Borrowing it
Nothing to install: this file belongs to DavidLam-oss/obsidian-wechat-converter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DavidLam-oss/obsidian-wechat-converter/main/.claude/commands/openprd/visual-prepare.mdgit clone --depth 1 https://github.com/DavidLam-oss/obsidian-wechat-converterWrote 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/davidlam-oss/obsidian-wechat-converter/visual-prepare)<a href="https://agentmods.dev/commands/davidlam-oss/obsidian-wechat-converter/visual-prepare"><img src="https://agentmods.dev/badge/commands/davidlam-oss/obsidian-wechat-converter/visual-prepare.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00324 |
| Opus 5 | $0.00000 | $0.00162 |
| Sonnet 5 | $0.00000 | $0.00065 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
visual-prepare 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- openprd-visual-prepare — 94% identical, 2 lines differ
What it actually says
OpenPrd Visual Prepare
When one confirmed reference image contains multiple sub-images, grid cells, or objects, run openprd visual-prepare . --reference <effect-image> --grid <columns>x<rows> or --boxes <plan.json> before implementation comparison.
Treat newly generated images as candidate references until the user confirms they match expectations, should be used for later effect-image vs implementation comparison, and should drive implementation.
The command writes a deterministic reference-set under .openprd/harness/visual-reviews/reference-sets/<id>/, including reference-set.json, crops/, contact-sheet.jpg, focus-board.template.json, parallel-board.template.json, and compare-plan.json.
Use --include <csv> when the user only wants part of a grid or board to enter later acceptance, instead of blindly carrying the whole image forward.
Always open the generated contact sheet before proceeding, and reject any run where the numbering, crop boundaries, or object completeness look wrong.
After preparation, use compare-plan.json for per-item openprd visual-compare --reference/--actual commands, or edit the generated board templates when one whole screen needs local-region acceptance.
For interactive OpenPrd work, rebuild state from .openprd/ before acting. In unattended automation, skip OpenPrd context/gates unless the task explicitly opts into OpenPrd.
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.
- 3d ago First seen · 18 lines · 0 tokens per session scan A 8774b1c266d1
visual-prepare is a command published in the GitHub repository DavidLam-oss/obsidian-wechat-converter (306 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 324 tokens. 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 2026-09-04.
Other commands, from other repositories
rive-interactive-viewmodel_builder
Command "rive-interactive-viewmodel_builder" from freshtechbro/claudedesignskills, covering /rive-interactive-viewmodelbuilder, description, usage, implementation and notes.
video
Create a design based on video.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.