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 skills/trebormc/drupal-ai-agents/drupal-debuggingnpx skills add trebormc/drupal-ai-agents --skill drupal-debugginggit clone --depth 1 https://github.com/trebormc/drupal-ai-agentsWhat 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 | $0.00115 | $0.02193 |
| Opus 5 | $0.00057 | $0.01097 |
| Sonnet 5 | $0.00023 | $0.00439 |
| Haiku 4.5 | $0.00012 | $0.00219 |
Grade D, and why
drupal-debugging scanned grade D with 2 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Browser screenshots not saving | `ssh web mkdir -p /var/www/html/sites/simpletest/browser_output && ssh web chmod 777 /var/www/html/sites/simpletest/browser_output` | Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| "Test site directory exists already" | `ssh web rm -rf /var/www/html/sites/simpletest/` then recreate browser_output dir | How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Environment
All commands via ssh web.
For Xdebug tracing/profiling (function call trees, execution timing), use the xdebug-profiling skill.
Core Debugging & Information
| Command | Purpose |
|---|---|
ssh web drush status |
Drupal root, site path, DB connection |
ssh web drush core-status |
Detailed system status |
ssh web drush watchdog:show |
Recent log messages |
ssh web drush watchdog:show --severity=Error |
Only errors |
ssh web drush watchdog:show --count=50 |
Last 50 entries |
Cache Debugging
| Command | Purpose |
|---|---|
ssh web drush cache:clear render |
Clear only render cache |
ssh web drush cache:clear router |
Rebuild routing cache |
ssh web drush cache:clear css-js |
Clear CSS/JS aggregation cache |
ssh web drush cr |
Full cache rebuild (when in doubt, use this) |
Configuration Debugging
| Command | Purpose |
|---|---|
ssh web drush config:get system.site |
Show config value |
ssh web drush config:set system.site name "New" |
Set config value |
ssh web drush config:status |
Show config sync status |
PHP Evaluation (drush php:eval)
# Inspect state values
ssh web drush php:eval "var_dump(\Drupal::state()->get('system.cron_last'));"
# Check if function exists
ssh web drush php:eval "var_dump(function_exists('my_custom_function'));"
# List enabled modules
ssh web drush php:eval "print_r(array_keys(\Drupal::moduleHandler()->getModuleList()));"
# Pending entity definition updates
ssh web drush php:eval "print_r(\Drupal::entityDefinitionUpdateManager()->getChangeSummary());"
# List available services
ssh web drush php:eval "print_r(\Drupal::getContainer()->getServiceIds());"
# Check specific service exists
ssh web drush php:eval "var_dump(\Drupal::hasService('mymodule.my_service'));"
# Inspect entity field definitions
ssh web drush php:eval "print_r(array_keys(\Drupal::service('entity_field.manager')->getFieldDefinitions('node', 'article')));"
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.
- 2d ago First seen · 190 lines · 115 tokens per session scan D 0a98dc174ca9
drupal-debugging is a skill published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 115 tokens to every session and 2,193 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…