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 agentmods add commands/abdulkader-safi/wp-to-code/wp-diffgit clone --depth 1 https://github.com/Abdulkader-Safi/wp-to-codeWhat 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 | $0.00019 | $0.00540 |
| Opus 5 | $0.00010 | $0.00270 |
| Sonnet 5 | $0.00004 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
wp-diff 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 yesterday.
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
Run the diff gate for the page the user named: $ARGUMENTS.
NODE_PATH="${CLAUDE_PLUGIN_DATA}/node_modules" \
node "${CLAUDE_PLUGIN_ROOT}/scripts/diff.mjs" --page <slug> [--viewport 1440,768,390]
Before running, confirm both sides are actually being served:
- The mirror server on the port in
.wp-to-code/config.json(mirror.port). Start it withnode "${CLAUDE_PLUGIN_ROOT}/scripts/serve.mjs"if it is not up. - The project's own dev server on
port.devUrl.
A connection error against one of those two URLs is the most common cause of a failed run, so check that before touching any markup.
Reading the output
1440px
# height top verdict section
0 839 vs 838 0 vs 0 MATCH header
1 267 vs 267 839 vs 838 MATCH section.stats
2 612 vs 612 1106 vs 1206 Δtop +100 section.mission
Δhmeans the section is the wrong height. Work inside it.ΔtopwithΔhabsent means the section is the right size and in the wrong place. Something above it moved, or a margin collapsed out of it. Check the first section above with a delta, and check for a negative margin on an inner element that has escaped its parent.flow-rooton the container is the usual fix.clientWidth differsmeans the two pages are laying out at different widths, usually a scrollbar. Nothing below that line is comparable until it matches.section countmismatch means the structure diverged. Fix that before reading any number.
What to do next
Work top down: the first section with a delta often explains every delta below it. Fix one section, run the diff again. Two to four rounds per page is normal.
Do not round measured values to the framework's spacing scale. Use the measured number as an arbitrary value.
When every section matches, say so with the table. Never report a page as done without a diff run behind it, and never report it on height alone.
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.
- yesterday First seen · 43 lines · 19 tokens per session scan A 67bb4678cdce
wp-diff is a command published in the GitHub repository Abdulkader-Safi/wp-to-code (2 stars, last pushed 13d ago), licensed MIT. It adds 19 tokens to every session and 540 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 2026-08-31.
Other commands, from other repositories
ds-sync
Mevcut bir tasarım sistemi kütüphanesini Figma'dan senkronize eder. Tam sync, kısmi sync ve resume (yarım kalanı devam ettirme) destekler.
feature
Post a feature to the Features Board on production and write tweets.
commit-all
Group all changes semantically and commit each group separately.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
build-verify
Run the full build / test / analyze / format verification pass for this Flutter app.
apollo-status
Show the current Apollo removal migration progress.