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 twig-auditgit 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/twig-audit)<a href="https://agentmods.dev/skills/trebormc/drupal-ai-agents/twig-audit"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/twig-audit/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/twig-audit"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/twig-audit.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 | $0.00054 | $0.01359 |
| Opus 5.5 | $0.00022 | $0.00544 |
| Sonnet 5.5 | $0.00011 | $0.00272 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
twig-audit 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twig Audit
Principle: Twig is for presentation ONLY. Preprocess handles logic.
Audit Workflow
- Run the detection greps below on the theme/module templates.
- Read EVERY flagged template in full (grep hits need context to confirm).
- Classify each confirmed hit against the anti-pattern list (severity: drilling/raw = CRITICAL, logic/isolation = HIGH, attributes = MEDIUM).
- Produce the report using the Audit Report Format at the end.
Detection Commands
Replace TPL with the templates directory, e.g. $DDEV_DOCROOT/themes/custom/*/templates/:
# Anti-pattern 1: render array drilling — matches content.field_x[0]['#markup'] and ['#items']
grep -rn "\[.['\"]#" TPL ; grep -rn "\['#" TPL
# Anti-pattern 2: business logic — comparisons/calculations on .value inside if/set
grep -rnE "\{% *(if|set) .*\.value" TPL
# Anti-pattern 3: raw filter usage — every hit must be justified
grep -rn "|raw" TPL
# Anti-pattern 4: non-isolated includes — check each hit for "with_context = false" or "only"
grep -rn "include(" TPL ; grep -rn "{% embed" TPL
# Anti-pattern 6: direct entity access bypassing the render system
grep -rn "\.entity\." TPL
# Anti-pattern 7: attributes built as strings
grep -rnE "class=\"[^\"]*\{\{" TPL
A grep hit is a CANDIDATE, not a confirmed issue — always read the template before reporting.
Anti-Patterns to Detect
1. Render Array Drilling (CRITICAL — Breaks Cache)
{# BAD — loses cache metadata, security risk #}
{{ content.field_image[0]['#markup'] }}
{{ content.field_body['#items'][0]['value'] }}
{# GOOD #}
{{ content.field_image }}
{{ content.body }}
2. Business Logic in Templates
{# BAD #}
{% if user.field_role.value == 'premium' and user.field_expiration.value|date('U') > 'now'|date('U') %}
{% set discount = product.price.value * 0.2 %}
{# GOOD — variable from preprocess #}
{% if has_premium_discount %}
{{ formatted_discounted_price }}
3. Unsafe |raw Usage
{# BAD — XSS vulnerability #}
{{ node.field_user_content.value|raw }}
{# GOOD — use processed field #}
{{ content.field_user_content }}
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 · 188 lines · 54 tokens per session scan A e18ea2e04058
twig-audit is a skill published in the GitHub repository trebormc/drupal-ai-agents (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,359 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 2026-08-31.
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…