Borrowing it
Nothing to install: this file belongs to keta1930/icml2026-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/keta1930/icml2026-mcp/opensource/AGENTS.mdgit clone --depth 1 https://github.com/keta1930/icml2026-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/keta1930/icml2026-mcp/agents-md)<a href="https://agentmods.dev/instructions/keta1930/icml2026-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/keta1930/icml2026-mcp/agents-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/keta1930/icml2026-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/keta1930/icml2026-mcp/agents-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 | $0.00972 | $0.00972 |
| Opus 5 | $0.00486 | $0.00486 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
icml2026-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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Scope
This repository serves hybrid search over 6,341 ICML 2026 papers through six MCP tools. DashScope produces 1,024-dimensional embeddings. Milvus 2.5 stores the paper records and performs native COSINE and BM25 retrieval. Milvus combines both rankings with standard RRF. SQLite stores sessions, rate limits, provider-minute usage, and the query-embedding cache.
Package structure
src/icml_paper_search/
├── cli/ command-line entry point
├── corpus/ source-snapshot loading and catalog data
├── domain/ models and public errors
├── embeddings/ DashScope client
├── indexing/ Milvus collection builder and manifest
├── milvus/ schema and repository
├── runtime/ SQLite sessions, limits, quotas, and cache
├── search/ application service and output formatting
└── transport/ FastMCP and HTTP health routes
Dependencies flow from transport and cli toward search, then through domain-specific interfaces. Runtime state must not leak into the domain models. The Milvus SDK stays behind milvus/ and indexing/.
Retrieval
- Each query issues one dense COSINE request and one native BM25 request to the same Milvus collection.
- Combine the two rankings with
RRFRanker()and no weights. - Apply
area,paper_type, andspotlightfilters to both requests. - Search one fixed candidate window. Do not expand it automatically to fill a deduplicated result page.
- Keep the returned score in
[0, 1]. It is useful only for ordering one query. - Validate the current manifest, full paper-ID set, schema, BM25 function, and indexes without contacting DashScope.
Sessions and runtime state
- A request without
session_idis stateless. A session suppresses papers already returned or fetched within that capability. - Store only hashes of session IDs, client addresses, and queries.
- Commit session deduplication and returned papers in one SQLite transaction.
- Enforce session capacity, TTL, round count, seen-paper count, and output limits.
- Use the current SQLite schema only. A database with another schema must be rejected.
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.
- 8d ago First seen · 79 lines · 972 tokens per session scan A 1eb6710ff288
icml2026-mcp AGENTS.md is an instructions file published in the GitHub repository keta1930/icml2026-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 972 tokens to every session, about $0.0049 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.