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 skills/stephansama/packages/multipublishnpx skills add stephansama/packages --skill multipublishgit clone --depth 1 https://github.com/stephansama/packagesWrote 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/stephansama/packages/multipublish)<a href="https://agentmods.dev/skills/stephansama/packages/multipublish"><img src="https://agentmods.dev/badge/skills/stephansama/packages/multipublish.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 | $0.00083 | $0.01243 |
| Opus 5 | $0.00042 | $0.00622 |
| Sonnet 5 | $0.00017 | $0.00249 |
| Haiku 4.5 | $0.00008 | $0.00124 |
Grade A, and why
multipublish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
multipublish
Publishes monorepo packages to multiple registries in a single step. Reads released package info from changesets and loops over configured platforms.
Setup
{
"$schema": "./node_modules/@stephansama/multipublish/config/schema.json",
"platforms": [
["jsr", { "experimentalGenerateJSR": true }],
["npm", { "tokenEnvironmentKey": "NODE_AUTH_TOKEN" }]
]
}
Place as .multipublishrc.json, .config/multipublishrc.json, or a multipublish key in package.json. See cosmiconfig docs for all supported filenames.
Core Patterns
Changeset-based release (GitHub Actions)
- name: Create Changeset Release
uses: changesets/action@v1
id: changesets
with:
publish: pnpm run publish
- name: Publish to other registries
if: steps.changesets.outputs.published == 'true'
run: echo "${{ steps.changesets.outputs.publishedPackages }}" | multipublish
changeset publish output is piped into multipublish via stdin. The JSON array of published packages tells multipublish which packages to process and at which versions.
Use --useChangesetStatus instead of stdin
{
"scripts": {
"preversion": "multipublish --useChangesetStatus --versionJsr",
"version": "changeset version"
}
}
--useChangesetStatus reads which packages have pending (unreleased) changesets directly from the changeset state — without piping from changeset publish. Use it in preversion to update JSR config versions before the changeset version bump runs.
GitHub npm registry with scoped token
{
"platforms": [
[
"npm",
{
"registry": "https://npm.pkg.github.com",
"tokenEnvironmentKey": "GITHUB_TOKEN"
}
]
]
}
Set packages: write permission in the GitHub Actions workflow.
Dry run
multipublish --dry
Runs the full flow but passes --dry-run to the underlying publish commands. Use to verify config without publishing.
Common Mistakes
CRITICAL No jsr.json/deno.json and experimentalGenerateJSR not enabled
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.
- 4d ago First seen · 185 lines · 83 tokens per session scan A ba2938318d80
multipublish is a skill published in the GitHub repository stephansama/packages (5 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,243 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
chrome-release-verify
End-to-end Chrome security backport for an Electron release branch. Given a Chrome Releases blog URL and a branch (e.g. 41-x-y), determines which CVE fixes are missing from the actual synced source, writes the cherry-pick patches locally, validates them with e sync --3 + lint --patches, then pushes a single PR. Use…
release-changelog
Polish a published qiankun GitHub Release's aggregated notes into a bilingual (English then Chinese) write-up with an agent. Use after a release goes out — turning the mechanically-aggregated, per-package release notes into a clean, human-readable, English + Chinese write-up (highlights, de-duped cross-package lines…
opendia-harness
Install, configure, and troubleshoot OpenDia for Grok Build (and other MCP harnesses). Use when setting up the plugin, config.toml MCP entry, ports, extension disconnects, tool timeouts, or tunnel mode.
npm-security
Prevent JavaScript/TypeScript projects from supply-chain attacks across package managers like npm, pnpm, yarn, bun, and deno. Use whenever planning, installing, updating packages or configuring package managers.
opendia
Drive the user's real browser through OpenDia MCP (logged-in sessions, cookies, wallets, bookmarks, history). Use when automating Chrome/Firefox for social posts, form fills, multi-tab research, local webapp testing, or any task that needs the user's existing browser profile — not a disposable cloud browser.
frontmcp-extensibility
Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…