atlas-review

atlas-review is a skill for Claude Code from Blazity/atlas. It costs 48 tokens per session (2,487 once invoked), scanned A, original, MIT.

A review process for deciding whether an AI tool, workflow, or change is ready to build, use, release, or investigate after an incident.

In plain words
What is it for?
Use it to assess ideas, challenge plans or implementations, approve releases, or conduct post-incident reviews without changing the project's workspace structure.
Why use it?
It adds an evidence-based checkpoint with a clear decision and a saved review record.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the atlas plugin — 3 skills shipped together

Good fit Use it to assess ideas, challenge plans or implementations, approve releases, or conduct post-incident reviews without changing the project's workspace structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blazity/atlas/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 Blazity/atlas --skill atlas-review
Clone the repo
git clone --depth 1 https://github.com/Blazity/atlas

Made for: Claude Code.

Or install atlas, the plugin that ships this one along with the rest of its 3 skills.

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/blazity/atlas/atlas-review/github.svg)](https://agentmods.dev/skills/blazity/atlas/atlas-review)
Your own site
<a href="https://agentmods.dev/skills/blazity/atlas/atlas-review"><img src="https://agentmods.dev/badge/skills/blazity/atlas/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/blazity/atlas/atlas-review"><img src="https://agentmods.dev/badge/skills/blazity/atlas/atlas-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,487 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 $0.00048 $0.02487
Opus 5 $0.00024 $0.01243
Sonnet 5 $0.00010 $0.00497
Haiku 4.5 $0.00005 $0.00249

Measured 11d ago against content hash 68bc9510c2ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 11d 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.

.ai/skills/atlas-review/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atlas Review

Overview

This skill is the Atlas process gate: an evidence-based checkpoint that applies the Atlas standard to an AI tool and leaves a review artifact with an explicit verdict. The goal is controlled leverage — AI that is useful in real project work without losing control: repeatable, verifiable, observable, secure, and owned.

The skill is framework-agnostic and tool-agnostic: it reviews any AI tool, agent, workflow, or migration regardless of stack or vendor. It never mutates workspace structure — creating, moving, or repairing directories and config is the CLI's job. This skill only reads the workspace config and writes review artifacts into the configured results directory.

Modes

One skill, five modes. Pick the mode from what the user presents — an idea, an accepted idea needing a plan, a plan or implementation to challenge, a release candidate, or an incident. If the mode is ambiguous, ask before starting.

Intake

Decide whether the AI tool should exist: whether AI is actually needed, which preset applies, and what value is expected. Run the Shared Core questions and the Purpose and Fit check in full. Output a build / reshape / do-not-build recommendation with the chosen preset and the expected value.

Plan

Turn an accepted idea into a tool plan: workflow, users, inputs/outputs, autonomy level, data/tools/permissions, validation, monitoring, and ownership. Every Practical Check must have a planned answer; gaps become open questions, not silence.

Review

Challenge a plan or implementation against Atlas: missing proof, unclear owner, weak observability, overbroad permissions, no failure path, poor fit with existing tools, or non-compounding design. Output findings as required changes plus a verdict in the review artifact format.

Gate

Evidence-based readiness check before release or promotion (prototype → internal beta → production candidate → production). The verdict is pass / conditional pass / fail, with required changes, risks, and proof. A conditional pass must name the exact conditions and who clears them. Never issue a verdict without inspecting the evidence first-hand.

Read the full file on GitHub · 215 lines

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. 11d ago First seen · 215 lines · 48 tokens per session scan A 68bc9510c2ba

Subscribe to this mod's changes

atlas-review is a skill published in the GitHub repository Blazity/atlas (24 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,487 once invoked, about $0.0002 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 2026-08-30.