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-headless-apigit 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-headless-api)<a href="https://agentmods.dev/skills/bnomei/kirby-mcp/kirby-headless-api"><img src="https://agentmods.dev/badge/skills/bnomei/kirby-mcp/kirby-headless-api/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-headless-api"><img src="https://agentmods.dev/badge/skills/bnomei/kirby-mcp/kirby-headless-api.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 | $0.00041 | $0.00563 |
| Opus 5.5 | $0.00016 | $0.00225 |
| Sonnet 5.5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
kirby-headless-api 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 11d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kirby Headless API
Use Kirby 6 conventions for new work. Basic Auth cannot complete second factors; use dedicated least-privilege API users rather than disabling 2FA on editor accounts.
KB entry points
kirby://kb/scenarios/44-headless-api-with-kqlkirby://kb/scenarios/02-json-content-representation-ajax-load-morekirby://kb/scenarios/45-headless-kiosk-applicationkirby://kb/scenarios/28-figma-auto-populate
Required inputs
- Consumers and auth requirements.
- Public vs private content boundaries.
- Response shape and caching policy.
- Preferred approach (KQL, representations, or routes).
Default delivery choices
- Use
.jsonrepresentations for page-backed responses. - Use KQL for cross-collection queries and filtered datasets.
- Use routes for non-page or composite endpoints.
Default response envelope
{
"status": "ok",
"data": {}
}
Caching rule
- Public endpoints: set
Cache-Controlwith a short max-age. - Authenticated endpoints: disable caching.
Common pitfalls
- Exposing private fields or drafts in JSON output.
- Caching authenticated responses.
Verification checklist
- Confirm auth requirements and public/private boundaries.
- Validate JSON output for required fields.
Workflow
- Clarify consumers, authentication, and which content is public vs private.
- Call
kirby:kirby_initand readkirby://config/apito confirm API settings. - Check plugin availability for KQL:
kirby:kirby_plugins_index. - If you need custom endpoints, inspect existing routes with
kirby:kirby_routes_index(install runtime if needed). - Search the KB with
kirby:kirby_search(examples: "headless api with kql", "json content representation", "figma auto populate", "headless kiosk"). - Use
kirby:kirby_onlineto fetch official API/KQL docs when KB coverage is insufficient. - Implement:
- enable API auth (
api.basicAuth) when required - create or update KQL queries for
/api/query - add
.jsonrepresentations for template-backed JSON
- enable API auth (
- Verify:
- request
/api/querywith Basic Auth - render
.jsonrepresentations withkirby:kirby_render_page(contentType: json)
- request
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.
- 11d ago Changed · +2 lines 0e1fa328f928
- 1mo ago First seen · 67 lines · 41 tokens per session scan A 77143fc31922
kirby-headless-api is a skill published in the GitHub repository bnomei/kirby-mcp (67 stars, last pushed 8d ago), licensed MIT. It adds 41 tokens to every session and 563 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 2026-08-30.
Other skills, from other repositories
// nodemailer import nodemailer from 'nodemailer'.
supabase
Skill "supabase" from dhaupin/vant, covering supabase, when to use, what to do, 1. connect and supabase-js.
test-integration
Test how components work together. Test database + API, auth + user service, etc. Use when testing multi-component flows or after unit tests pass.
api
Application programming interface.
environment
APIKEY=secret123 DATABASEURL=postgres://localhost DEBUG=true.
graphql
Skill "graphql" from dhaupin/vant, covering graphql, when to use, what to do, 1. query and 2. mutation.