// Prevent TSZ machines and worktrees from running out of disk while preserving useful build caches. Use before creating worktrees, running large builds/tests, diagnosing low disk, cleaning artifacts, deciding whether to delete caches, or recovering space without slowing future Rust/TypeScript builds.
Drive TSZ GitHub PRs through review, CI, and the merge queue. Use when checking PR status, debugging failing GitHub Actions, deciding whether a PR is WIP, marking draft PRs ready, enqueueing or verifying the queue, landing a PR, or interpreting TSZ CI gates.
Create, refresh, and publish TSZ pull requests with correct coordination state. Use when opening a draft PR, updating a PR body, applying canonical agent labels, changing WIP/draft/ready state, acknowledging review, handing off readiness to a manager agent, or making sure a TSZ PR satisfies AgentName, Project Corpus Impact, verification, and overlap rules.
Audit TSZ repo iteration speed and quality. Use when asked to deep-dive repo health, identify avoidable delays, improve agent workflows, reduce CI/PR churn, add guardrails, choose skills to install or create, or turn recurring TSZ process failures into focused tooling/docs PRs.
Use when planning, implementing, reviewing, or interpreting TSZ performance work, including benchmark regressions, cache/residency changes, timing claims, perf counters, hotspot investigations, OOM/timeout/stack-overflow blockers, or optimization PR evidence.
Start TSZ work safely in a crowded multi-agent checkout. Use when beginning a TSZ task, resuming a goal, switching or creating branches/worktrees, recovering from a merged or stale branch, checking disk/cache state, reading lane goals, or deciding whether local dirty files belong to the requested work.
Preserve TSZ architecture boundaries while changing checker, solver, binder, emitter, LSP, WASM, or CLI code. Use when planning semantic fixes, moving logic across query boundaries, handling architecture guard failures, ratcheting boundary debt, or reviewing changes for solver-first and no hardcoding rules.
| name | tsz-disk-cache-hygiene |
| description | Prevent TSZ machines and worktrees from running out of disk while preserving useful build caches. Use before creating worktrees, running large builds/tests, diagnosing low disk, cleaning artifacts, deciding whether to delete caches, or recovering space without slowing future Rust/TypeScript builds. |
Use this skill whenever disk space or cleanup is part of the task. The priority order is: keep the machine usable, preserve hot build caches when possible, and avoid broad disk archaeology that burns time and terminal output.
Start with compact signals:
df -h .
scripts/setup/disk-worktree-guard.sh
scripts/agents/disk-preflight.sh <AgentName>
git worktree list
Reuse an inactive worktree before creating a new one, especially when it
already has .target, target, .target-bench, or TypeScript state.
If disk is low, run the cache-preserving ladder in order:
scripts/setup/disk-worktree-guard.sh --auto-prune
scripts/setup/clean.sh --quiet
Rerun the compact guard to see whether enough space was recovered.
Escalate only when the guard still reports low space.
Read references/cleanup-ladder.md before deleting worktrees, running
scripts/setup/clean.sh --full, or removing build directories manually.
Preserve by default:
.target/.target-bench/target/TypeScript/These are expensive to rebuild and directly affect iteration speed. Do not run
cargo clean, rm -rf target, or scripts/setup/clean.sh --full as routine
hygiene.
Safe routine cleanup:
incremental subdirectories older than seven days,Before git worktree add, answer:
Preferred new-worktree setup:
git worktree add ../tsz-<short-scope> -b codex/<short-scope>-<yyyymmdd> origin/main
cd ../tsz-<short-scope>
scripts/setup/link-ts-submodule.sh
When cleanup or reuse affects the work, include:
Do not include giant recursive size listings unless a targeted cleanup needs exact ownership.