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 trebormc/drupal-ai-agents --skill drupal-security-coverage-prepgit clone --depth 1 https://github.com/trebormc/drupal-ai-agentsWrote 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/trebormc/drupal-ai-agents/drupal-security-coverage-prep)<a href="https://agentmods.dev/skills/trebormc/drupal-ai-agents/drupal-security-coverage-prep"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/drupal-security-coverage-prep/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/trebormc/drupal-ai-agents/drupal-security-coverage-prep"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/drupal-security-coverage-prep.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 | $0.00170 | $0.01403 |
| Opus 5.5 | $0.00068 | $0.00561 |
| Sonnet 5.5 | $0.00034 | $0.00281 |
| Haiku 4.5 | $0.00017 | $0.00140 |
Grade A, and why
drupal-security-coverage-prep 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drupal Security Coverage Prep
Walks an EXISTING module through the drupal.org reviewer checklist. All commands via
ssh web; grep the module source directly. Report each finding as defect / verified-safe /
process-gap.
Step 1 — Process requirements (report, do not fix)
Code work is wasted if these are missing:
- FULL project (not sandbox) with a STABLE release (
1.0.0/8.x-1.0). Coverage NEVER applies to dev/alpha/beta/RC. - No open issues tagged "security" in the project queue.
- New projects wait 10 days before opting in.
- The maintainer applies for the vetted role via the project application queue (that application IS the human code review), then opts in on the project page.
Step 2 — Automated code sweep (severity order)
- State-changing GET routes — for every
*.routing.ymlroute whose controller mutates state (runs processes, saves config/state, deletes), require_csrf_token: 'TRUE'. Drupal appends the token automatically toUrl::fromRoute()links, so usually no controller change is needed. Add a functional test asserting BOTH: a tokenless direct request → 403 even WITH permission, AND the generated link contains?token=. |rawin Twig — replace with autoescaping; for module-generated HTML, filter withXss::filterAdmin()and wrap in\Drupal\Core\Render\Markupat the builder/assembly layer so templates stay escape-by-default. Concatenated attribute strings → inline attributes orAttributeobjects.- SQL — every
->query()uses placeholders; no interpolated values (incl.information_schemaqueries). unserialize()— must pass['allowed_classes' => [...]](explicit allowlist or FALSE). Comment WHY those classes — reviewers ask.- Process execution —
Symfony\Component\Process\Processwith ARRAY commands only.shell_exec()/exec()acceptable only with fixed literal commands + an availability guard; any variable interpolation is a defect. - Dangerous functions —
eval(,system(,passthru(, backticks, direct$_GET/$_POST/$_REQUESTaccess → all defects. - Permissions — every route has
_permission/_entity_access; admin-level permissions declarerestrict access: truein*.permissions.yml. - Route parameters — invalid values must yield
NotFoundHttpException(404), not a rendered 200 error page.
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 · 111 lines · 170 tokens per session scan A 179f25994967
drupal-security-coverage-prep is a skill published in the GitHub repository trebormc/drupal-ai-agents (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 170 tokens to every session and 1,403 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…