env-hygienelisted

# /foundry:env-hygiene The environment-isolation-hygiene lifecycle. Agents that spin up ephemeral dev/test RESOURCES must bring them DOWN when the work is done — no stacking, no leaks. The enforcement for the *forgetful* agent is automatic (a SessionEnd reaper); this skill is the on-demand `status` + `teardown` surface plus the discipline. ## The directive (own what you start) - **Reuse before start.** Check whether a suitable resource is already running before firing up a new one (reference-counting spirit) — don't stack a second Colima/kind/dev-server. - **LABEL what you start with the session id.** Stamp ownership at create-time so the reaper can identify your resources (and only yours): - containers: `docker run --label foundry.session=$CLAUDE_SESSION_ID …` - clusters: name it `foundry-$CLAUDE_SESSION_ID` (`kind create cluster --name foundry-$CLAUDE_SESSION_ID`) - dev servers: record the pid **with its command + start-time** under `.foundry/env-hygiene/<name>.json` so the pid-recycling guard has a signature to verify. - **Pair setup with teardown.** Every fire-up has a matching bring-down at end of work. - **Never stop the shared runtime.** The container-runtime daemon/host (Colima/Docker/Podman) is shared singleton infrastructure — leave it running; `status` surfaces it, the operator stops it manually if they wish. Tunnels/VPN are status-only too. - **Leave no orphans.** What you started, you bring down (own-scoped). ## Actions | action | what it d