Borrowing it
Nothing to install: this file belongs to bitcoinaustria/pretix-agent-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bitcoinaustria/pretix-agent-mcp/main/.claude/skills/add-pretix-tool/SKILL.mdgit clone --depth 1 https://github.com/bitcoinaustria/pretix-agent-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/bitcoinaustria/pretix-agent-mcp/add-pretix-tool)<a href="https://agentmods.dev/skills/bitcoinaustria/pretix-agent-mcp/add-pretix-tool"><img src="https://agentmods.dev/badge/skills/bitcoinaustria/pretix-agent-mcp/add-pretix-tool/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/bitcoinaustria/pretix-agent-mcp/add-pretix-tool"><img src="https://agentmods.dev/badge/skills/bitcoinaustria/pretix-agent-mcp/add-pretix-tool.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 | $0.00069 | $0.01482 |
| Opus 5 | $0.00034 | $0.00741 |
| Sonnet 5 | $0.00014 | $0.00296 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
add-pretix-tool 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a pretix tool
Read tools/events.py first — it is the reference implementation, and matching it is faster than reading this twice. The rules that are not obvious from it are below.
1. Check what pretix actually offers
Fetch https://docs.pretix.eu/dev/api/resources/<resource>.html and confirm the endpoint
path, the required fields on create, and the exact field names. A wrong path is the most
common failure here, and memory is not good enough — the docs also contain a few
singular/plural typos where the DRF router registers the plural form (quotas/{id}/, not
quota/{id}/).
If pretix cannot do the thing: implement the subset that exists and add the gap to "Known limits" in the README. Never scrape the UI, use an admin session, or call an undocumented endpoint.
2. Write the function
@tool("read")
async def list_quotas(app: App, event: str, limit: int = 50) -> dict:
"""First line is what the model sees when deciding whether to call this.
Say what it does not do, and name the better tool when there is one. This docstring is
the tool description — it is the only documentation the agent gets.
"""
quotas, total, truncated = await app.pretix.paginate(
"events", app.check_event(event), "quotas", cap=page_size(limit)
)
return listing([pick(q, "id", "name", "size") for q in quotas], total=total, truncated=truncated)
- First parameter is always
app: App. Everything after it is agent-supplied and becomes JSON Schema from its annotation, so annotate concretely (str,int,bool,list[str],dict[str, Any],str | None = None). A default makes it optional. No*args/**kwargs. Return-> dict. - Name the event-slug parameter
event. The registry keys the event allowlist and the live-event guard on that exact name; any other name silently loses both. - Validate everything that becomes a path segment:
app.check_event(event)(validates and enforces the allowlist),object_id(value, field="quota_id"),order_code(code),page_size(limit). RaiseValidationErrorfor anything else malformed, before the request is built. - Never redact, audit, or check capabilities in a tool — the registry does all three.
- Reuse tools/_shared.py:
i18n()flattens pretix's{"en": ...}fields,pick()subsets an object,clean()dropsNoneso a PATCH only touches what the agent named,listing()gives lists a uniform shape. - Reject an empty update (
if not payload: raise ValidationError(...)) rather than sending a no-op PATCH. - Prices are decimal strings (
"23.00"). Annotate the parameterstrand list it in the decorator'smoney=(...)— the registry validates declared amounts throughvalidate.price()before a high-risk call is queued for approval, which a tool body cannot do because it does not run until after the approval. Sum withDecimal.
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 First seen · 118 lines · 69 tokens per session scan A 8e5ea0cb1b7f
add-pretix-tool is a skill published in the GitHub repository bitcoinaustria/pretix-agent-mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 69 tokens to every session and 1,482 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-telemetry
Catalog of OpenTelemetry instrumentation built into framework @cyanheads/mcp-ts-core — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up…
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.
api-services
API reference for built-in service providers (LLM, Speech, Graph). Use when looking up service interfaces, provider capabilities, or integration patterns.
cmdb-patterns
Create ServiceNow CIs and cmdbrelci relationships, walk upstream/downstream impact, detect orphan/stale CIs, and align discovered CIs with the proper sysclassname hierarchy.
csm-patterns
Build ServiceNow Customer Service Management — customeraccount, customercontact, sncustomerservicecase routing, service entitlements with usage decrement, and Customer Portal case submission widgets.