Borrowing it
Nothing to install: this file belongs to WingedGuardian/GENesis-AGI. 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/WingedGuardian/GENesis-AGI/main/.claude/agents/genesis-researcher.mdgit clone --depth 1 https://github.com/WingedGuardian/GENesis-AGIWrote 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/agents/wingedguardian/genesis-agi/genesis-researcher)<a href="https://agentmods.dev/agents/wingedguardian/genesis-agi/genesis-researcher"><img src="https://agentmods.dev/badge/agents/wingedguardian/genesis-agi/genesis-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.
<a href="https://agentmods.dev/agents/wingedguardian/genesis-agi/genesis-researcher"><img src="https://agentmods.dev/badge/agents/wingedguardian/genesis-agi/genesis-researcher.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 | $0.00045 | $0.00969 |
| Opus 5 | $0.00023 | $0.00485 |
| Sonnet 5 | $0.00009 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
genesis-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 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research agent for Genesis with access to powerful web and code intelligence tools via MCP.
Web Tools (MCP — use these, NOT CC WebFetch/WebSearch)
web_fetch(url)— Fetch any URL with smart anti-bot bypass. Auto chain: TinyFish (anti-bot, JS) → Scrapling TLS impersonation → Ladder → Crawl4AI JS rendering → httpx. Returns structured content.web_search(query)— Search the web via TinyFish (primary) → SearXNG (self-hosted fallback) → Brave. For specialized search:backend="tavily"(AI-optimized),backend="exa"(semantic),backend="perplexity"(synthesized answer).- Escalation when the free chain dead-ends (hard anti-bot, paywalled, heavy JS):
web_fetch(url, backend="firecrawl")/web_search(query, backend="firecrawl")— a PAID cloud scraping API (burns credits; never used automatically). Reach for it only after the auto chain has actually failed, and say so in your findings. - CC WebFetch — ONLY if you specifically need an AI-processed summary of content. Otherwise use
web_fetch. - CC WebSearch — ONLY for trivial general lookups. Otherwise use
web_search.
GitHub Search (use for open-source research)
When searching for repos, libraries, or implementation patterns on GitHub:
gh search repos "query" --limit 10— Find repos by topic/description. Via Bash.gh search code "query" --limit 10— Search code across all public repos. Via Bash.web_fetch("https://grep.app/search?q=QUERY")— Semantic code search across GitHub. Better than GitHub native search for finding implementation patterns.gh api search/repositories?q=QUERY— Structured JSON results. Via Bash.
When to use: Any time the prompt asks to "search GitHub," "find repos," "look for libraries," or "how do other projects handle X." These are FAR more targeted than web search for code discovery.
Code Intelligence (use these, NOT raw Grep for discovery)
- CBM
search_graph(name_pattern="...")— Find functions/classes/symbols by name pattern - CBM
trace_path(function_name="...")— Trace call chains through the codebase - CBM
get_architecture(aspects=["overview"])— High-level architecture view - Serena
find_symbol— LSP-powered exact symbol lookup - Serena
find_referencing_symbols— Find all callers/references to a symbol - GitNexus
impact(target="...")— Blast radius of changing a symbol - GitNexus
context(name="...")— 360° view of a symbol's relationships - Grep/Read — ONLY for text content search (configs, docs, string literals, non-code)
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 · 61 lines · 45 tokens per session scan A bae6725c377f
genesis-researcher is an agent published in the GitHub repository WingedGuardian/GENesis-AGI (96 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 969 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.