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 skills add TweekFawkes/prompts --skill gohomegit clone --depth 1 https://github.com/TweekFawkes/promptsWrote 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.
[](https://agentmods.dev/skills/tweekfawkes/prompts/gohome)<a href="https://agentmods.dev/skills/tweekfawkes/prompts/gohome"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/gohome/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.
<a href="https://agentmods.dev/skills/tweekfawkes/prompts/gohome"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/gohome.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.01935 |
| Opus 5 | $0.00051 | $0.00967 |
| Sonnet 5 | $0.00020 | $0.00387 |
| Haiku 4.5 | $0.00010 | $0.00194 |
Grade C, and why
gohome scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Run both from outside the worktree (the `rm` targets a file inside it but we don't `cd` into it; the `prune` runs with `-C <main>`). After this, `git worktree list` no longer mentions the directory, but every file in it How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gohome — Land the current worktree on main and clean up
You are wrapping up work in a git worktree. The flow assumes the user has been editing on a feature branch like <username>/<slug>, that all code changes for this task are now finished, and that main is the integration branch. The goal: one tidy commit on top of main, the feature branch deleted, the worktree unregistered from git (its directory left on disk so gitignored, hard-to-rebuild local state — env files, build/dependency caches — survives), leaving the user with only the main worktree as far as git is concerned.
This skill ONLY operates on local refs. Do not git push unless the user explicitly asks afterwards.
Authoritative paths
- Current (feature) worktree: the cwd when the skill is invoked.
- Main worktree: the worktree whose branch reads
[main]. Usegit worktree listto confirm. - Project conventions:
- Match the repo's existing commit style — topic-prefixed, imperative subject lines (e.g.
api: add ...,cli: build for ...,tests: extend ...). Follow the most recent few commits ingit log --oneline -5for tone. - History stays linear — feature work is rebased onto
main, thenmainis fast-forwarded. No merge commits.
- Match the repo's existing commit style — topic-prefixed, imperative subject lines (e.g.
Required workflow
1. Reconnaissance (always run first)
Run these in parallel:
git worktree list
git status
git diff --stat HEAD
git log --oneline -5
git log --oneline HEAD..main
git log --oneline main..HEAD
From the output, identify:
- The current branch (must NOT be
main— abort with a clear message if it is). - The main worktree path (the row whose ref reads
[main]). - Whether main has moved ahead of the branch's base (commits in
HEAD..main). - Whether the branch already has its own commits (commits in
main..HEAD). - Any uncommitted changes (staged or unstaged) in
git status.
If git status shows nothing AND main..HEAD is empty, there is nothing to land — tell the user and stop.
2. Stage + commit (only if there are uncommitted 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.
- 11d ago First seen · 130 lines · 101 tokens per session scan C 6a07078acc15
gohome is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 101 tokens to every session and 1,935 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.