landtomain

landtomain is a skill for Claude Code, Codex from TweekFawkes/prompts. It costs 172 tokens per session (3,620 once invoked), scanned A, original, Unlicense.

A workflow for merging the current Git worktree branch into the main branch and checking that the worktree can be deleted safely. A Git worktree is a separate checkout of the same repository.

In plain words
What is it for?
Syncing with main, committing and pushing changes, opening and merging a GitHub pull request, and checking for anything that could be lost.
Why use it?
It reduces the risk of leaving commits, files, tickets, or saved changes behind when cleaning up a worktree.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

Good fit Syncing with main, committing and pushing changes, opening and merging a GitHub pull request, and checking for anything that could be lost.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tweekfawkes/prompts/landtomain
Install

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.

Any agent
npx skills add TweekFawkes/prompts --skill landtomain
Clone the repo
git clone --depth 1 https://github.com/TweekFawkes/prompts

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for landtomain

README.md
[![agentmods](https://agentmods.dev/badge/skills/tweekfawkes/prompts/landtomain/github.svg)](https://agentmods.dev/skills/tweekfawkes/prompts/landtomain)
Your own site
<a href="https://agentmods.dev/skills/tweekfawkes/prompts/landtomain"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/landtomain/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for landtomain

Your own site · 80×15
<a href="https://agentmods.dev/skills/tweekfawkes/prompts/landtomain"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/landtomain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00172 $0.03620
Opus 5 $0.00086 $0.01810
Sonnet 5 $0.00034 $0.00724
Haiku 4.5 $0.00017 $0.00362

Measured 11d ago against content hash 2b010616ca80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

landtomain 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 11d 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.

skills/landtomain/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/landtomain — Merge this worktree into main, then prove it's safe to delete

You are wrapping up work in a git worktree. The goal: every change in this worktree lands on main via a merged GitHub PR, and you prove that deleting the worktree afterward loses nothing. You do the merge; you do NOT delete the worktree — the user deletes it once you've confirmed it's safe.

This is the "finish and clean up" counterpart to two narrower skills:

  • /openpr pushes a branch and opens a PR but never merges — use it when the change needs human review.
  • /gohome lands work on main locally and never pushes.
  • /landtomain (this skill) syncs → pushes → opens PR → merges it → verifies the worktree is safe to delete → rescues anything at risk → reports. It stops short of the actual git worktree remove.

Work the phases in order. Stop and ask if any phase fails, is ambiguous, or surfaces something unexpected — landing to main and the subsequent delete are hard to walk back.

Authoritative facts (verify, don't assume)

  • Remote: origin → your GitHub repo. Confirm with git remote -v.
  • Base branch: main.
  • CLI: use the gh CLI for all GitHub operations (confirm with gh auth status). Never hand-craft API calls.
  • Branch naming: feature branches follow your convention (e.g. <username>/<slug>); agent branches may be codex/<slug> or claude/<slug>. Use the branch already checked out — do not rename it.
  • Merge style: if the repo merges PRs as a merge commit, Merge pull request #N from <branch>, with the PR title as the merge subject, write the PR title as the real change summary and merge with gh pr merge --merge (not squash/rebase) unless the user says otherwise.
  • Worktree gitignored artifacts: a worktree may carry seeded, gitignored local state (env files, dependency/build caches). These do NOT appear in git status and are NOT "lost work" — they're reproducible and seeded fresh on every worktree. Never force-add them, and never count them as something to rescue.
  • What deleting a worktree actually loses: only things that exist solely in this worktree's working tree and aren't on main — i.e. uncommitted/unstaged changes, untracked non-ignored files (e.g. new z_tickets/** files), and unmerged local commits. (Stashes are stored in the shared repo .git, not the worktree, so a stash survives the delete — but still surface it, per the brief.) Proving the worktree is safe to delete = proving none of those exist, or that you've rescued them.

Read the full file on GitHub · 195 lines

Changes

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.

  1. 11d ago First seen · 195 lines · 172 tokens per session scan A 2b010616ca80

Subscribe to this mod's changes

landtomain is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 172 tokens to every session and 3,620 once invoked, about $0.0009 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.