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 GalaxyRuler/Galactic-skills --skill research-groundinggit clone --depth 1 https://github.com/GalaxyRuler/Galactic-skillsWrote 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/galaxyruler/galactic-skills/research-grounding)<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/research-grounding"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/research-grounding/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/galaxyruler/galactic-skills/research-grounding"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/research-grounding.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 | $0.00083 | $0.00591 |
| Opus 5 | $0.00042 | $0.00296 |
| Sonnet 5 | $0.00017 | $0.00118 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
research-grounding 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 10d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Grounding
Overview
Recommendations, comparisons, version facts, prices, and benchmarks drift; training data lags reality. Before presenting any such claim as solid, verify it with a current web search and cite the source. This is a standing, repeatedly-stated user requirement across projects — not optional polish.
When to use
- Recommending or ranking tools, libraries, models, services, or approaches
- "Best", "latest", "cheapest", "fastest", "state-of-the-art" claims
- Version numbers, release status, deprecations, API/SDK shapes
- Cost / pricing / quota / token-spend estimates
- Proposing a plan or architecture the user will act on
- Any external fact that could have changed since training
- User asks: "is this grounded?", "are your suggestions online-search grounded?"
When NOT: pure reasoning about the user's own code/files, clearly-labeled opinion, or facts the user just supplied.
Workflow
- Before asserting, list the claims that could be stale.
- Search for each — WebSearch for general facts/prices/benchmarks; Context7 for library/SDK/API docs.
- Cite sources inline (name + link). Prefer official/primary sources; check the page date.
- State assumptions explicitly. Label anything you could NOT verify as unverified.
- Only then present the recommendation/plan as "solid."
Red flags — STOP, search first
- About to say "best / latest / cheapest / state-of-the-art" with no citation
- Quoting a price, version, model name, or benchmark from memory
- A plan hinges on an external tool's current capabilities
- Thinking "I'm pretty sure this is still true"
Rationalizations — all wrong
| Excuse | Reality |
|---|---|
| "I already know this" | Training lags; verify anyway. |
| "Searching is slower" | A wrong recommendation costs far more rework. |
| "It probably hasn't changed" | Prices, models, and APIs change monthly. Check. |
| "User is in a hurry" | Ground at least the load-bearing claims. |
Common mistakes
- Citing a source without reading its date (stale page).
- Grounding the easy claims, asserting the hard ones from memory.
- Burying assumptions instead of stating them up front.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 53 lines · 83 tokens per session scan A 6bd3c482556d
research-grounding is a skill published in the GitHub repository GalaxyRuler/Galactic-skills (5 stars, last pushed 5d ago), licensed MIT. It adds 83 tokens to every session and 591 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 2026-08-31.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…