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 shopwareLabs/ai-coding-tools --skill xml-config-migratinggit clone --depth 1 https://github.com/shopwareLabs/ai-coding-toolsWrote 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/shopwarelabs/ai-coding-tools/xml-config-migrating)<a href="https://agentmods.dev/skills/shopwarelabs/ai-coding-tools/xml-config-migrating"><img src="https://agentmods.dev/badge/skills/shopwarelabs/ai-coding-tools/xml-config-migrating/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/shopwarelabs/ai-coding-tools/xml-config-migrating"><img src="https://agentmods.dev/badge/skills/shopwarelabs/ai-coding-tools/xml-config-migrating.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 187 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00106 | $0.04878 |
| Opus 5.5 | $0.00042 | $0.01951 |
| Sonnet 5.5 | $0.00021 | $0.00976 |
| Haiku 4.5 | $0.00011 | $0.00488 |
Grade A, and why
xml-config-migrating 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 1mo 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate Shopware Extension XML Configuration to PHP
Shopware 6.7 deprecates loading Symfony configuration from XML for bundles and plugins; Shopware 6.8 removes it, because Symfony 8 drops the XML loaders entirely. Extensions that still ship XML config break with 6.8.
The migration is mechanical and behavior-neutral: the compiled container and route collection stay identical apart from what verify-dumps.sh classifies as inert. A tool-computed verdict is the only verdict that enters the report.
Scope
| In scope | Out of scope (Shopware-specific XML formats — keep as XML) |
|---|---|
src/Resources/config/services.xml, services_test.xml |
Resources/config/config.xml (plugin settings) |
src/Resources/config/routes.xml, routes_<env>.xml, routes_overwrite.xml, any XML under Resources/config/routes/ |
Resources/config/custom-fields.xml, flow.xml, rule-conditions.xml |
src/Resources/config/packages/**/*.xml |
App manifest.xml |
packages/** config is loaded only by a bundle that calls buildDefaultConfig(), which in Shopware is its own core bundles and nothing else; a plugin's packages files are inert unless the extension loads them itself. They stay in scope regardless — dead XML is still XML that has to be gone before 6.8 — but nothing in this workflow can observe their content, so Step 7 and Step 10 treat a packages row differently from every other row.
Prerequisites
- A working Shopware installation (6.6+) with the extension installed and active, and
bin/consoleworking. Run every console command through the project's development environment. jqavailable on the host forverify-dumps.sh.- The dump directory and the extension sources readable from where the bundled scripts run.
${CLAUDE_SKILL_DIR} is this skill's own directory; on a host that does not define it, substitute the path to this skill's directory.
Workflow
digraph xml_config_migrating {
"Skill invoked" [shape=doublecircle];
"Step 1: Inventory (inventory.sh)" [shape=box];
"Inventory empty?" [shape=diamond];
"STOP — report: nothing to migrate" [shape=octagon, style=filled, fillcolor=red, fontcolor=white];
"Step 2: Baseline dumps" [shape=box];
"Step 3: Migrate one XML file to one PHP file" [shape=box];
"Step 4: Import pre-check (check-class-imports.sh)" [shape=box];
"Imports complete?" [shape=diamond];
"Step 5: Add the missing imports" [shape=box];
"Step 6: After dumps" [shape=box];
"Step 7: Verify (verify-dumps.sh)" [shape=box];
"verify-dumps.sh exit 0?" [shape=diamond];
"Step 8: Fix the PHP file" [shape=box];
"Step 9: Tests and deprecation gate" [shape=box];
"Tests and gate pass?" [shape=diamond];
"Step 10: Report" [shape=box];
"Report: migration verified" [shape=doublecircle];
"Report: NOT done" [shape=doublecircle];
"Skill invoked" -> "Step 1: Inventory (inventory.sh)";
"Step 1: Inventory (inventory.sh)" -> "Inventory empty?";
"Inventory empty?" -> "STOP — report: nothing to migrate" [label="yes"];
"Inventory empty?" -> "Step 2: Baseline dumps" [label="no"];
"Step 2: Baseline dumps" -> "Step 3: Migrate one XML file to one PHP file";
"Step 3: Migrate one XML file to one PHP file" -> "Step 4: Import pre-check (check-class-imports.sh)";
"Step 4: Import pre-check (check-class-imports.sh)" -> "Imports complete?";
"Imports complete?" -> "Step 5: Add the missing imports" [label="no"];
"Step 5: Add the missing imports" -> "Step 4: Import pre-check (check-class-imports.sh)";
"Imports complete?" -> "Step 6: After dumps" [label="yes"];
"Step 6: After dumps" -> "Step 7: Verify (verify-dumps.sh)";
"Step 7: Verify (verify-dumps.sh)" -> "verify-dumps.sh exit 0?";
"verify-dumps.sh exit 0?" -> "Step 8: Fix the PHP file" [label="no"];
"Step 8: Fix the PHP file" -> "Step 6: After dumps";
"verify-dumps.sh exit 0?" -> "Step 9: Tests and deprecation gate" [label="yes"];
"Step 9: Tests and deprecation gate" -> "Tests and gate pass?";
"Tests and gate pass?" -> "Report: NOT done" [label="no"];
"Tests and gate pass?" -> "Step 10: Report" [label="yes"];
"Step 10: Report" -> "Report: migration verified";
}
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 204 lines · 106 tokens per session scan A a8e98733ec15
xml-config-migrating is a skill published in the GitHub repository shopwareLabs/ai-coding-tools (45 stars, last pushed 4d ago), licensed MIT. It adds 106 tokens to every session and 4,878 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
commerce-detail-page-copy
A writing tool for Korean e-commerce product detail pages. It can generate a full 13-section page, assess an existing page, or create two persona-based copy sets.
commerce-ad-claim-compliance-kr
A pre-publication check for Korean advertising and product-page wording. It reviews claims against South Korea's advertising, food-safety, and e-commerce laws.
commerce-detail-page-planner
A strategy brief for deciding what a Korean e-commerce product page should say, show, and prioritise. It defines the main message, opening, page structure, sales channel approach, and photo checklist before copy, code, or images are made.
commerce-integrated-strategy
An e-commerce planning skill that combines customer research, product messaging, and store data into a one-page sales strategy with three priority actions.
cs-voc-triage
A customer-feedback analysis tool that combines reviews and support contacts from multiple channels. VOC means “voice of the customer”: the comments, questions, complaints, and praise customers leave about a business.