agentmods.dev

sutra: Instructions file for Codex

AGENTS.md

sutra AGENTS.md is an instructions file for Codex, OpenCode from 4rgon4ut/sutra. It costs 649 tokens per session, scanned A, original, MIT.

A set of contribution instructions for Sutra, a server that gives AI agents tools for reasoning, memory, and collaboration. It explains the project's architecture, coding standards, and journaling process.

In plain words
What is it for?
Use it when contributing to Sutra, especially when designing context, memory, or multi-agent features.
Why use it?
It gives contributors the project context they need before changing code. It also explains where new work belongs and how to document it.

Instructions file for CodexOpenCode

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

This is 4rgon4ut/sutra's own configuration. It tells Codex and OpenCode how to work on sutra 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 sutra configures →

not rated 0repo 10mo ago A scan 649 tokens original MIT
View source ↗ 4rgon4ut/sutra
Reuse

Borrowing it

Nothing to install: this file belongs to 4rgon4ut/sutra. 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/4rgon4ut/sutra/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/4rgon4ut/sutra

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 sutra AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/4rgon4ut/sutra/agents-md/github.svg)](https://agentmods.dev/instructions/4rgon4ut/sutra/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/4rgon4ut/sutra/agents-md"><img src="https://agentmods.dev/badge/instructions/4rgon4ut/sutra/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 sutra AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/4rgon4ut/sutra/agents-md"><img src="https://agentmods.dev/badge/instructions/4rgon4ut/sutra/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 649 This file is loaded in full into every session.
When invoked 649 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 $0.00649 $0.00649
Opus 5.5 $0.00260 $0.00260
Sonnet 5.5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured 2mo ago against content hash a45d6320d846, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sutra 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md: The Sutra Contribution Protocol

"The limit of your context is the limit of your world."

1. Mission Statement

You are entering Sutra, a Model Context Protocol (MCP) server dedicated to the science of Context Engineering. Your goal is not merely to write Python code, but to architect the "Operating System" for meaning, reasoning, and memory in Large Language Models.

We build primitives that allow agents to:

  1. Reason (Cognitive Tools/Thinking Models)
  2. Remember (Memory Cells/State)
  3. Collaborate (Organs/Multi-agent Systems)
  4. Resonate (Neural Fields/Continuous Semantics)

2. The Context Stack (Architecture)

All contributions must map to a specific layer of the Context Engineering Foundation. Do not introduce flat logic where structured context is required.

  • Layer 0: Atoms (/core/atoms.py): Raw instruction prompts.
  • Layer 1: Molecules (/core/molecules.py): Few-shot templates and CoT patterns.
  • Layer 2: Cells (/core/cells.py): Stateful memory protocols (JSON schemas + system prompts).
  • Layer 3: Organs (/systems/organs.py): Multi-agent orchestration blueprints.
  • Layer 4: Fields (/systems/fields.py): Mathematical models of semantic resonance and decay.
  • Layer 5: Cognitive (/cognitive/): Reasoning engines (IBM Tools, Symbolic Mechanisms).

3. Coding Standards (The Implementation)

  • Language: Python 3.10+
  • Framework: mcp (Model Context Protocol).
  • Style:
    • Type Hinting: Mandatory. Use typing heavily.
    • Docstrings: Google Style. Every prompt template must explain why it works based on foundation modules.
    • Modularity: One tool/resource per function. Do not create god-objects.

4. The Journaling Protocol

Memory is critical. You must maintain the Context Ledger.

  • File: .journal.md

  • Trigger: After every significant logical unit (feature complete, bug fix, refactor).

  • Format:

    ## [YYYY-MM-DD HH:MM] Feature Name
- **Intent**: What did we try to build?
- **Changes**: What files were touched?
- **Reasoning**: Why this approach? (Cite Module X)
- **State**: [Success/WIP/Failed]

Read the full file on GitHub · 59 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 · 59 lines · 649 tokens per session scan A a45d6320d846

Subscribe to this mod's changes

sutra AGENTS.md is an instructions file published in the GitHub repository 4rgon4ut/sutra (0 stars, last pushed 10mo ago), licensed MIT. It adds 649 tokens to every session, about $0.0026 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 2026-08-31.

Building agentsWriting and docs
Related

sutra AGENTS.md compared with instructions from other repositories

sutra AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sutra AGENTS.md4rgon4ut/sutraInstructions file010mo agoMITA649Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode