agentmods.dev

srchd: Instructions file for Codex

AGENTS.md

srchd AGENTS.md is an instructions file for Codex, OpenCode from dust-tt/srchd. It costs 1,130 tokens per session, scanned A, original, MIT.

Project instructions documenting the architecture, requirements, commands, database, and main components of the `srchd` application.

In plain words
What is it for?
Use it when working on `srchd`, including its AI-agent publication and review workflow, SQLite database, migrations, type checks, and linting.
Why use it?
It gives coding agents the project context and the approved commands they need to make changes without guessing how the system is organised.

Instructions file for CodexOpenCode

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

This is dust-tt/srchd's own configuration. It tells Codex and OpenCode how to work on srchd 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 srchd configures →

not rated 100repo 15d ago A scan 1,130 tokens original MIT
View source ↗ dust-tt/srchd
Reuse

Borrowing it

Nothing to install: this file belongs to dust-tt/srchd. 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/dust-tt/srchd/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dust-tt/srchd

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 srchd AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dust-tt/srchd/agents-md"><img src="https://agentmods.dev/badge/instructions/dust-tt/srchd/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,130 This file is loaded in full into every session.
When invoked 1,130 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 $0.01130 $0.01130
Opus 5.5 $0.00452 $0.00452
Sonnet 5.5 $0.00226 $0.00226
Haiku 4.5 $0.00113 $0.00113

Measured 2mo ago against content hash 2c5507fbfe06, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

srchd 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 2mo 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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Architecture Documentation

Requirements

  • Node.js: v24.15+ required
    • On macOS with Homebrew: export PATH="/opt/homebrew/opt/node@24/bin:$PATH"

Commands

  • Run CLI: npx tsx src/srchd.ts
  • Type checking: npm run typecheck
  • Linting: npm run lint
  • Database migrations: npx drizzle-kit generate && npx drizzle-kit migrate

Architecture Overview

srchd orchestrates AI agents through a publication/review system. Agents collaborate to solve complex problems by publishing papers, reviewing each other's work, and citing relevant publications.

Core Components

Database Layer (src/db/)

ORM: Drizzle ORM with SQLite backend (./db.sqlite)

Schema Entities:

  • experiments - Experiment metadata with unique names and problem statements
  • agents - AI agents with model, provider, thinking config, and tools
  • evolutions - System prompt evolution history for self-improvement
  • messages - Agent conversation history with position tracking
  • publications - Research papers with status (SUBMITTED/PUBLISHED/REJECTED)
  • citations - Citation relationships between publications
  • reviews - Peer reviews with grades (STRONG_ACCEPT/ACCEPT/REJECT/STRONG_REJECT)
  • solutions - Tracked solutions with reasoning and publication references
  • token_usages - Token usage tracking for cost monitoring

Key Data Relationships:

  • Experiments contain multiple agents
  • Agents have memories and can author publications
  • Publications can cite other publications within experiments
  • Publications undergo peer review by agents
  • All entities maintain created/updated timestamps

CLI Interface (src/srchd.ts)

Built with Commander.js, provides commands for:

  • Experiment management (create, list, metrics)
  • Agent management (create, list, evolve, run)
  • Computer image building
  • Web UI server

Agent Profile System (src/agent_profile.ts)

Profiles define pre-configured agent types in agents/<profile-name>/:

  • prompt.md - System prompt defining behavior and objectives
  • settings.json - Tools, environment variables, Docker image name
  • Dockerfile (optional) - Custom Docker environment for computer-use agents

Read the full file on GitHub · 134 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. 2mo ago First seen · 134 lines · 1,130 tokens per session scan A 2c5507fbfe06

Subscribe to this mod's changes

srchd AGENTS.md is an instructions file published in the GitHub repository dust-tt/srchd (100 stars, last pushed 15d ago), licensed MIT. It adds 1,130 tokens to every session, about $0.0045 per session on Opus 5.5. 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.

Related

srchd AGENTS.md compared with instructions from other repositories

srchd AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
srchd AGENTS.mddust-tt/srchdInstructions file10015d agoMITA1,130Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode