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 marcusquinn/aidevops --skill cloudron-app-publishinggit clone --depth 1 https://github.com/marcusquinn/aidevopsWrote 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/marcusquinn/aidevops/cloudron-app-publishing)<a href="https://agentmods.dev/skills/marcusquinn/aidevops/cloudron-app-publishing"><img src="https://agentmods.dev/badge/skills/marcusquinn/aidevops/cloudron-app-publishing/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/marcusquinn/aidevops/cloudron-app-publishing"><img src="https://agentmods.dev/badge/skills/marcusquinn/aidevops/cloudron-app-publishing.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 | $0.00018 | $0.04264 |
| Opus 5.5 | $0.00007 | $0.01706 |
| Sonnet 5.5 | $0.00004 | $0.00853 |
| Haiku 4.5 | $0.00002 | $0.00426 |
Grade A, and why
cloudron-app-publishing 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 5d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudron App Publishing
Distribute Cloudron apps independently using a CloudronVersions.json version catalog. Users add the file's URL in their dashboard or install via cloudron install --versions-url <url>.
Quick Reference
- Docs: docs.cloudron.io/packaging/publishing
- Upstream skill: git.cloudron.io/docs/skills (
cloudron-app-publishing) - Prerequisite: Each version needs a registry-hosted image, normally built with
cloudron builder login→cloudron builder build; on-server builds cannot be published - Last upstream review:
74e455bd03f5; adopted registry builder and explicit version-image selection guidance - Key file:
CloudronVersions.json— version catalog hosted at a public URL - Listing: Cloudron Community Apps accepts a public versions URL after the catalog contains a tested release; listing is optional
- Forum: announce published community packages in Community Apps (220); ask packaging questions in App Packaging & Development (96)
Workflow
Keep these states distinct: upstream detected (a monitor finding),
package prepared (manifest and changelog updated), image build verified
(immutable Docker sources resolve and a no-push build succeeds), and catalog
published (a reviewed image is present in CloudronVersions.json). Detection
does not authorize any later state.
cloudron versions init # creates CloudronVersions.json + DESCRIPTION.md, CHANGELOG, POSTINSTALL.md (edit all placeholders)
cloudron builder login # authenticate with the Container registry app
cloudron builder build # build and push image; remembers the repository
cloudron versions add --last-build --state testing # record the last builder image without exposing it as stable
cloudron versions update --version=1.0.0 --state=published
# host CloudronVersions.json at a public URL
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.
- 5d ago Changed · +123 lines 279502f86022
- 6d ago Changed · +22 lines 836da2723f7c
- 7d ago Changed 4761380994a3
- 8d ago Changed 568af2d1c37f
- 1mo ago Changed · +6 lines 8d8bd70310f2
- 1mo ago First seen · 136 lines · 18 tokens per session scan A 5b9c9c5c72da
cloudron-app-publishing is a skill published in the GitHub repository marcusquinn/aidevops (421 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 4,264 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
release-publish
Publish an approved Orchard release.
release-review
Review Orchard deployment manifests.
orchard-release
Check deployment evidence and recovery conditions.
release-notes
Draft short release notes from a list of changes. Use when the user asks for changelogs, release notes, or a concise product update.
orchard-review
Review a release proposal.