agentmods.dev

autoresearch-mcp: Instructions file for Codex

AGENTS.md

autoresearch-mcp AGENTS.md is an instructions file for Codex, OpenCode from ShreeMulay/autoresearch-mcp. It costs 524 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for autoresearch-mcp, an MCP server for finding research techniques, creating experiments, tracking results, and running optimization loops. It documents the project’s architecture and coding conventions.

In plain words
What is it for?
It is for guiding development of autoresearch-mcp. It covers its TypeScript and Bun setup, SQLite search catalog, experiment schemas, tool naming, and trust levels for actions.
Why use it?
It gives a coding agent the project context and rules needed to make consistent changes. Without it, the agent may misunderstand the server’s design or workflow.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is ShreeMulay/autoresearch-mcp's own configuration. It tells Codex and OpenCode how to work on autoresearch-mcp 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 autoresearch-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/dev/ai_projects/scripts/export_beads_preserving_history.py.

not rated 0repo changed 4d ago A scan 524 tokens original Apache-2.0
View source ↗ ShreeMulay/autoresearch-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to ShreeMulay/autoresearch-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.

Copy the file
curl -O https://raw.githubusercontent.com/ShreeMulay/autoresearch-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ShreeMulay/autoresearch-mcp

Made for: Codex, OpenCode.

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 autoresearch-mcp AGENTS.md

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

agentmods 80×15 button for autoresearch-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shreemulay/autoresearch-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/shreemulay/autoresearch-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 524 This file is loaded in full into every session.
When invoked 524 The same file — it is already loaded in full.
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 $0.00524 $0.00524
Opus 5 $0.00262 $0.00262
Sonnet 5 $0.00105 $0.00105
Haiku 4.5 $0.00052 $0.00052

Measured 4d ago against content hash 8c2eb7988678, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autoresearch-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 4d 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.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autoresearch-mcp

Architecture

  • Runtime: Bun
  • Language: TypeScript (strict)
  • MCP SDK: @modelcontextprotocol/sdk (Stdio transport MVP)
  • Database: bun:sqlite + FTS5
  • Validation: Zod
  • Catalog: YAML source of truth → SQLite + FTS5 for search

Conventions

  • Tool names: snake_case
  • Resource URIs: autoresearch://category/item
  • Catalog YAML: one file per technique in catalog/{layer}/
  • Templates: organized by recipe in catalog/templates/{recipe}/
  • All experiment data models include cost tracking (tokens, dollars, wall time)

Validation CI

  • .forgejo/workflows/ci.yml is the active PR-only validation workflow.
  • Branch protection requires only its terminal ci job; that job fails unless the bun, node22, node24, and canonical package_smoke jobs all succeed.
  • Do not reintroduce Woodpecker validation or add push, default-branch, manual, publication, deployment, secret-bearing, or provider-calling triggers to this workflow.

Beads Safety

  • Use exactly bd 0.43.0 (dev) with BEADS_NO_DAEMON=1, an external database, and both auto-flush and auto-import disabled.
  • Infer the canonical issue prefix read-only from the existing ledger; never invent or change it.
  • Export mutations only through /home/dev/ai_projects/scripts/export_beads_preserving_history.py with its required safeguards.
  • Never hand-edit .beads or run raw bd sync.

Landing

  • Run the repository's applicable validation before committing and pushing the existing branch.
  • Open a Forgejo pull request and require Forgejo Actions CI / ci (pull_request) to pass for the exact pushed HEAD.
  • Merge only through the protected path after that exact-head check is green; never bypass branch protection.
  • Oracle input, when used, is advisory and never an approval gate.

Observability

  • Follow /home/dev/tke-observability-standard/STANDARD.md, observe.contract.yaml, and the TypeScript/Bun template before changing telemetry; do not re-derive the standard here.
  • Keep telemetry PHI-free and secret-free. Never emit raw requests, responses, prompts, model output, identifiers, or unsanitized exceptions.
  • Validate endpoint normalization, header parsing, redaction, and safe telemetry behavior before merge.

Read the full file on GitHub · 42 lines

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. 4d ago Changed · -70 lines · -718 tokens per session 8c2eb7988678
  2. 9d ago First seen · 112 lines · 1,242 tokens per session scan A dbf0ef8ec38d

Subscribe to this mod's changes

autoresearch-mcp AGENTS.md is an instructions file published in the GitHub repository ShreeMulay/autoresearch-mcp (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 524 tokens to every session, about $0.0026 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.

ResearchScientific
Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens