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-multi-version-compatnpx skills add trebormc/drupal-ai-agents --skill drupal-multi-version-compatgit 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 | $0.00194 | $0.01562 |
| Opus 5 | $0.00097 | $0.00781 |
| Sonnet 5 | $0.00039 | $0.00312 |
| Haiku 4.5 | $0.00019 | $0.00156 |
Grade A, and why
drupal-multi-version-compat 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drupal Multi-Version Compatibility
Multi-version support creates conflicts where generic "modernize" advice is wrong. Measure
locally, then apply the matrix. All commands via ssh web.
Step 1 — Measure, never trust the report
Bot / Upgrade Status reports come from the drupal.org snapshot, which may be many commits behind your working tree. Verify every finding against local code first (in a real case 4 of 6 finding categories were already fixed locally and one referenced deleted code).
Local measurement, no extra tooling: PHPStan with phpstan-deprecation-rules. If
phpstan/extension-installer is present, the deprecation rules are ALREADY active in every
normal run — a level-8 clean run means zero deprecated API usage. Do NOT add a manual
includes: entry for the deprecation rules in that case: PHPStan aborts the whole run with
an error when the same extension is included twice.
# 1. Is extension-installer present? If yes, deprecation rules already run — add NO includes.
ssh web composer show phpstan/extension-installer
# 2. Measure. Every remaining deprecation finding is real; anything the bot reports beyond
# this list is stale.
ssh web ./vendor/bin/phpstan analyse $DDEV_DOCROOT/modules/custom/<module>
Step 2 — Accept/reject matrix
| Change | Verdict for ^10.2 || ^11 || ^12 |
|---|---|
| core_version_requirement: ^10.2 \|\| ^11 \|\| ^12 in EVERY info.yml (submodules too) | REQUIRED |
| REQUIREMENT_* constants (removed in D12) | REQUIRED — normalize ONCE (one helper converting the RequirementSeverity enum and legacy ints to a single int), NOT the bot's per-line DeprecationHelper::backwardsCompatibleCall() |
| PHPUnit annotations → attributes | REJECT while D10 is supported: #[DataProvider] is invisible to PHPUnit 9 → data-provider tests silently break on D10. Keep annotations, accept the doc-comment warnings, file a follow-up |
| Procedural hooks → OOP #[Hook] classes | REJECT: needs D11.1+; procedural hooks work in 10/11/12. Optional even after dropping D10 |
| #[RunTestsInSeparateProcesses] on Kernel AND Functional test classes | REQUIRED (deprecated without it since D11.3, throws in D12; harmless on D10 — unknown attributes are ignored) |
| Rector patch brace style | Always re-run PHPCS: bot output uses PSR-12 braces that violate the Drupal standard |
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 · 129 lines · 194 tokens per session scan A c7f9b96fa419
drupal-multi-version-compat is a skill published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 194 tokens to every session and 1,562 once invoked, about $0.0010 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…