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 airvalona/antigravity-like-claude-code --skill deep-researchgit clone --depth 1 https://github.com/airvalona/antigravity-like-claude-codeWrote 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/airvalona/antigravity-like-claude-code/deep-research)<a href="https://agentmods.dev/skills/airvalona/antigravity-like-claude-code/deep-research"><img src="https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/deep-research/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/airvalona/antigravity-like-claude-code/deep-research"><img src="https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/deep-research.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 | $0.00068 | $0.00422 |
| Opus 5 | $0.00034 | $0.00211 |
| Sonnet 5 | $0.00014 | $0.00084 |
| Haiku 4.5 | $0.00007 | $0.00042 |
Grade A, and why
deep-research 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 9d 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.
What it actually says
/deep-research — Multi-Step Research Workflow
Port of Claude Code's bundled deep-research skill.
When to use
Broad or multi-part questions, comparisons, or anything where a single search would only give a surface-level answer — not simple factual lookups.
Steps
-
Break the topic into sub-questions. Before searching, list the distinct angles that need covering (e.g. for "should we migrate to X", that's: what X is, current adoption/maturity, migration cost, comparison to current stack, known pitfalls).
-
Search each angle separately. Don't combine multiple sub-questions into one search query — it returns shallow results for all of them. Use short, specific queries (2-6 words), starting broad and narrowing based on results.
-
Follow up on gaps. After the first pass, check which sub-questions are still thin and search again with reformulated queries or more specific terms.
-
Prefer primary sources (official docs, source repos, original announcements) over aggregator/blog summaries when both are available.
-
Synthesize, don't just list. The final answer should be organized around the sub-questions, not around which search produced which fact. Note where sources disagree rather than silently picking one.
-
Cite sources by name/link so the user can verify anything load-bearing.
Notes
Scale the number of searches to the complexity of the question — a handful for a medium comparison, more for something genuinely open-ended. Stop once every sub-question is actually grounded in something retrieved, not just plausible.
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.
- 9d ago First seen · 41 lines · 68 tokens per session scan A 1ac12a1a6a83
deep-research is a skill published in the GitHub repository airvalona/antigravity-like-claude-code (2 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 422 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
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…