Borrowing it
Nothing to install: this file belongs to rafaelghif/antigravity-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rafaelghif/antigravity-agents/main/.agents/skills/deep-research/SKILL.mdgit clone --depth 1 https://github.com/rafaelghif/antigravity-agentsWrote 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/rafaelghif/antigravity-agents/deep-research)<a href="https://agentmods.dev/skills/rafaelghif/antigravity-agents/deep-research"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/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/rafaelghif/antigravity-agents/deep-research"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/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 | $0.00027 | $0.00926 |
| Opus 5 | $0.00014 | $0.00463 |
| Sonnet 5 | $0.00005 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00093 |
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 2d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research & External Grounding Protocol
Role: Principal Technical Researcher & Epistemic Grounding Specialist.
Overview & Trigger Conditions
Activate this skill when encountering unfamiliar libraries, framework migrations, external APIs, deprecation notices, or complex system errors. Agents MUST NEVER guess, hallucinate, or assume method signatures, configuration keys, or interface types.
Trigger Scenarios & Keywords:
- External API lookups, framework documentation, SDK migration guides, RFC references.
- Keywords:
research,search web,browse,documentation,docs,lookup,rfc,investigate,latest version,official guide,api reference.
Core Standards & Invariants
-
Anti-Hallucination Baseline:
- Zero invention: never guess non-existent function arguments, CLI flags, package exports, or configuration properties.
- If an API or feature cannot be confirmed via official documentation or local code inspection, explicitly label it
UNKNOWN / UNVERIFIED.
-
Official Source Hierarchy:
- Tier 1 (Authoritative): Official language and package documentation (
docs.python.org,pkg.go.dev,developer.mozilla.org,crates.io,docs.rs). - Tier 2 (Vendor & Standards): Official vendor documentation, RFC specifications, GitHub release notes, and library migration guides.
- Tier 3 (Secondary): Community forums and blog posts (must always be verified against Tier 1/2 official documentation).
- Tier 1 (Authoritative): Official language and package documentation (
-
Reconciliation with Local Codebase (
scripts/grounding.py):- Always cross-reference external documentation with the actual installed versions in the repository (
package.json,pyproject.toml,Cargo.toml,go.mod). - Never adopt newer syntax or APIs that are incompatible with the repository's pinned dependencies or runtime versions.
- Always cross-reference external documentation with the actual installed versions in the repository (
The 3-Step External Grounding Loop
- Targeted Web Search (
search_web):- Formulate precise, high-density queries including language, library version, and exact error/method name:
- Good:
"pydantic v2 model_validate JSON schema migration guide" - Bad:
"how to fix python error"
- Good:
- Formulate precise, high-density queries including language, library version, and exact error/method name:
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.
- 2d ago Changed c6f1180c1032
- 4d ago Changed · +33 lines · +5 tokens per session 938bf05520ee
- 5d ago First seen · 39 lines · 22 tokens per session scan A 7ed84e33c73d
deep-research is a skill published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 926 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
cicd
Automated CI/CD pipeline scaffolding, multi-job quality gates, Dependabot smart auto-merge, and CD release workflows for projects in PARA workspace.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
agentic-actions-auditor
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.
deployment-pipeline-design
Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use when architecting deployment workflows, setting up continuous delivery, or implementing GitOps practices.