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 rgomezcasas/dotfiles --skill global-clean-pr-commitsgit clone --depth 1 https://github.com/rgomezcasas/dotfilesWrote 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/rgomezcasas/dotfiles/global-clean-pr-commits)<a href="https://agentmods.dev/skills/rgomezcasas/dotfiles/global-clean-pr-commits"><img src="https://agentmods.dev/badge/skills/rgomezcasas/dotfiles/global-clean-pr-commits/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/rgomezcasas/dotfiles/global-clean-pr-commits"><img src="https://agentmods.dev/badge/skills/rgomezcasas/dotfiles/global-clean-pr-commits.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.00536 |
| Opus 5 | $0.00011 | $0.00268 |
| Sonnet 5 | $0.00004 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
global-clean-pr-commits 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 9d 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.
What it actually says
Context
- Current git status: !
git status - Current branch: !
git branch --show-current - Upstream tracking: !
git rev-parse --abbrev-ref HEAD@{upstream} 2>/dev/null - Merge base with main: !
git merge-base HEAD main - Commits on this branch (run manually):
git log --oneline <merge-base>..HEAD - Full diff from base (run manually):
git diff <merge-base>..HEAD - Repository root path: !
git rev-parse --show-toplevel
Conventional Commits
We use Conventional Commits specification for all commit messages.
Task
Reorganize all commits on the current branch into clean, logical commits.
Steps
- Analyze the full diff and existing commits to understand all changes
- Propose a list of final commits grouping changes logically — present this to the user as a numbered list with the commit message and which files/changes each commit includes
- Wait for approval — the user may request changes to the grouping, do NOT proceed until they confirm
- Execute once approved:
a.
git reset --soft $(git merge-base HEAD <base-branch>)to undo all commits while keeping changes staged b.git reset HEAD .to unstage everything c. For each proposed commit: stage the relevant files withgit addand create the commit d. Rungit log --oneline $(git merge-base HEAD <base-branch>)..HEADto show the final result
Important
- NEVER force push — that is the user's responsibility
- If there are uncommitted changes at the start, abort and tell the user to commit or stash first
- Preserve ALL changes — no code should be lost in the process
- If a file has changes that belong to different commits, use
git add -por stage specific hunks
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.
- 9d ago First seen · 43 lines · 22 tokens per session scan A 2725b783ce7b
global-clean-pr-commits is a skill published in the GitHub repository rgomezcasas/dotfiles (362 stars, last pushed 21d ago), licensed MIT. It adds 22 tokens to every session and 536 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
git-commit
This skill should be used BEFORE running any git commit command. Triggers when about to run git commit. Ensures commit messages follow Conventional Commits specification and prompts for the Jira ticket number.
create-pr
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes.
scan-commit
Automatically scan the repository for unstaged/untracked changes, group them into logical commits using hunk-level analysis, stage and commit them following Conventional Commits.
smart-commit
Analyze staged changes and split them into multiple logical commits following Conventional Commits.
gen-commit-msg
Generate intelligent commit messages based on staged changes following Conventional Commits format.
ship
Generate a conventional commit message from staged or unstaged changes and create an atomic commit, then optionally push and watch CI until it passes or fails. Use when the user says "write a commit", "generate a commit message", "commit this", "git add .", or "ship this". Push and CI-watch are optional and skipped if…