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 45ck/skill-harness --skill model-review-artifactgit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/model-review-artifact)<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.
<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>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 | $0.00028 | $0.00687 |
| Opus 5 | $0.00014 | $0.00344 |
| Sonnet 5 | $0.00006 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
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.
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, orreview-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
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.
- 9d ago First seen · 69 lines · 28 tokens per session scan A 8aba18f4b892
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.
Other skills, from other repositories
do-it-architecture
Use when authority, ownership, contracts, dependency boundaries, migration, recovery, or structural deletion can change a design.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.
do-it-core
Use when repository work needs a shared baseline for intent, facts, causal changes, and honest evidence.
do-it-decide
Use when uncertainty about a choice, plan, dependency, or handoff could materially change what gets built.
do-it-skill-authoring
Use when creating or revising a do-it skill so its trigger and unique professional judgment are useful without prescribing ceremony.