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.
git clone --depth 1 https://github.com/theclaymethod/artifactureWrote 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/commands/theclaymethod/artifacture/generate-visual-plan)<a href="https://agentmods.dev/commands/theclaymethod/artifacture/generate-visual-plan"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/generate-visual-plan/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/commands/theclaymethod/artifacture/generate-visual-plan"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/generate-visual-plan.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 | $0.00011 | $0.00376 |
| Opus 5.5 | $0.00004 | $0.00150 |
| Sonnet 5.5 | $0.00002 | $0.00075 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
generate-visual-plan 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 15d 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.
What it actually says
Load SKILL.md and cards/visual-plan.md, then plan: $@
Use cards/code-walkthrough.md for sections that explain existing code.
Establish the proposal
- Extract the desired behavior, constraints, and scope from the request.
- Inspect affected modules, callers, types, APIs, extension points, and existing tests. Find similar implementations before proposing new mechanisms.
- Work through state transitions, API contracts, integration points, failures, concurrency, and compatibility.
- Record each claim with its source location. Distinguish verified current behavior, proposed changes, and unresolved assumptions.
Compose the plan
Lead with a concrete current-versus-desired example. Include the sections the implementation requires:
- A state or flow diagram when transitions matter. Follow
cards/web-diagram.md; label decisions with their conditions and outcomes. - A state table with names, types, purpose, and changes.
- API signatures and focused code snippets with source paths.
- Edge cases paired with expected behavior.
- A file/change table and implementation order where dependencies require it.
- Existing checks and direct runtime validation that would establish success. Propose new test files only within the user's authorized scope.
- Compatibility, performance, migration, or rollback notes that affect the design.
Prefer prose for rationale, tables for comparable facts, and diagrams for relationships. Use shared components and the default ISO preset. Do not add a document-type kicker, arbitrary focal statistic, metric tiles, or repeated cards around each paragraph.
Write MDX/TSX beside ~/.agent/diagrams/<feature-name>-plan.html, export using SKILL.md, and complete references/verification.md. Open the artifact and report the editable source, HTML, final report, and unresolved assumptions.
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.
- 15d ago Changed dda23f942e9f
- 16d ago Changed 37e4b8811531
- 1mo ago Changed · -89 lines · -9 tokens per session 439a9585b412
- 1mo ago First seen · 118 lines · 20 tokens per session scan A 1c3a75fdfc1e
generate-visual-plan is a command published in the GitHub repository theclaymethod/artifacture (3 stars, last pushed 5d ago), licensed MIT. It adds 11 tokens to every session and 376 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other commands, from other repositories
octo-design-ui-ux
Design UI/UX systems with style guides, palettes, typography, and component specs.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
ux-audit
Audit a Figma file against a design brief — checks page structure, frame naming, sizes, styles, components, and content compliance.
ux-grill
Use when a running web app's UX has to be audited reproducibly rather than by feel — a deterministic mechanical pass over routes and viewports (axe, target size, horizontal overflow, page title, scripted journeys) followed by a screenshot-grounded interrogation of the operator, journey by journey, with two persona…
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.