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 Blazity/atlas --skill atlas-reviewgit clone --depth 1 https://github.com/Blazity/atlasWrote 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/blazity/atlas/atlas-review)<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.
<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>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 | $0.00048 | $0.02487 |
| Opus 5 | $0.00024 | $0.01243 |
| Sonnet 5 | $0.00010 | $0.00497 |
| Haiku 4.5 | $0.00005 | $0.00249 |
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.
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.
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.
- 11d ago First seen · 215 lines · 48 tokens per session scan A 68bc9510c2ba
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.
Other skills, from other repositories
agentic-code-review
Use when reviewing a diff, pull request, branch, or AI-generated code for correctness, security, regression, test, performance, and maintainability risks before merge.
repo-health-check
Use when auditing a repo before changes to find the smallest safe PR, quality risks, stale docs, missing tests, ignored-file gaps, or agent setup issues. Best first skill for unfamiliar codebases.
solid-php
Use when applying SOLID principles to Laravel 13 / PHP 8.3+ code — file size limits, interface placement, or PHPDoc enforcement.
code-quality
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional verification (run verification FIRST, then code-quality).
elicitation
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).
react-effects-audit
Use when auditing React or Next.js components for unnecessary or unsafe useEffect usage -- detects 9 anti-patterns from "You Might Not Need an Effect".