Borrowing it
Nothing to install: this file belongs to All3yp/omnisearch-mcp. 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/All3yp/omnisearch-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/All3yp/omnisearch-mcpWrote 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/all3yp/omnisearch-mcp/agents-md)<a href="https://agentmods.dev/instructions/all3yp/omnisearch-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/all3yp/omnisearch-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.01014 | $0.01014 |
| Opus 5 | $0.00507 | $0.00507 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
omnisearch-mcp AGENTS.md 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 5d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
omnisearch-mcp is a FastMCP server exposing tools for searching academic papers across multiple search providers (IEEE Xplore, arXiv, ACM, CrossRef, Semantic Scholar, CORE, Scite.ai, Consensus.app) and local PDF libraries.
MCP Consumer Skill
Agents that call this server must read .github/skills/omnisearch-mcp/SKILL.md (also mirrored at .claude/skills/omnisearch-mcp/SKILL.md for Claude Code). It defines the tool contract, result shape, provider limits, authentication recovery, IEEE pagination, and the responsibility of the calling agent to produce any required structured synthesis. Keep both copies in sync when editing.
Agent Usage & Error Recovery Protocol
1. How to Use MCP Tools
- Use
search_allto search all academic sources in parallel. - Use targeted tools (
search_ieee,search_scite,search_consensus,search_arxiv,search_pdf_library) for provider-specific queries.
2. What to do when Cookies / Auth Expire
If an MCP tool returns auth_required: true, expired-cookie text, IEEEKeyMissingError, 401 Unauthorized, 403 Forbidden, a login redirect, or HTML instead of JSON:
- Do NOT edit source code.
- Do NOT retry the same provider in a loop. Stop, report the auth block, and wait for human relogin.
- Ask the human to run the command returned by the tool's
commandfield. Defaults:- CAPES / IEEE (highest priority):
uv run omnisearch-capes-login(visible browser recommended; use--headlessonly if it is known to work) - Scite.ai:
uv run omnisearch-scite-login - Consensus.app:
uv run omnisearch-consensus-login
- CAPES / IEEE (highest priority):
- Wait until the login script reports success. The script persists browser state in
.omnisearch/sessions/and writes derived cookies to.env. - Retry the MCP tool once. If
auth_required: truepersists, stop and ask the human to relogin visibly/manual-complete MFA/CAPTCHA/SSO.
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.
- 5d ago First seen · 74 lines · 1,014 tokens per session scan A a1b23d127843
omnisearch-mcp AGENTS.md is an instructions file published in the GitHub repository All3yp/omnisearch-mcp (0 stars, last pushed 25d ago), licensed MIT. It adds 1,014 tokens to every session, about $0.0051 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 instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.