Borrowing it
Nothing to install: this file belongs to yoloshii/gigaxity-deep-research. 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/yoloshii/gigaxity-deep-research/main/CLAUDE.mdgit clone --depth 1 https://github.com/yoloshii/gigaxity-deep-researchWrote 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/instructions/yoloshii/gigaxity-deep-research/claude-md)<a href="https://agentmods.dev/instructions/yoloshii/gigaxity-deep-research/claude-md"><img src="https://agentmods.dev/badge/instructions/yoloshii/gigaxity-deep-research/claude-md/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/instructions/yoloshii/gigaxity-deep-research/claude-md"><img src="https://agentmods.dev/badge/instructions/yoloshii/gigaxity-deep-research/claude-md.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 | $0.10438 | $0.10438 |
| Opus 5.5 | $0.04175 | $0.04175 |
| Sonnet 5.5 | $0.02088 | $0.02088 |
| Haiku 4.5 | $0.01044 | $0.01044 |
Grade A, and why
gigaxity-deep-research CLAUDE.md scanned grade A with 1 finding 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 27d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Empty results from `discover` / `synthesize` | SearXNG host unreachable | `curl $RESEARCH_SEARXNG_HOST/healthz` — should return 200. REST mode: `GET /api/v1/health/connectors` probes every connector at once | This is a copy
100% identical to gigaxity-deep-research AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gigaxity Deep Research — Agent Reference
This is the agent reference for Gigaxity Deep Research, an open-source deep research MCP server for Claude Code, Hermes, Cursor, and other MCP-compatible agents. Qwen3-30B-A3B-Thinking runs via OpenRouter, the Triple Stack search MCPs (Context7, Exa, Jina) handle web/docs/code retrieval, and the bundled research-workflow skill routes queries to the right tool per query class.
This file is loaded by Claude Code (CLAUDE.md) and other MCP-compatible agents (AGENTS.md is byte-identical). It documents how to operate the seven MCP tools this server exposes (three primitives plus four deep-research tools) and how to plug them into the broader deep research stack.
If your harness loads a global CLAUDE.md or AGENTS.md (Claude Code, Codex, Cursor, Hermes, etc.), copy the instruction block at the bottom of this file into that global file. For standalone agents that take a system prompt instead, paste the block directly into the system prompt. That single block makes any compatible agent automatically route research queries through this MCP plus the six companion MCPs (Context7, Exa, Exa Answer, Jina, Brightdata fallback, gptr-mcp) in the full deep research stack.
Tool surface
The MCP server exposes three primitives plus four deep-research tools — seven tools total. Pick a primitive when you want raw or combined behavior in one call; pick a deep-research tool when you want to drive discovery, synthesis, or reasoning as a discrete step.
Primitives
| Tool | Use for | Token cost (typical) |
|---|---|---|
mcp__gigaxity-deep-research__search |
Raw multi-source aggregation (SearXNG + Tavily + LinkUp + Brave + Parallel, RRF-fused), plus one SearXNG category lane (science / it / videos) chosen by focus_mode (general = none) or, without one, a keyword heuristic. No LLM call. |
0 LLM tokens; search-API quotas only |
mcp__gigaxity-deep-research__vertical_search |
One SearXNG category on its own: videos, science, it, docs, packages or general. Reports engines that failed on the call. No LLM call. |
0 LLM tokens; no search-API quota |
mcp__gigaxity-deep-research__research |
Combined search + synthesis with citations in a single call. The simple pipeline. | ~3000–8000 |
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.
- 27d ago Changed · +12 lines · +654 tokens per session 679ec6392b24
- 1mo ago First seen · 472 lines · 9,784 tokens per session scan A 0ab6fb762f97
gigaxity-deep-research CLAUDE.md is an instructions file published in the GitHub repository yoloshii/gigaxity-deep-research (63 stars, last pushed 28d ago), licensed MIT. It adds 10,438 tokens to every session, about $0.0418 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to gigaxity-deep-research AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.