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-debugging-and-tracinggit 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-debugging-and-tracing)<a href="https://agentmods.dev/skills/bnomei/kirby-mcp/kirby-debugging-and-tracing"><img src="https://agentmods.dev/badge/skills/bnomei/kirby-mcp/kirby-debugging-and-tracing/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-debugging-and-tracing"><img src="https://agentmods.dev/badge/skills/bnomei/kirby-mcp/kirby-debugging-and-tracing.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 | $0.00045 | $0.00629 |
| Opus 5.5 | $0.00018 | $0.00252 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
kirby-debugging-and-tracing 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kirby Debugging and Tracing
Use Kirby 6 conventions for new work. When existing code differs, inspect the installed CMS version and kirby://kb/scenarios/83-migrate-kirby-5-to-6 before replacing it; unfamiliar APIs may also come from plugins.
Quick start
- Follow the workflow below to reproduce and trace render issues.
KB entry points
kirby://kb/scenarios/68-snippet-controllerskirby://kb/scenarios/03-shared-controllerskirby://kb/scenarios/13-custom-routeskirby://kb/scenarios/02-json-content-representation-ajax-load-morekirby://kb/scenarios/14-escaping-and-safe-markdown
Required inputs
- Page id/uuid or URL path.
- Expected vs actual output and content type.
- Auth/session requirements and steps to reproduce.
Repro checklist
- Capture page id/uuid or URL, content type, and expected vs actual output.
- Note auth/session state and request parameters.
- Record cache state and the render
traceId.
Stop condition
- Stop once output matches expected behavior and temporary dumps are removed.
Dump placement example
mcp_dump([
'page' => $page->id(),
'template' => $page->intendedTemplate()->name(),
]);
- Remove dumps after the issue is resolved.
Common pitfalls
- Leaving
mcp_dump()in production code. - Debugging cached output or the wrong content type.
Workflow
- Ask for page id/uuid or URL path, expected vs actual output, content type, and any session/login requirements.
- Call
kirby:kirby_init, then ensure runtime availability withkirby:kirby_runtime_statusandkirby:kirby_runtime_installif needed. - Reproduce with
kirby:kirby_render_page(noCache=true, contentType=...)and capturetraceIdplus errors. - Locate relevant code paths:
kirby:kirby_templates_indexkirby:kirby_snippets_indexkirby:kirby_controllers_indexkirby:kirby_models_indexkirby:kirby_routes_indexwhen routing is involved
- If the issue is unclear, add targeted
mcp_dump()calls and read the trace withkirby:kirby_dump_log_tail(traceId=...). - Apply the smallest fix, re-render to confirm, and remove temporary dumps.
- Search the KB with
kirby:kirby_search(examples: "custom routes", "snippet controllers", "shared controllers", "content representations").
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 adec3140b8b3
- 1mo ago First seen · 66 lines · 45 tokens per session scan A be7c8cb347c0
kirby-debugging-and-tracing is a skill published in the GitHub repository bnomei/kirby-mcp (67 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 629 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
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
runtime-admin-api
Call the Mendix M2EE admin API on port 8090 directly — OQL, runtime info, and the rest, with curl examples. Use when querying a running app from a script, or when debugging connectivity to the admin port.
error-codes
Explains an Acme API error code and the fix. Use when the user pastes an E-code from an API response.
doris-debug-deployment
Use for Doris FE/BE startup failures, port conflicts, prioritynetworks misrouting, metadir corruption, and ADD/DROP BACKEND issues.
debug-hub
Evidence-first debugging WITH MCP tools. Use when debughub MCP server is available. Inject log calls, collect via HTTP API (port 39200), analyze through MCP tools, clean up when done. If debughub MCP is unavailable, use debug skill (bundled Python collector) instead.
audit-reliability
Skill "audit-reliability" from dhaupin/vant, covering reliability, the question, what to check, 1. graceful degradation and 2. recovery.