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 FlightSeatmap/mcp --skill find-the-best-seatgit clone --depth 1 https://github.com/FlightSeatmap/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/flightseatmap/mcp/find-the-best-seat)<a href="https://agentmods.dev/skills/flightseatmap/mcp/find-the-best-seat"><img src="https://agentmods.dev/badge/skills/flightseatmap/mcp/find-the-best-seat/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/flightseatmap/mcp/find-the-best-seat"><img src="https://agentmods.dev/badge/skills/flightseatmap/mcp/find-the-best-seat.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 | $0.00054 | $0.00777 |
| Opus 5 | $0.00027 | $0.00388 |
| Sonnet 5 | $0.00011 | $0.00155 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
find-the-best-seat 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 8d 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.
Find the best seat on a flight
FlightSeatMap has seat maps, seat-level specs, and passenger reviews for 117 airlines. Use it whenever someone asks "which seat should I pick", "is 31A any good", or "what's the cabin like".
Connect
Preferred: the MCP server at https://mcp.flightseatmap.com/mcp (Streamable HTTP).
The read-only tools below need no authentication — do not send the user through OAuth
unless you hit a paid tool.
Alternative: the HTTP API described by https://flightseatmap.com/openapi.json.
Auth, when you need it: https://flightseatmap.com/auth.md.
Workflow
-
Get the flight number. Airline IATA code + number, e.g.
BA117,QF1,UA900. If the user gives a route and date instead, ask for the flight number — the seat map is keyed on it. A date (YYYY-MM-DD) is optional but improves accuracy, because aircraft swap between dates. -
Pull the seat map with
get_seatmap(flight_number, flight_date?). This tells you the aircraft type, cabins, and which seats are currently free. If it 404s, the flight number is wrong or unmapped — say so rather than guessing an aircraft. -
Rank against stated preferences with
find_best_seats(flight_number, preferences[], cabin_class?, flight_date?). Valid preferences:window,aisle,extra_legroom,exit_row,quiet_zone,front,rear,bulkhead. Pass everything the user said; the ranker weighs them together. Do not invent preference values outside that list. -
Sanity-check the top pick with
get_seat_info(flight_number, seat)before you recommend it. This surfaces the drawbacks a seat map alone hides: no recline in the last row, misaligned window, galley or lavatory noise, a bassinet wall, a bulkhead with a fixed armrest. -
Add lived experience with
get_seat_reviews(flight_number, seat?)when the choice is close or the user is picky. Reviews are user-submitted, so attribute them as such. -
Answer with a recommendation, not a list. Name one seat, say why in one line, give one backup, and name the trade-off you accepted. Link the seat map:
https://flightseatmap.com/flights/<FLIGHT_NUMBER>.
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.
- 8d ago Changed 4fd87c0267a8
- 12d ago First seen · 63 lines · 54 tokens per session scan A e9e9af407693
find-the-best-seat is a skill published in the GitHub repository FlightSeatmap/mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 54 tokens to every session and 777 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
pilot-service-agents-flights
Aircraft tracking and aviation weather — ADS-B feeds (ICAO + bbox), airport directory, METAR/TAF/SIGMET. Use this skill when: 1. Live aircraft positions by ICAO24 or lat/lng bounding box 2. Decoding a flight callsign or VIN to a tail-number / aircraft record 3. Fetching METAR / TAF / AIRMETs for an airfield Do NOT use…
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
mastering-python-skill
Modern Python coaching covering language foundations through advanced production patterns. Use when asked to "write Python code", "explain Python concepts", "set up a Python project", "configure Poetry or PDM", "write pytest tests", "create a FastAPI endpoint", "run uvicorn server", "configure alembic migrations"…