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 IBM/galaxium-travels --skill grill-and-sharegit clone --depth 1 https://github.com/IBM/galaxium-travelsWrote 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/grill-and-share)<a href="https://agentmods.dev/skills/ibm/galaxium-travels/grill-and-share"><img src="https://agentmods.dev/badge/skills/ibm/galaxium-travels/grill-and-share/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/grill-and-share"><img src="https://agentmods.dev/badge/skills/ibm/galaxium-travels/grill-and-share.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 | $0.00077 | $0.01042 |
| Opus 5 | $0.00039 | $0.00521 |
| Sonnet 5 | $0.00015 | $0.00208 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
grill-and-share 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 13d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill and Share
You are running a focused planning review. The goal is: ask a few sharp questions, reach a clear shared understanding, then produce polished HTML and Markdown planning documents and (if a GitHub issue is available) post them as a comment.
Step order matters for live demos: produce the Markdown first (fast), confirm and post to GitHub, then generate the HTML artifact last (slow).
Step 1 — Gather the Input
Check what the user has provided. Accept any of the following as input:
- A pasted plan or description in the conversation
- A GitHub issue number or URL (e.g.
#42orhttps://github.com/owner/repo/issues/42) - A reference to an existing plan document
If a GitHub issue number/URL was given, fetch its body now:
gh issue view <number> --json title,body --jq '"# " + .title + "\n\n" + .body'
Use the fetched content as the plan to review. If no input is provided at all, ask the user for one before continuing.
Step 2 — Ask Up to 3 Questions
Identify the three most important gaps or risks in the plan. Ask them one at a time using ask_followup_question, waiting for each answer before continuing. Do not exceed three questions total.
For each question:
- Provide your recommended answer as the first suggestion
- Keep it tight and decision-forcing — no open-ended "tell me more" questions
- If the answer can be determined by exploring the codebase, do that instead of asking
After all questions are answered, summarise the updated understanding in one short paragraph (2–4 sentences). Show it to the user and confirm they are happy before proceeding.
Step 3 — Markdown Document
Use write_file to save a Markdown version on the project root:
Where <plan-slug> is a kebab-case slug of the plan title (e.g. checkout-flow-plan.md).
If the user provided a markdown file, don't overwrite it. Create a new version with a scripted title in the same location.
Structure the Markdown with: title, summary, key decisions table (Decision | Choice | Rationale), open items (bullet list), next steps (ordered list).
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.
- 13d ago First seen · 106 lines · 77 tokens per session scan A 07fadfdde9ca
grill-and-share is a skill published in the GitHub repository IBM/galaxium-travels (53 stars, last pushed 16d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,042 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…