Notes on agent tooling, token economics, and the tools and products behind mellicci.dev.https://mellicci.devhttps://mellicci.dev/writing/decision-models-prompt-injection-guardhttps://mellicci.dev/writing/decision-models-prompt-injection-guardUp to three models screened 10,336 test emails and repository files, mostly from public prompt-injection datasets on Hugging Face and GitHub. Email results look promising; repository results do not yet. An indication from a lab test, not production evidence.Thu, 22 Oct 2026 00:00:00 GMThttps://mellicci.dev/writing/token-cost-fundamentals-coursehttps://mellicci.dev/writing/token-cost-fundamentals-courseA free, ten-page module on what a coding agent costs to run and why, built from four mechanics (re-reading, caching, expiry and generation) and ending with a controlled cost experiment you can run on your own work.Thu, 22 Oct 2026 00:00:00 GMThttps://mellicci.dev/writing/cli-or-mcp-kubernetes-agent-token-costhttps://mellicci.dev/writing/cli-or-mcp-kubernetes-agent-token-costFour hypotheses tested in 40 measured agent runs across five Kubernetes operations (incident repair, a failed rollout, a capacity change, a memory fix and a Helm lifecycle), each evaluated per session with Agent Tokenwatch against independently verified success.Sat, 03 Oct 2026 00:00:00 GMT