data-sources

A set of coding rules for retrieving and combining travel data from outside services. It covers how to clean incoming data, handle partial failures, and keep different kinds of identifiers and prices distinct.

In plain words
What is it for?
Use it when building travel search and booking features that combine hotels, flights, and ground transport.
Why use it?
It prevents incorrect trip results caused by mixing data formats, using the wrong identifiers, hiding failed searches, or caching expired prices and availability.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/evilfreelancer/zaezd/data-sources
Clone the repo
git clone --depth 1 https://github.com/EvilFreelancer/zaezd

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,429 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01429
Opus 5 $0.00000 $0.00714
Sonnet 5 $0.00000 $0.00286
Haiku 4.5 $0.00000 $0.00143

Measured yesterday against content hash a0da04d44ae0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-sources 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 yesterday.

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.

.cursor/rules/data-sources.mdc · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data sources: clients, normalization, degradation

src/sources/ speaks protocol and normalizes; src/enrich/ adds optional context. Raw third-party JSON stops at this boundary: above it only domain types travel. Full reference in specs/03-istochniki.md and ideas/01-tutu-mcp-obzor.md.

Traps that were measured, not guessed

  • Hotel geo_id and transport geo_id are different namespaces. A hotel id may only come from a previous search_hotels response (meta.geo_id / meta.resolved_geo). Passing a transport id yields an empty hotels[] next to perfectly live transport.
  • Hotel price is the whole stay (price_basis: "stay_total"). Never per night.
  • search_multitransport fails softly per mode. An empty array for one mode while the others are populated is a partial failure. Log it; never report "there are no flights".
  • Multitransport counts adults only. Children require the per-mode searches, which the MVP does not do. Say so in the limitations, do not silently drop passengers.
  • Ground transport takes a city, not a station, even though the response names the station.
  • checkout_ref, search_id, availability and prices expire. They are never cached and never stored in a snapshot; checkout links are rebuilt live at click time.
  • confcal requires a session. mcp-session-id comes from initialize and is required afterwards; it dies with the process. Re-initialize once automatically on a session error and retry the call. Keep concurrency at one until parallel calls through one session are proven safe. Never mix confcal headers into the Tutu client, which has no session at all.
  • confcal has no coordinates. venue is free text ("РУДН, Москва", "YADRO", null). Geocoding is mandatory and will fail often; falling back to the city centre is a normal mode of operation, not an exception.
  • starts_at may be null. Then only the date is known and feasibility relaxes.
  • confcal has no event end time at all. The field set is id, title, url, start_date, end_date, starts_at, city, city_slug, venue, format, is_free, price, topics, tags, program_url, description. The check-out day is therefore always end_date plus one.
  • OSRM must run the foot profile. The public router.project-osrm.org serves the car profile only; measured on one pair of points in Kazan it answered 269 s where routing.openstreetmap.de/routed-foot answered 847 s on the same pair. Labelling a car route "N мин пешком" is a lie. Use the foot profile, and when it is unavailable show no walking time at all.
  • Tutu responses arrive as a JSON string inside a text block, with no outputSchema. Parse in one place, in normalize.ts.

Read the full file on GitHub · 107 lines

Changes

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.

  1. yesterday First seen · 107 lines · 0 tokens per session scan A a0da04d44ae0

Subscribe to this mod's changes

data-sources is a cursor rule published in the GitHub repository EvilFreelancer/zaezd (1 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,429 tokens. 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.