Install
$ agentstack add skill-otaviosoares-agent-skills-land ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
land — post-merge worktree cleanup (thin wrapper)
All logic lives in the bundled script land.sh (same directory as this file: ~/.claude/skills/land/land.sh); this skill only runs it and relays the result. The script operates on whatever repo the current directory is inside — GitHub (gh) or GitLab (glab), picked automatically from origin's host.
Run
From anywhere inside the repo (main checkout or a worktree), passing the user's argument through verbatim — issue number, branch, or path; nothing = the worktree the session is in. Add -n if the user asked for a dry run:
~/.claude/skills/land/land.sh [target] [-n]
After
- Success: relay the script's "Done" summary. If it printed the NOTE about
the shell being inside the removed worktree, cd to the main checkout before any further commands.
- Refusal (exit 1): show the reason verbatim and stop. The refusals are the
safety model — never retry with --force, delete branches manually, or otherwise work around them. If the user wants to override, they do it by hand.
- Locked worktrees: the script unlocks stale claude-session locks (holder
pid gone) and self-held locks (the session running land is the one that locked the worktree — landing from inside it) by itself. If it refuses because a different live claude session holds the lock, tell the user which pid — the fix is to close that session (e.g. its cmux pane) and re-run; only they decide whether to git worktree unlock a session that's still open.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: otaviosoares
- Source: otaviosoares/agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.