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 Siteation/magento2-debugbar --skill docsgit clone --depth 1 https://github.com/Siteation/magento2-debugbarWrote 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/siteation/magento2-debugbar/docs)<a href="https://agentmods.dev/skills/siteation/magento2-debugbar/docs"><img src="https://agentmods.dev/badge/skills/siteation/magento2-debugbar/docs/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/siteation/magento2-debugbar/docs"><img src="https://agentmods.dev/badge/skills/siteation/magento2-debugbar/docs.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 | $0.00051 | $0.01501 |
| Opus 5.5 | $0.00020 | $0.00600 |
| Sonnet 5.5 | $0.00010 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
use-siteation-debugbar 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 10d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Siteation Debug Bar
Read exact, stored Magento request data instead of guessing from a screenshot or a log. Every profile is already redacted and bounded. The tools are read only and change nothing.
Find the right request
- If you have the
X-Siteation-DebugBar-Profileresponse header, use that id directly. It is the only reliable way to say which request you are looking at. - Otherwise call
list_debug_profiles. Match on method, path, status and duration. Do not assume the newest profile is the one you want. Storefront pages fire background AJAX, and those are profiled too. - Pass
only_with_findings: truewhen you are hunting for a problem rather than describing a specific request.
Read in the right order
get_debug_findingsfirst, always. It is the module's own conclusion about the request and it is small.- Then the smallest section that tests that conclusion, with
get_debug_profile_section. It serves one ofrequest,queries,events,observers,blocks,cache,pagecache,layout,interception,seoortimeline, a page at a time: passlimit, and feed thenext_cursorit returns back ascursorto read the next page.timelineis the whole request in order, which is the fastest way to see where the time went when no single section stands out. For SEO,get_debug_seois the better read. inspect_debug_queriesonly when the evidence points at the database. Start withfilter: "slow"andlimit: 5.
Ask for small limits. Start with 10 profiles, 10 findings, 5 items. Increase or page with
cursor only when the answer actually needs more.
Measure a change, do not guess at it
compare_debug_profiles takes two profile ids, baseline_profile_id (before the change)
and subject_profile_id (after it), and reports what moved between them:
duration, memory, queries, cache and findings, with query shapes matched by fingerprint so
a repeated query that went away is visible as such. Its seo key lists the SEO facts the
server sent that differ, each with both values, or says why one side has no SEO record.
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.
- 10d ago Changed · +21 lines cb224de278fa
- 11d ago Changed · +4 lines 965f9997b700
- 1mo ago First seen · 79 lines · 51 tokens per session scan A de9b72c78f07
use-siteation-debugbar is a skill published in the GitHub repository Siteation/magento2-debugbar (29 stars, last pushed 10d ago), licensed MIT. It adds 51 tokens to every session and 1,501 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
revenuecat-troubleshoot
Diagnose and resolve RevenueCat integration issues — inspects dashboard configuration through the RevenueCat MCP, walks the SDK debug logs, and covers code-side gotchas. Use when the user says offerings are empty, products not loading, entitlement not active after purchase, paywall won't load, transactions not…
b2c-logs
Retrieve and search logs from B2C Commerce instances using the b2c CLI. Use this skill whenever the user needs to view server logs, search for errors, filter log entries by level or time, or monitor logs in real-time. Also use when the user reports a 500 error, broken checkout, failing job, or any server-side issue…
keynobi
Use for Android work that needs state kept between calls - Gradle builds with their errors and history, logcat streaming and filtering, crashes and deobfuscated stack traces, app exit reasons, launch times, debug sessions that record each install and what followed, and UI automation on the running app - through the…
vendure-troubleshooting
Diagnose a broken or misbehaving Vendure project. Use when a Vendure server or worker does not start, migrations fail or are pending, @vendure/ or plugin versions do not match, assets or emails do not work, or an upgrade to the next 3.x minor breaks something. Collects local project context first, then follows the…
wcs-health-check-processing
WooCommerce Subscriptions 8.8+ Health Check and Processing Reliability playbook for missing renewal schedules, automatic-renewal candidates, guarded Resolve actions, dedicated Action Scheduler processing, web cron, health-check tables, logs, AJAX nonces, and queue filters. Use for WCS Health Check…
wc-logging
Add production-safe WooCommerce logs with wcgetlogger(). Covers stable sources, severity levels and thresholds, structured JSON context, correlation IDs, sensitive-data redaction, WooCommerce 11.0 file-v2 formatting and batched retention cleanup, volume control, custom handlers, and why logs are not durable business…