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 CiscoDevNet/essentials --skill git-tidygit clone --depth 1 https://github.com/CiscoDevNet/essentialsWrote 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/ciscodevnet/essentials/git-tidy)<a href="https://agentmods.dev/skills/ciscodevnet/essentials/git-tidy"><img src="https://agentmods.dev/badge/skills/ciscodevnet/essentials/git-tidy/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/ciscodevnet/essentials/git-tidy"><img src="https://agentmods.dev/badge/skills/ciscodevnet/essentials/git-tidy.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 | $0.00121 | $0.01548 |
| Opus 5.5 | $0.00048 | $0.00619 |
| Sonnet 5.5 | $0.00024 | $0.00310 |
| Haiku 4.5 | $0.00012 | $0.00155 |
Grade A, and why
git-tidy 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 21d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Tidy
Cleaning up branches by hand means running twenty git commands and holding the answers in your head. This skill puts the inventory and the classification in a script, so the only thing left is judgment: which of the ask-first items you actually want gone.
Quick start
skills/ess/git-tidy/scripts/audit.sh # read-only; writes a report
Then read report.md from the printed directory, present it, and act on what
the user approves.
What it decides
Every local branch lands in exactly one category. The disposition column is what you may act on without asking.
| Category | Meaning | Disposition |
|---|---|---|
base |
The local integration branch itself | keep |
fresh-start |
Tip is identical to base: work just begun | ask |
merged-ancestor |
Fully contained in base | safe, git branch -d |
pr-merged-verified |
Tip matches a merged PR's head commit | safe, git branch -D |
pr-merged-diverged |
PR merged, then commits were added | ask |
pr-open |
PR still open | keep |
unmerged-no-pr |
Work in progress, nothing upstream | keep |
superseded |
Contained in another local branch | ask |
Worktrees: primary, current, locked, dirty, active and active-open-pr
are kept or asked about; prunable (directory gone) and stale-merged (clean,
work already in base) are safe.
fresh-start is the one that most tools get wrong. A branch sitting exactly on
main looks empty and disposable, but it is almost always someone who just ran
git checkout -b and has not committed yet. Deleting it destroys intent, not
code, which is why it never enters the safe set.
Workflow
1. Audit
Run from inside the target repo. The script only reads; it deletes nothing.
skills/ess/git-tidy/scripts/audit.sh [--base origin/main] [--remote origin]
| Flag | Use it when |
|---|---|
--fetch |
Remote-tracking refs may be stale |
--no-gh |
Offline, or the repo is not on GitHub |
--no-size |
Worktrees are large and du is slow |
--base <ref> |
The integration branch is not main/master |
--output DIR |
You want the report somewhere specific |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 21d ago First seen · 156 lines · 121 tokens per session scan A 74d66ea7e903
git-tidy is a skill published in the GitHub repository CiscoDevNet/essentials (7 stars, last pushed 10d ago), licensed Apache-2.0. It adds 121 tokens to every session and 1,548 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
reviewing-blogs
Reviews and critiques blog posts in src/content/blog/posts/ against Appwrite's established standards for voice, tone, structure, SEO, formatting, and accuracy. Use when the user asks to review, audit, critique, or improve an existing blog post.
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
publish-npm-version
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…
triage-contributor-pr
Triage open pull requests from external contributors to prisma/orm and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…
contrib-pr
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.