atlas-review

atlas-review is a plugin for Claude Code from fledgeling-co/fledgeling-plugins. Its manifest loads nothing; the 1 skill it bundles cost 344 tokens per session together, scanned A, original, MIT.

A workflow for taking open pull requests in the Atlas/Bella monorepo—a repository that contains several related projects—from review through fixes, testing, rebasing, merging, pushing, and reporting.

In plain words
What is it for?
It is for reviewing and resolving pull requests, adding tests, wiring backend changes, applying written product notes, checking the merged tree, and merging by rebase.
Why use it?
It addresses problems that ordinary branch checks can miss, including conflicts introduced after merging and tests that pass without checking the new behavior.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit It is for reviewing and resolving pull requests, adding tests, wiring backend changes, applying written product notes, checking the merged tree, and merging by rebase.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add fledgeling-co/fledgeling-plugins/plugin install atlas-review
Install

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.

Clone the repo
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Wrote 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.

agentmods badge for atlas-review

README.md
[![agentmods](https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/atlas-review/github.svg)](https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/atlas-review)
Your own site
<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/atlas-review"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/atlas-review/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.

agentmods 80×15 button for atlas-review

Your own site · 80×15
<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/atlas-review"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/atlas-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 344 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

atlas-review 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.

plugins/atlas-review/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "atlas-review",
  "version": "1.0.0",
  "description": "Takes the open pull requests of the Atlas/Bella monorepo from arrival to reviewed, fixed, merged, pushed and reported. The review itself is code-review:code-review, which is read-only, so resolving what it finds is this skill's own stage and the reason it exists. Lands by rebase rather than merge commit, pulls so local main is the real main, then runs the three stages a pull-request stack always needs and nobody files: extending the tests to cover what the pull requests added, doing the backend wiring the product owner deliberately left to the developer, and acting on the notes they sent as prose alongside the work. Gates the merged tree rather than the branches, because 20-35% of clean textual merges carry a semantic conflict no branch-isolated check can see, and two such conflicts fired in the session this skill was built from. Treats any test the diff touched as unproven until an injected fault makes it fail: 75% of compiling LLM-written tests are vacuous, and static reading is rated Low at catching the two shapes that dominate, so eighteen unfailable checks were found in one session and none by reading. Verifies a finding out of family before acting on it, since raw LLM review runs 40-70% false positives and cross-model checking halves the error. Every written word goes through create-luke-content, and the run ends in a single-column HTML page a non-technical product owner can finish. The release that follows is atlas-publish's job.",
  "author": {
    "name": "Fledgeling",
    "email": "[email protected]"
  }
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 344 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

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.

  1. 3d ago First seen · 10 lines scan A 56535124e3fb

Subscribe to this mod's changes

atlas-review is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 3d 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 2026-09-09.