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.
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/plugins/fledgeling-co/fledgeling-plugins/atlas-publish)<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/atlas-publish"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/atlas-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/plugins/fledgeling-co/fledgeling-plugins/atlas-publish"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/atlas-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
atlas-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 1mo 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.
What it actually says
{
"name": "atlas-publish",
"version": "2.1.3",
"description": "Takes the open PRs of the Atlas/Bella monorepo to a registered draft release on either the over-the-air or the App Store lane, classifying between them from the expo-updates native fingerprint rather than from intent — ios.buildNumber sits inside that fingerprint, so a buildNumber bump alone forces a store release. Every irreversible step names the observable to read back, because a build tool, an upload and an MCP call all return success without having done anything. Gates report not-run as a third state beside passed and failed, which is how a cert-parity test that skips its only real assertion stops reading as a green gate. Eleven steps, each marked with the lanes it applies to and each with an abort path next to it. Draft is where automation stops: publishing to users is a founder action the skill will not take. The diff review that used to ship beside it is now the standalone code-review:code-review plugin.",
"author": {
"name": "Fledgeling",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 281 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago Changed 5e8ceb550d38
- 1mo ago Changed c522f2db5da8
- 1mo ago First seen · 10 lines scan A 09e67e4f0617
atlas-publish is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 8d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
asc
Production workflows for shipping apps with the unofficial App Store Connect CLI, including builds, TestFlight, metadata, submissions, signing, screenshots, and Apple Ads.
asc-mcp
Run an App Store release from a conversation: review status, reviews and sales, metadata, screenshots, builds, TestFlight, in-app purchases, submit and release. A local MCP server for App Store Connect plus a review-triage skill.
android-release-bump
Reusable Android release workflow with version bumps, Play release notes, verification, optional headless emulator QA, and optional Play upload.
charon
Ferries a GitHub PR to merge without waiting forever: an honest snapshot-not-block loop that fixes CI, repairs conflicts, version-checks reviewer suggestions, and never says 'just wait'.
oat-publish-python
Python release management: cleanup, version bump, uv build, GitHub release, publish monitoring.
ooda-loop marketplace
Plugin marketplace listing 1 plugin: ooda-loop.