NoizuPromptLingo: Instructions file for Codex

AGENTS.md

NoizuPromptLingo AGENTS.md is an instructions file for Codex, OpenCode from noizu-labs-ml/NoizuPromptLingo. It costs 3,123 tokens per session, scanned A, original, MIT.

Repository instructions for starting and organizing work sessions in NoizuPromptLingo. A session is a tracked unit of agent work, and the instructions require creating one before other actions, either directly for a clear task or first as an exploratory session.

In plain words
What is it for?
Use them to initialize agent sessions, create child sessions for deferred tasks, and follow the repository's required startup sequence.
Why use it?
They ensure every conversation has a project, task, and agent context before work begins. They also provide a way to keep unclear exploration separate from later concrete tasks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

This is noizu-labs-ml/NoizuPromptLingo's own configuration. It tells Codex and OpenCode how to work on NoizuPromptLingo 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 NoizuPromptLingo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. 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/noizu-labs-ml/NoizuPromptLingo/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingo

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 NoizuPromptLingo AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/noizu-labs-ml/noizupromptlingo/agents-md/github.svg)](https://agentmods.dev/instructions/noizu-labs-ml/noizupromptlingo/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/noizu-labs-ml/noizupromptlingo/agents-md"><img src="https://agentmods.dev/badge/instructions/noizu-labs-ml/noizupromptlingo/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 NoizuPromptLingo AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/noizu-labs-ml/noizupromptlingo/agents-md"><img src="https://agentmods.dev/badge/instructions/noizu-labs-ml/noizupromptlingo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,123 This file is loaded in full into every session.
When invoked 3,123 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 $0.03123 $0.03123
Opus 5.5 $0.01249 $0.01249
Sonnet 5.5 $0.00625 $0.00625
Haiku 4.5 $0.00312 $0.00312

Measured 1mo ago against content hash 5fb381a4741f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

NoizuPromptLingo 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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.


Session Initialization (MANDATORY — DO THIS FIRST)

BLOCKING REQUIREMENT: Before doing ANY work — before reading files, answering questions, or executing tasks — you MUST generate a session. No exceptions. This is the absolute first action in every conversation.

The $NPL_PROJECT environment variable MUST be set.

Single-Call Session Init

If the task is already clear from the user's first message, create a task session directly — no separate root session needed:

ToolSession.Generate(
    agent="<agent-name>",
    brief="<what this task does>",
    task="<task-slug>",
    project=$NPL_PROJECT
)

Save the returned UUID — it is both the root and task session ID for this conversation.

Deferred Task Session (exploratory/unclear intent)

If the user's intent is unclear and you need to explore first, create a root session:

ToolSession.Generate(
    agent="Root",
    brief="Session: <ISO8601 timestamp with ms>",
    task="root",
    project=$NPL_PROJECT
)

Then create child sessions as work items become clear:

ToolSession.Generate(
    agent="<agent-name>",
    brief="<what this task does>",
    task="<task-slug>",
    project=$NPL_PROJECT,
    parent="<root-session-uuid>"
)

Sub-Agent Hierarchy

When spawning sub-agents, always pass the parent session UUID. Use root for top-level tasks, or the task session for sub-tasks within that scope.

Instructions Require Sessions

Instructions and Instructions.Create require a valid session UUID. You cannot use them without completing session initialization.

If the MCP server is unavailable or $NPL_PROJECT is not set, inform the user immediately and do not proceed until resolved.


Project Documentation (Agentic Reference)

Three documentation files provide a structured understanding of the codebase. Consult these before any task that requires knowledge of project structure, architecture, or data model. Each has a .summary.md companion for quick lookups.

Read the full file on GitHub · 312 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. 1mo ago Changed · -2 lines · -40 tokens per session 5fb381a4741f
  2. 2mo ago Changed · +16 lines · +450 tokens per session 1c7ff489249a
  3. 2mo ago First seen · 298 lines · 2,713 tokens per session scan A 3ed2252e9305

Subscribe to this mod's changes

NoizuPromptLingo AGENTS.md is an instructions file published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 10d ago), licensed MIT. It adds 3,123 tokens to every session, about $0.0125 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 2026-09-04.

Related

NoizuPromptLingo AGENTS.md compared with instructions from other repositories

NoizuPromptLingo AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
NoizuPromptLingo AGENTS.mdnoizu-labs-ml/NoizuPromptLingoInstructions file1310d agoMITA3,123Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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