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.
git clone --depth 1 https://github.com/SaadRahman01/claude-moodle-devWrote 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/rules/saadrahman01/claude-moodle-dev/cmd-moodle-mustache-lint)<a href="https://agentmods.dev/rules/saadrahman01/claude-moodle-dev/cmd-moodle-mustache-lint"><img src="https://agentmods.dev/badge/rules/saadrahman01/claude-moodle-dev/cmd-moodle-mustache-lint/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/rules/saadrahman01/claude-moodle-dev/cmd-moodle-mustache-lint"><img src="https://agentmods.dev/badge/rules/saadrahman01/claude-moodle-dev/cmd-moodle-mustache-lint.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 | $0.00032 | $0.00722 |
| Opus 5.5 | $0.00013 | $0.00289 |
| Sonnet 5.5 | $0.00006 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
cmd-moodle-mustache-lint 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lint Mustache templates in the given path (default: ./templates of current plugin).
User's input: {user_input}
Procedure
- Resolve target path. If
{user_input}empty, glob**/templates/**/*.mustacheunder cwd. - Activate
moodle-accessibilityandmoodle-theme-developmentskills for rule context. - For every
.mustachefile, check:
Security
- No raw triple-stache
{{{ ... }}}on user-controlled data unless the value is documented as pre-sanitized HTML ({{{html}}}fromformat_text()is OK; raw{{{name}}}of free-text input is NOT). - No
<script>blocks — JS belongs inamd/src/modules, loaded via{{#js}}block. - No inline
onclick=/onload=/javascript:URLs.
Accessibility
- Every
<img>hasalt=""(decorative) oralt="{{#str}}..."(meaningful). - Every interactive element is a
<button>or<a href>, not<div onclick>. - Form inputs have associated
<label for="...">oraria-label. - Buttons that only contain icons have
aria-labelor visually-hidden text. - Heading order is not skipped (no
<h1>then<h4>). - Color is not the only signal (icons + text, not just red/green).
Strings & i18n
- No hard-coded user-facing English. Use
{{#str}}identifier, component{{/str}}. - Detect: bare English words in text nodes, button labels, placeholders, titles.
- Aria labels likewise must use
{{#str}}.
Moodle conventions
- Template starts with a Mustache comment block documenting context variables:
{{! @template component/templatename Description. Context variables required for this template: * variable - description }} - Use
{{#pix}}for icons, not raw<i class="fa-...">. - Use
{{#js}}for JS init, not inline<script>. - Use
core/modalmarkup, not bootstrap-direct<div class="modal">.
Output
Produce a markdown report:
# Mustache lint: <path>
## Summary
- Files scanned: N
- Errors: N | Warnings: N | Info: N
## Errors (must fix)
- templates/foo.mustache:12 — raw {{{user_input}}} without sanitization context — use {{user_input}} or document why raw HTML is safe
## Warnings (should fix)
- templates/foo.mustache:34 — hard-coded "Submit" — use {{#str}}submit, core{{/str}}
## Info
- templates/foo.mustache — missing {{! @template ... }} header
## Suggested next steps
1. ...
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 · 78 lines · 722 tokens per session scan A 933fcc7c2de6
cmd-moodle-mustache-lint is a cursor rule published in the GitHub repository SaadRahman01/claude-moodle-dev (41 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 722 once invoked, about $0.0001 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 2026-08-30.
Other cursor rules, from other repositories
add-landing-template
Workflow for adding a new org landing-page template (editorial, vibrant, terminal, etc.) to the ClassroomIO monorepo. Activate when the user asks to add/create/build a new landing template or theme, or hands over a design reference for a new landing visual style.
language-coach
Real-time language coaching. Corrects your writing in your target language before answering every prompt.
report
A set of rules for generating HTML dashboards that present data and analysis in Korean. It defines the required page structure, visual libraries, fonts, and report content.
frontend-translation-management
Maintain consistent translation practices across the frontend application to ensure proper internationalization and user experience.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.