agent-workflow
Done is not committed
Context7 and browser automation reach all three developer CLIs, after live verification exposes two integrations lost with an ephemeral worktree.
One skill, three agents
Moving the repository-owned skills to one provider-neutral home, restoring the Codex workspace sandbox, and making portability a tested claim.
The allowlist was too generous
Two routine blog handoffs expose a less routine problem: broad agent permissions were approving destructive commands without review.
More than one agent in the workshop
Codex and Antigravity join Claude Code inside the devcontainer, with pinned versions, shared skills, and checks that the safety boundaries are real.
Tuning the agent workbench: from game log polish to MCP servers
A solo-plus-agents project spends real time on its own tooling. Three days of making the workshop pleasant.
A room where the agent can work
The project moves into a devcontainer with local data, restricted networking, scoped Git identity, and enough browser tooling to run the whole development loop safely.