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 agentmods add commands/kavo-labs/kavo/prgit clone --depth 1 https://github.com/kavo-labs/kavoWrote 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/commands/kavo-labs/kavo/pr)<a href="https://agentmods.dev/commands/kavo-labs/kavo/pr"><img src="https://agentmods.dev/badge/commands/kavo-labs/kavo/pr.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00848 |
| Opus 5 | $0.00008 | $0.00424 |
| Sonnet 5 | $0.00003 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
pr 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 3d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Branch: !
git rev-parse --abbrev-ref HEAD - Working tree: !
git status --short - Commits on branch: !
git log main..HEAD --oneline - Remote: !
git remote -v | head -1 || echo "NO REMOTE" - Existing PR for this branch: !
gh pr view --json number,url,isDraft 2>/dev/null || echo "NO PR"
Your task
Push this branch and create or update its PR. Notes: $ARGUMENTS
-
Refuse to push if any of these hold — say which one, and stop:
- the branch is
main; - there is no GitHub remote;
- the working tree is dirty (commit with
/commitfirst); - there are no commits on the branch.
- the branch is
-
Run the gate for real:
pnpm check pnpm docs:linksIf build, typecheck,
depcruise, or the tests fail, stop and report the failure output. A red gate is never pushed, and never worked around. The same goes fordocs:links— it is a separate CI job, sopnpm checkpassing says nothing about it, and pushing without it means finding out from a red job instead of from a one-second local run. -
Push:
git push -u origin HEAD -
Create the PR, or update it if one already exists (see the context above):
- No PR yet —
gh pr create. Use--draftif the user asked for a draft or if anything non-blocking is still open. The description should say:- What changed and why, in a short paragraph — not a file list.
Closes #<n>for the issue, so the merge closes it automatically. Get<n>from the branch name, which theconventionsskill fixes as<type>/<issue-number>-<short-slug>— theBranch:line in the context above is enough to read it off. If$ARGUMENTSnames an issue explicitly (#123), that wins; if neither yields a number, say so and open the PR without the trailer rather than guessing one, since a wrongClosessilently closes someone else's issue on merge. A PR covering more than one issue gets oneCloses #<n>line each.- Public API impact — barrel changes, and whether they are breaking. Write "none" when there are none; do not omit the line.
- Testing — what was added, and the verified
pnpm checkresult. - Review notes — anything you want a reviewer to look at hardest, and any non-blocking findings deliberately left for later.
- No PR yet —
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.
- 3d ago First seen · 73 lines · 15 tokens per session scan A 8c9b39f7b29c
pr is a command published in the GitHub repository kavo-labs/kavo (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 848 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 2026-09-02.
Other commands, from other repositories
sonicjs-pr-fixer
You are a specialized agent that helps fix and merge problematic PRs in the SonicJS repository. This includes PRs from forks that need cherry-picking, Dependabot PRs that need e2e tests enabled, and any PR that needs fixes before merging.
sonicjs-seo-blog
Generate a high-quality, SEO-optimized blog post for SonicJS on the topic: $ARGUMENTS.
upgrade-webkit
Upgrade Bun's WebKit fork to the latest upstream version of WebKit.
dedupe
Find duplicate GitHub issues.
pre-commit
Before running the checklist, run git fetch origin. If the current branch is behind origin/master, stop and rebase before proceeding.
start
Runs a project that has already been compiled with vendure build.