model-review-artifact

model-review-artifact is a skill for Claude Code, Codex from 45ck/skill-harness. It costs 28 tokens per session (687 once invoked), scanned A, original, MIT.

A way to prepare architecture and system diagrams for human review while keeping their original text source easy to edit and compare. It covers views such as C4 architecture diagrams, UML-style diagrams, dependency graphs, and workflows.

In plain words
What is it for?
Use it to create source-backed context, component, sequence, state, class, deployment, dependency, and change-impact views, plus notes about ownership, risks, and design decisions.
Why use it?
It keeps diagrams tied to evidence from code, specifications, or project documents instead of treating a picture as the only source of truth. It also avoids relying on live diagram software inside the review page.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create source-backed context, component, sequence, state, class, deployment, dependency, and change-impact views, plus notes about ownership, risks, and design decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/45ck/skill-harness/model-review-artifact
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 45ck/skill-harness --skill model-review-artifact
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

Made for: Claude Code, Codex.

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 model-review-artifact

README.md
[![agentmods](https://agentmods.dev/badge/skills/45ck/skill-harness/model-review-artifact/github.svg)](https://agentmods.dev/skills/45ck/skill-harness/model-review-artifact)
Your own site
<a href="https://agentmods.dev/skills/45ck/skill-harness/model-review-artifact"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/model-review-artifact/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 model-review-artifact

Your own site · 80×15
<a href="https://agentmods.dev/skills/45ck/skill-harness/model-review-artifact"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/model-review-artifact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 687 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 $0.00028 $0.00687
Opus 5 $0.00014 $0.00344
Sonnet 5 $0.00006 $0.00137
Haiku 4.5 $0.00003 $0.00069

Measured 9d ago against content hash 8aba18f4b892, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

model-review-artifact 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 9d 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.

packs/developer-artifact-skills/skills/model-review-artifact/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Review Artifact

Use this skill when a human needs to inspect a system model, architecture view, dependency graph, workflow, or UML-style diagram.

Core Rule

Keep the model source durable and diffable. Use generated HTML only as the review surface.

  • Canonical source: Markdown, TOON, specgraph, Mermaid text, PlantUML text, or project docs.
  • Review surface: static HTML with pre-rendered inline SVG or static markup.
  • Do not load Mermaid, PlantUML, or other diagram runtimes in generated review HTML by default.

Good Fits

  • C4 context, container, component, dynamic, or deployment views.
  • UML-style sequence, state, class/domain, activity, and use-case views.
  • Architecture-space summaries: ownership, risk, quality attributes, dependencies, and decisions.
  • Blast-radius views for proposed agentic changes.
  • Generated dependency graphs derived from code, package metadata, specs, or traces.

Notation Guidance

  • Mermaid sequence, state, and class diagrams are good source-backed diagram candidates.
  • Mermaid C4 is useful for review, but mark its C4 level explicitly and do not treat the diagram as the only architecture authority.
  • UWE UML is a modelling method, not a Mermaid-native contract. Keep UWE concepts in structured source and generate simplified review diagrams when useful.
  • Dependency graphs should usually be generated from evidence rather than hand-maintained.

Required Metadata

  • artifact type: model-view, model-diff, architecture-view, blast-radius, or review-dashboard
  • model id: stable identity across revisions when the project uses model policy checks
  • model kind: sequence, state, class, domain, context, container, component, dynamic, deployment, dependency, use-case, activity, or architecture-space
  • notation
  • method when relevant: uml, uwe, or c4
  • facets when relevant: UWE content, navigation, presentation, process, access, or adaptation
  • abstraction level: domain, design, runtime, deployment, or decision
  • canonical source path
  • generated review path, if any
  • evidence links
  • owner
  • freshness data: source hash, renderer, renderer version, and generated timestamp when available
  • for model diffs: before artifact id, after artifact id, diff method, lineage, and generated review path

Read the full file on GitHub · 69 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. 9d ago First seen · 69 lines · 28 tokens per session scan A 8aba18f4b892

Subscribe to this mod's changes

model-review-artifact is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 687 once invoked, about $0.0001 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.