One week of agent-first backend work in the logs: 2,200 session files across four tools, 350 prompts typed by hand, and which checks actually found real defects.
One week of agent-first backend work in the logs: 2,200 session files across four tools, 350 prompts typed by hand, and which checks actually found real defects.
Where Claude Code, Codex, Cursor, Amp, opencode, and pi store session logs, which formats they use, how long they keep them, and what remains undocumented.
One block in CLAUDE.md and AGENTS.md that makes coding agents write throwaway scripts in Ruby instead of Python or bash, so you stay the reviewer instead of a rubber stamp
Real stats from two months of agent-first development: four coding agents (Claude, Codex, Cursor, Amp) competing on every feature across 951 sessions
Documenting a weekend experiment with codex /goal command, using superplanning for initial planning and fizzy cli skill for task management. A straightforward workflow for imple...
Capture the session state before compaction and restores it after. Not a summary. A structured handoff document that any session, agent, or person ca
51 checks that might help combat some of prompt injections in LLM applications.
Automate Rails upgrades with superpowers-ruby v6.1.0 — the rails-upgrade skill enforces green test suites, resolves defaults, and requires explicit ap
Superplanning: a unified Claude Code skill merging top elements from 48+ planning skills into a 7-phase flow for product and feature planning.
superpowers-ruby v5.0.6 adds a Compound Skill adapted from compound-engineering-plugin to capture reusable Rails solutions in docs/solutions and prese
You can also subscribe with RSS!