atlas-review

atlas-review is a skill for Claude Code from fledgeling-co/fledgeling-plugins. It costs 344 tokens per session (2,312 once invoked), scanned A, original, MIT.

A workflow for taking open pull requests—proposed code changes—from review through fixes, commits, pushing, merging, test updates, and reporting. It is designed for the Atlas/Bella monorepo, a repository containing multiple related projects.

In plain words
What is it for?
It helps review and fix pull requests, commit and push changes, merge them into the main branch, update tests, and report the result.
Why use it?
It reduces the chance that reviewed changes remain unfinished, unmerged, or unexplained to the product owner.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Gemini CLI.

Part of the atlas-review plugin — 1 skill shipped together

Good fit It helps review and fix pull requests, commit and push changes, merge them into the main branch, update tests, and report the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fledgeling-co/fledgeling-plugins/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.

Any agent
npx skills add fledgeling-co/fledgeling-plugins --skill atlas-review
Clone the repo
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Or install atlas-review, the plugin that ships this one along with the rest of its 1 skill.

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/skills/fledgeling-co/fledgeling-plugins/atlas-review/github.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/atlas-review)
Your own site
<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/atlas-review"><img src="https://agentmods.dev/badge/skills/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/skills/fledgeling-co/fledgeling-plugins/atlas-review"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/atlas-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 344 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,312 The whole file, excluding the scripts and references it only reads on demand.
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.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00344 $0.02312
Opus 5 $0.00172 $0.01156
Sonnet 5 $0.00069 $0.00462
Haiku 4.5 $0.00034 $0.00231

Measured 3d ago against content hash a6ae58a60d75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

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/skills/atlas-review/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

atlas-review, the Atlas review conductor

You take the open pull requests on the Atlas/Bella monorepo and drive them to merged, pushed, and reported. The reporting half is not decoration: the person who opened these PRs is a non-technical product owner, and a merge they cannot read about is a merge they have to take on trust.

The sibling of atlas-publish, which starts where you finish. That skill's boundary is "draft is where automation stops" because publishing reaches phones. Yours is different: merging and pushing to main is recoverable, so you finish the job. What you do not do is release.

Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. Other models skip it.

The loop, in the product owner's own words

Nine stages. Stages 6 to 8 are the ones nobody asks for and every stack needs.

1 review the open PRs          → code-review:code-review, per PR
2 resolve what it found        → YOURS. code-review reports and fixes nothing
3 commit and push
4 merge to main by REBASE      → not a merge commit
5 pull                         → local main is now the real main
6 update the tests             → cover what the PRs actually added
7 do the backend work          → plus whatever the owner's notes ask for
8 test and iterate until green → unit AND automated UI, not one or the other
9 commit and push

Stage 2 exists because code-review is read-only by design. Stage 6 exists because a PR that adds four screens adds no coverage for them. Stage 7 exists because the product owner writes the UI and says so: "I tried not to touch anything backend/API wise and will leave that to you." Their notes arrive as prose, not tickets, and they are a work item.

The one rule that changes what you trust

A test the diff touched is unproven until an injected fault makes it fail.

Not a style preference. Meta's TestGen-LLM deployment filtered 75% of compiling LLM-written tests as vacuous, and 30-54% of generated tests carry structural smells. Worse for you: static reading is measured Low at catching exactly the two shapes that dominate: a mock that swallows the attribute under test, and a guard over a collection that is empty. An LLM reading a test treats a mock as a valid fixture.

Read the full file on GitHub · 158 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 158 lines · 344 tokens per session scan A a6ae58a60d75

Subscribe to this mod's changes

atlas-review is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 344 tokens to every session and 2,312 once invoked, about $0.0017 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 2026-09-09.