes a phishing engagement. Covers pretext design, GoPhish campaigns, evilginx2 MFA-bypass proxying, O365 credential/token harvest, lookalike domains, and the mandatory blue-team deconfliction handshake.

Writing technical blog posts about tldraw features and implementation details. Use when creating blog content about how tldraw solves interesting problems.

Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources.

Control Philips Hue lights and scenes via the OpenHue CLI.

Edit PDFs with natural-language instructions using the nano-pdf CLI.

Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.

JSON Web Token attacks — algorithm confusion (alg=none, HS256↔RS256), kid header injection, JWKS spoofing, weak HMAC secret cracking, signature stripping.

OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1.

Supply-chain attack category — dependency confusion, typosquatting, package-registry abuse, build-pipeline poisoning, SBOM manipulation.

Modbus TCP attack — port 502 enumeration, coil/holding-register read/write without auth, function-code abuse (FC8 diagnostic, FC43 read-device-id), Modbus-over-Serial via TCP gateway, write-with-no-confirm DoS, value tampering against PLCs.

BACnet/IP attack — UDP/47808 discovery via Who-Is broadcast, ReadProperty / WriteProperty without auth, BBMD abuse for remote reach, vendor-specific I-Am responses, COV (Change Of Value) subscription flood, Building Automation HMI pivot.

Deploy and drive Kali Linux tools via MCP-Kali-Server — structured tool-call interface, SSH tunnel setup, prompt-injection hygiene for AI-assisted engagements.