Borrowing it
Nothing to install: this file belongs to kavo-labs/kavo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kavo-labs/kavo/main/.claude/commands/publish.mdgit 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/publish)<a href="https://agentmods.dev/commands/kavo-labs/kavo/publish"><img src="https://agentmods.dev/badge/commands/kavo-labs/kavo/publish/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/commands/kavo-labs/kavo/publish"><img src="https://agentmods.dev/badge/commands/kavo-labs/kavo/publish.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 | $0.00014 | $0.01606 |
| Opus 5 | $0.00007 | $0.00803 |
| Sonnet 5 | $0.00003 | $0.00321 |
| Haiku 4.5 | $0.00001 | $0.00161 |
Grade A, and why
publish 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 7d 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 — 123 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 - Current lockstep version: !
node -p "require('./packages/core/package.json').version" - Remote: !
git remote -v | head -1 || echo "NO REMOTE" - Package dir argument: $ARGUMENTS
When to use this
Only to bootstrap a package that has never been published — npm view <name>
returns nothing. It exists because npm's trusted-publisher settings are
per-package and configured on npmjs.com, and a package with zero versions has
no settings page to configure, so .github/workflows/publish.yml cannot be
the thing that first publishes it.
Routine releases are not this command. They are a merged release-please
PR: release-please keeps one release PR open on main with the computed
lockstep version bump (every package.json) and the generated CHANGELOG.md;
merging it creates the vX.Y.Z tag + GitHub Release, and publish.yml runs
on release: published. See
docs/internals/adr/0041-releases-are-cut-by-release-please.md
and the design doc
docs/superpowers/specs/2026-08-29-release-please-design.md.
Do not bump versions, commit to main, or push a vX.Y.Z tag from this
command — that is release-please's job.
Your task
Bootstrap the first published version of the package in $ARGUMENTS.
- Preconditions. Refuse and stop unless: the branch is
mainand up to date withorigin/main; the working tree is clean;$ARGUMENTSis one of the directories listed inPACKAGE_DIRSin.github/workflows/publish.yml; andnpm view "<name>"for that package reports no versions (if it has any, this command does not apply — the package is already bootstrapped and goes out through release-please like every other). The package'sversionin itspackage.jsonmust already equal the current lockstep version — bootstrapping never bumps versions.
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.
- 7d ago First seen · 123 lines · 14 tokens per session scan A cf533a84ce8c
publish is a command published in the GitHub repository kavo-labs/kavo (14 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 1,606 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
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
ship
Ship is the operational release-prep flow for a connected project repo.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.
release
Standalone SDK release command for the BUILD repo. Not a workspace phase — runs independently after any number of implement/redteam cycles. Handles PyPI publishing, documentation deployment, and CI management for the kailash Python SDK and its framework packages.
doc-changelog
Generation and maintenance of the project changelog.