maias: Skill for Claude Code

.claude/skills/maias-review/SKILL.md

maias-review is a skill for Claude Code from MAIAS-project/maias. It costs 49 tokens per session (817 once invoked), scanned A, original, Apache-2.0.

A review tool for MAIAS documents, which describe an application's information architecture—the screens, navigation, and user journeys. It first validates the document, then checks its structure and usability.

In plain words
What is it for?
Use it to validate and critique MAIAS files, report findings with line references, and assess whether journeys and navigation make sense.
Why use it?
It catches formatting or specification errors as well as dead ends, missing exits, and inconsistent navigation that a mechanical validator may miss.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is MAIAS-project/maias's own configuration. It tells Claude Code how to work on maias itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything maias configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./node_modules/.bin/maias validate <file> --json.

Reuse

Borrowing it

Nothing to install: this file belongs to MAIAS-project/maias. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MAIAS-project/maias/main/.claude/skills/maias-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MAIAS-project/maias

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 maias-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/maias-project/maias/maias-review"><img src="https://agentmods.dev/badge/skills/maias-project/maias/maias-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 817 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 $0.00049 $0.00817
Opus 5 $0.00024 $0.00409
Sonnet 5 $0.00010 $0.00163
Haiku 4.5 $0.00005 $0.00082

Measured 12d ago against content hash 7098cf4362c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

maias-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 12d 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.

.claude/skills/maias-review/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

maias-review

Two layers: mechanical validation (the toolchain's job) and semantic critique of the information architecture (yours).

Layer 1 — mechanical (always first)

./node_modules/.bin/maias validate <file> --json

(Build with npm run build from the repo root if the binary is missing.) Report every finding with its line reference. Errors make the document invalid — lead with them. When there are zero diagnostics, say exactly that in one line ("validator: clean — 0 errors, 0 warnings") and move on to Layer 2; do not pad the mechanical layer. Ground any spec questions in docs/spec/llms.txt; for specific constructs: states → docs/spec/07-states.md, auth/deep links → 09-links-and-gating.md, presentation modes → 04-navigation.md.

Layer 2 — semantic critique

The validator proves the document is well-formed; you judge whether the IA is good. Work through:

Journey integrity

  • Dead ends: screens with no outbound navigation that aren't natural terminals (confirmations are fine; a form with no continue is not).
  • Journeys without exits: does each flow's last screen lead somewhere (replace into the main experience, or back)?
  • Entry/exit seams: are flow transitions marked presentation: replace where back-navigation into a finished journey would be wrong (post-auth, post-checkout)?

Navigation consistency

  • Similar screens, similar patterns: do all detail screens open the same way? Are modals used for the same class of task everywhere?
  • Hub balance: tabs with one screen vs. tabs hiding fifteen — is depth where the user expects it?
  • Self-targets and circular pairs the validator only warns about: are they intentional?
  • Elements-first discipline (spec §4.2): links with an on-screen affordance should be elements with target, not navigation.secondary items. The validator flags exact duplicates (W010); you flag the softer version — a secondary item that plainly describes a laid-out control (same label as a button, a "View X" pairing an obvious list row).
  • Pre-0.3 keys (screen actions, app.links) in a ≤0.2 document: valid, but suggest maias migrate while the document is young.

Read the full file on GitHub · 53 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. 12d ago First seen · 53 lines · 49 tokens per session scan A 7098cf4362c3

Subscribe to this mod's changes

maias-review is a skill published in the GitHub repository MAIAS-project/maias (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 817 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 2026-08-31.