antigravity-agents: Agent for Claude Code

.agents/agents/researcher.md

researcher is an agent for Claude Code from rafaelghif/antigravity-agents. It costs 19 tokens per session (554 once invoked), scanned A, original, MIT.

A technical research agent for checking web sources, official documentation, and API details against the versions used by a project. An API is the documented way that software exposes functions or services to other software.

In plain words
What is it for?
Use it to inspect project dependency versions, find official documentation and specifications, and verify API claims with source links and version limits.
Why use it?
It reduces incorrect answers caused by outdated documentation, mismatched dependency versions, or unverified forum advice.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents; installed under .agents/ (shared by several agents).

This is rafaelghif/antigravity-agents's own configuration. It tells Claude Code how to work on antigravity-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything antigravity-agents configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/rafaelghif/antigravity-agents/main/.agents/agents/researcher.md
Clone the repo
git clone --depth 1 https://github.com/rafaelghif/antigravity-agents

Made for: Claude Code.

Wrote 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.

agentmods badge for researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/rafaelghif/antigravity-agents/researcher/github.svg)](https://agentmods.dev/agents/rafaelghif/antigravity-agents/researcher)
Your own site
<a href="https://agentmods.dev/agents/rafaelghif/antigravity-agents/researcher"><img src="https://agentmods.dev/badge/agents/rafaelghif/antigravity-agents/researcher/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.

agentmods 80×15 button for researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/rafaelghif/antigravity-agents/researcher"><img src="https://agentmods.dev/badge/agents/rafaelghif/antigravity-agents/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 554 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00554
Opus 5 $0.00010 $0.00277
Sonnet 5 $0.00004 $0.00111
Haiku 4.5 $0.00002 $0.00055

Measured 3d ago against content hash 5bc1c3292433, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

researcher 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 3d 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.

.agents/agents/researcher.md · 40 lines

What it actually says

<ANTI_HALLUCINATION_PROTOCOL> MANDATORY STEP 0 (RECONNAISSANCE BEFORE EXECUTION):

  1. Codebase Grounding: Run python3 scripts/grounding.py to identify installed dependency versions and framework constraints before searching.
  2. Reality Anchor: Match research queries to the exact major/minor versions found in the target project manifests.
  3. Official Source Prioritization: Strictly verify claims against official vendor documentation, RFC specifications, and official GitHub source code.
  4. Falsifiable Evidence: Always supply exact documentation URLs, signature snippets, and version constraints. Never assume unverified forum workarounds. </ANTI_HALLUCINATION_PROTOCOL>
Changes

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.

  1. 3d ago Changed · +3 lines 5bc1c3292433
  2. 4d ago First seen · 37 lines · 19 tokens per session scan A 51053255dfaf

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 554 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.

Related

Other agents, from other repositories

dev-builder

Expert development engineer that adds logic, state management, and API integrations. Delegate when: adding business logic, form validation, CRUD operations, API integration. SUPERPOWER: Give API doc URL + credentials → builds complete integration autonomously. Self-sufficient: analyzes code, reads external docs…

wasintoh/toh-framework · 68 tokens

design-reviewer

Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…

wasintoh/toh-framework · 85 tokens

platform-adapter

Doc-driven platform integration agent. Converts web apps to LINE MINI App (LIFF SDK), PWA (Next.js), and Capacitor (iOS/Android); Expo & Tauri are secondary/legacy. Delegate when: user requests LINE, mobile/app-store, or desktop app conversion. Always pulls current official docs before writing platform code — no…

wasintoh/toh-framework · 92 tokens

root-cause-debugger

Investigation specialist that finds and PROVES the root cause of a bug before any code is changed. Reads logs, error/stack traces, git diff/log of recent changes, and traces data flow with targeted logging. Delegate when a bug's cause is unknown, a fix keeps failing, or you need hard evidence before touching code.…

wasintoh/toh-framework · 90 tokens

stackhawk-security-onboarding

Automatically set up StackHawk security testing for your repository with generated configuration and GitHub Actions workflow.

archubbuck/workspace-architect · 25 tokens

frontend-impl

Use to implement frontend/UI code: components, pages, data fetching, forms, and client state. Follows accessibility and type-safety standards.

mnzralee/claude-multi-agent-architecture · 33 tokens