Galaxium Travels is a demo full-stack application for booking trips between planets and moons. It models an enterprise-style booking system with multiple services, including searching routes, reserving seats, and completing or cancelling bookings.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/IBM/galaxium-travelsnpx agentmods add skills/ibm/galaxium-travels/verifyWrote 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/ibm/galaxium-travels/verify)<a href="https://agentmods.dev/skills/ibm/galaxium-travels/verify"><img src="https://agentmods.dev/badge/skills/ibm/galaxium-travels/verify/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/ibm/galaxium-travels/verify"><img src="https://agentmods.dev/badge/skills/ibm/galaxium-travels/verify.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 | $0.00085 | $0.02544 |
| Opus 5.5 | $0.00034 | $0.01018 |
| Sonnet 5.5 | $0.00017 | $0.00509 |
| Haiku 4.5 | $0.00009 | $0.00254 |
Grade A, and why
verify 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 2mo 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Skill
Run the appropriate test suites for the galaxium-travels repo. Always execute commands directly — do not just describe what to run.
Tiers
| Tier | Suites | Approx. time | When to use |
|---|---|---|---|
| fast (default) | backend pytest + frontend ESLint | ~15 s | Any verify/validate/test request without further qualification |
| standard | fast + Java unit tests | ~1 min | User says "standard", "including Java", "all unit tests", or Java files changed |
| e2e | standard + native e2e (no Docker) | ~3–5 min | User explicitly asks for e2e, integration, or cross-service testing |
| full e2e | e2e + slow auto-expiry test | ~5–6 min | User explicitly says "full e2e", "including slow", or asks about hold expiry |
Step 1 — Determine tier
Read the user's request:
- Default to fast unless the user mentions Java, all-unit, standard, e2e, integration, cross-service, hold expiry, slow, or full.
- Upgrade to standard if the user mentions Java unit tests, all unit tests, or standard.
- Upgrade to e2e if the user mentions e2e, end-to-end, integration tests, or cross-service.
- Upgrade to full e2e only if the user explicitly mentions slow tests, full e2e, or hold auto-expiry.
Step 2 — Detect changed files (git-aware skipping)
Run:
git diff --name-only HEAD 2>/dev/null || git diff --name-only
Parse the output to determine which components have changes:
- Python backend changed: any file under
booking_system_backend/ - Java service changed: any file under
booking_system_inventory_hold_service/ - Frontend changed: any file under
booking_system_frontend/ - e2e changed: any file under
e2e/ - No output / untracked only / clean tree: treat all components as changed (run everything in the selected tier)
If git diff returns nothing (e.g. clean working tree with no staged changes), also try:
git diff --name-only HEAD~1 HEAD 2>/dev/null
If that also returns nothing, assume all components may be affected.
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.
- 2mo ago First seen · 205 lines · 85 tokens per session scan A e831101d4b14
verify is a skill published in the GitHub repository IBM/galaxium-travels (60 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 2,544 once invoked, about $0.0003 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.