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/code-analysisnpx skills add trebormc/drupal-ai-agents --skill code-analysisgit 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 | $0.00222 | $0.01688 |
| Opus 5 | $0.00111 | $0.00844 |
| Sonnet 5 | $0.00044 | $0.00338 |
| Haiku 4.5 | $0.00022 | $0.00169 |
Grade A, and why
code-analysis 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 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.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Analysis
Independent quality verdict on a body of code. Output = a report file with findings in
exactly two buckets — BLOCKER (cannot ship as-is) and SUGGESTION (worth improving)
— plus an explicit final verdict. This skill NEVER edits code, never commits, never
"quickly fixes" a finding. All PHP tooling via ssh web.
Step 1 — Scope
- Task/changes review (default when there are uncommitted changes): analyze exactly
the files in
git diff --name-only+git diff --cached --name-only. Read the full file for context, but report findings only on changed code. - Module review (user names a module): everything under
$DDEV_DOCROOT/modules/custom/<module>. - State the chosen scope at the top of the report. Do not silently widen it.
Step 2 — Automated signal (input, not verdict)
Run the quality-checks pipeline on the scope (Audit module first, raw PHPCS/PHPStan/PHPUnit as fallback). Tool output feeds Step 3:
- Tool errors on YOUR scoped code → candidate findings (classify in Step 3).
- Pre-existing errors outside the scope → one SUGGESTION line ("legacy debt exists in X"), never a reason to expand the analysis.
- Tests: run the module's existing suites. A failing test on scoped code is ALWAYS a BLOCKER.
Step 3 — Manual review with fixed classification
Read every scoped file. Classify each finding using this table — do NOT invent severities, do NOT emit warnings without a bucket:
BLOCKER — merge is not acceptable (any single one fails the verdict):
| Category | Examples |
|---|---|
| Security | SQL built by string interpolation; unescaped user input in output or Twig |raw on user content; state-changing route without CSRF/permission; missing access checks; eval/system/backticks on variable input; hardcoded credentials |
| Data integrity | Writes without validation that can corrupt stored data; missing transactions where partial writes break invariants; destructive updates without guard |
| Fatality | Code that fatals on a reachable path (undefined function/class/service, wrong signature vs interface, strict_types violations); failing or crashing tests |
| Broken contracts | Service registered with wrong/missing arguments; hooks with wrong signatures; config schema absent for shipped config; broken DI (\Drupal:: in an injectable class is a BLOCKER only in NEW code, SUGGESTION in touched legacy code) |
| Debug residue | dpm(), dump(), var_dump(), console.log(), dd(), commented-out debug blocks |
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 · 131 lines · 222 tokens per session scan A 87d00df87672
code-analysis is a skill published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 222 tokens to every session and 1,688 once invoked, about $0.0011 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.
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…