Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/psd401/psd-claude-plugins/worktreenpx skills add psd401/psd-claude-plugins --skill worktreegit clone --depth 1 https://github.com/psd401/psd-claude-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.02390 |
| Opus 5 | $0.00022 | $0.01195 |
| Sonnet 5 | $0.00009 | $0.00478 |
| Haiku 4.5 | $0.00004 | $0.00239 |
Grade A, and why
worktree scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree Command
You manage parallel development using git worktrees. Worktrees let you work on multiple branches simultaneously without stashing or switching — each worktree is an independent checkout of the repo.
Arguments: $ARGUMENTS
Phase 1: Parse Arguments & Detect Intent
ARGS="$ARGUMENTS"
# Detect subcommand
case "$ARGS" in
list|ls)
SUBCOMMAND="list"
;;
prune)
SUBCOMMAND="prune"
;;
clean|sweep|tidy)
SUBCOMMAND="clean"
;;
remove\ *|rm\ *)
SUBCOMMAND="remove"
TARGET=$(echo "$ARGS" | sed 's/^remove //;s/^rm //')
;;
*)
SUBCOMMAND="create"
TARGET="$ARGS"
;;
esac
echo "Subcommand: $SUBCOMMAND"
echo "Target: ${TARGET:-N/A}"
Phase 2: Execute
If list:
echo "=== Active Worktrees ==="
git worktree list
echo ""
echo "=== Branches in Worktrees ==="
git worktree list --porcelain | grep "^branch" | sed 's/branch refs\/heads\// /'
If prune (worktrees only — lightweight):
echo "=== Pruning stale worktrees ==="
git worktree prune --verbose
echo ""
echo "=== Remaining worktrees ==="
git worktree list
If clean (post-merge hygiene — restores what /clean-branch used to do):
Sweeps merged branches (local and remote, squash-merge-aware), stale worktrees, and issues that should be closed. Gather the candidates first; the destructive steps (remote-branch deletion, issue closing) are confirmed before running.
echo "=== /worktree clean — post-merge hygiene ==="
DEFAULT_BRANCH=$(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name' 2>/dev/null || echo main)
if git ls-remote --exit-code --heads origin dev >/dev/null 2>&1; then BASE=dev; else BASE="$DEFAULT_BRANCH"; fi
CUR=$(git branch --show-current); PROT='^(main|master|dev|HEAD)$'
git fetch --prune origin --quiet 2>/dev/null || true # drop tracking refs for branches already deleted on the remote
echo "--- 1. local branches whose work is merged (safe to delete) ---"
LOCAL_DELETE=""
for b in $(git for-each-ref --format='%(refname:short)' refs/heads/); do
echo "$b" | grep -qE "$PROT" && continue
[ "$b" = "$CUR" ] && continue
# normal-merged into base, OR its PR is merged (covers squash merges, which change the SHA)
if git merge-base --is-ancestor "$b" "origin/$BASE" 2>/dev/null \
|| [ -n "$(gh pr list --head "$b" --state merged --limit 1 --json number --jq '.[].number' 2>/dev/null)" ]; then
LOCAL_DELETE="$LOCAL_DELETE $b"
fi
done
echo "${LOCAL_DELETE:-(none)}"
echo "--- 2. worktrees (remove any on a merged/gone branch) ---"
git worktree list
echo "--- 3. remote branches whose PR is MERGED/CLOSED (dependabot excluded) ---"
REMOTE_DELETE=""
for rb in $(git for-each-ref --format='%(refname:short)' refs/remotes/origin/ | sed 's#^origin/##'); do
echo "$rb" | grep -qE "$PROT" && continue
echo "$rb" | grep -qE '^dependabot/' && continue # Dependabot manages its own branches
S=$(gh pr list --head "$rb" --state all --limit 1 --json state --jq '.[].state' 2>/dev/null)
case "$S" in MERGED|CLOSED) REMOTE_DELETE="$REMOTE_DELETE $rb" ;; esac
done
echo "${REMOTE_DELETE:-(none)}"
echo "--- 4. issues still OPEN whose linked PR already merged ---"
ORPHANS=""
for pr in $(gh pr list --state merged --limit 30 --json number --jq '.[].number' 2>/dev/null); do
for issue in $(gh pr view "$pr" --json closingIssuesReferences --jq '.closingIssuesReferences[].number' 2>/dev/null); do
[ "$(gh issue view "$issue" --json state --jq '.state' 2>/dev/null)" = "OPEN" ] && ORPHANS="$ORPHANS #${issue}(PR#${pr})"
done
done
echo "${ORPHANS:-(none)}"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 231 lines · 43 tokens per session scan A fbddf2d14e1b
worktree is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 43 tokens to every session and 2,390 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.