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 bnomei/kirby-mcp --skill kirby-security-and-authgit clone --depth 1 https://github.com/bnomei/kirby-mcpWrote 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/bnomei/kirby-mcp/kirby-security-and-auth)<a href="https://agentmods.dev/skills/bnomei/kirby-mcp/kirby-security-and-auth"><img src="https://agentmods.dev/badge/skills/bnomei/kirby-mcp/kirby-security-and-auth/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/bnomei/kirby-mcp/kirby-security-and-auth"><img src="https://agentmods.dev/badge/skills/bnomei/kirby-mcp/kirby-security-and-auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00565 |
| Opus 5 | $0.00019 | $0.00282 |
| Sonnet 5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
kirby-security-and-auth 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 12d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kirby Security and Auth
KB entry points
kirby://kb/scenarios/62-access-restriction-loginkirby://kb/scenarios/43-user-registration-and-loginkirby://kb/scenarios/63-files-firewall-protected-downloadskirby://kb/scenarios/64-permission-tricks-role-basedkirby://kb/scenarios/67-indieauth-rel-me
Required inputs
- Protected pages/data and required roles.
- Login/logout flow and redirect rules.
- Download protection or route constraints.
Role matrix template
| Role | Pages | Actions | Downloads |
|---|---|---|---|
| admin | all | all | all |
| editor | edit | publish | limited |
Default guard pattern
- Check
$kirby->user()and required role/permission before returning content. - Redirect or return a 403 for unauthorized requests.
- Enforce CSRF and validation on auth-related forms.
Login redirect rule
- Store intended URL in the session and redirect after successful login.
- Fall back to the home page when no intent is stored.
Common pitfalls
- Checking access only in templates while routes remain public.
- Returning a 404 for unauthorized access instead of a 403 or redirect.
Verification checklist
- Test the role matrix across protected pages and downloads.
- Verify login/logout flows and session handling.
- Confirm CSRF failures render safely.
Workflow
- Clarify which pages/data are protected, required roles, and login/logout behavior.
- Call
kirby:kirby_initand readkirby://roots. - Inspect templates/controllers/blueprints to align with existing patterns:
kirby:kirby_templates_indexkirby:kirby_controllers_indexkirby:kirby_blueprints_index
- For protected downloads or auth routes, inspect routes with
kirby:kirby_routes_indexandkirby://config/routes(install runtime if needed). - Search the KB with
kirby:kirby_search(examples: "access restriction login", "user registration and login", "files firewall", "permission tricks", "page on own domain"). - Implement least-privilege checks in templates/controllers or routes; enforce CSRF and validation on auth forms.
- Verify by rendering protected pages (
kirby:kirby_render_page) and manually testing login and download URLs.
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.
- 12d ago First seen · 63 lines · 38 tokens per session scan A 2de831c41875
kirby-security-and-auth is a skill published in the GitHub repository bnomei/kirby-mcp (59 stars, last pushed 13d ago), licensed MIT. It adds 38 tokens to every session and 565 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
defending-applications
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning…
designing-architectures
Architecture knowledge reference covering API design, security architecture, cloud-native patterns, caching strategies, message queues, and data security. Use when designing system architecture, APIs, or cloud-native infrastructure.
backend
Backend engineering judgment, distilled from a stronger model - invoke when CHOOSING a tech stack, language, database, queue, or architecture; designing a service, API, business logic, or schema; making a system production-ready (observability, failure handling, security); or reviewing server-side code and judging…
api-contract-design
Use this skill when freezing the interface between a backend and its clients before parallel work starts, or when changing an endpoint other code already calls - request/response shapes, status codes, error envelope, pagination, filtering, idempotency, versioning, and the breaking-change rules. Covers writing the…
supabase-setup
Use this skill when setting up or changing a Supabase database - schema, migrations, row-level security, seeds, typed clients, or connecting an app to a hosted project. Covers the safe order of operations and the checks that prevent a public table or an unreviewable schema change.
yolo-detector
Use when designing or verifying Ultralytics YOLO detection, segmentation, tracking, or pose inference with licensed models and stable JSON outputs.