typedai AGENTS.md

typedai AGENTS.md is an instructions file for Codex, OpenCode from TrafficGuard/typedai. It costs 4,307 tokens per session, scanned A, original, MIT.

A set of coding rules for the typedai project. It covers code structure, asynchronous programming, error handling, and files that should not be changed without explicit permission.

In plain words
What is it for?
Implementing functions, handling invalid or exceptional cases, and restructuring code into smaller, clearer pieces.
Why use it?
It reduces inconsistent style and helps prevent risky edits to project configuration or protected documentation.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/trafficguard/typedai/agents-md
Clone the repo
git clone --depth 1 https://github.com/TrafficGuard/typedai

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 typedai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/trafficguard/typedai/agents-md.svg)](https://agentmods.dev/instructions/trafficguard/typedai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/trafficguard/typedai/agents-md"><img src="https://agentmods.dev/badge/instructions/trafficguard/typedai/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,307 This file is loaded in full into every session.
When invoked 4,307 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.04307 $0.04307
Opus 5 $0.02153 $0.02153
Sonnet 5 $0.00861 $0.00861
Haiku 4.5 $0.00431 $0.00431

Measured 4d ago against content hash afcebed73959, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

typedai 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 · 524 lines

How it starts

The opening of the file, as written. The whole thing — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General code standards

Do not update project level configuration files unless explicitly instructed to.

Use async/await where possible

Test exceptional cases first and return/throw early.

Never edit files name CONVENTIONS.md, .cursorrules, DOCS.md unless explicitly instructed to.

Prefer composing small descriptive functions over large complex functions.

Clean Code style guidelines

Example

Original code

async function cloneProject(projectPathWithOrg: string, branchOrCommit: string): Promise<string> {
    const paths = projectPathWithOrg.split('/');
    if(paths.length !== 2) {
        throw new Error(`${projectPathWithOrg} must be in the format organisation/project`);
    }
    const org = paths[0];
    const project = paths[1];
    
    const agent = agentContext();
    // Determine base path: system-wide or agent-specific
    const basePath = agent?.useSharedRepos ? join(systemDir(), 'github') : agent ? join(agentDir(), 'github') : join(systemDir(), 'github'); // Default to systemDir if no agent context
    
    // Construct the full target path for the project
    const targetPath = join(basePath, org, project);
    
    // Ensure the base directory and organization directory exist
    await fs.mkdir(basePath, {recursive: true});
    await fs.mkdir(join(basePath, org), {recursive: true});
    
    // remainder of the clone function ...
}

Analysis

paths.length validation can be on one line. The assignment to basePath is too complex with multiple ternary statements. 'github' is repeated many times. The variable which changes in the ternary expression should be extract out. Group together the statements which setup the folder. Add a comment at the start of the block of statements for readability. Change targetPath to repoPath, which has more relevant meaning. "Ensure the base directory and organization directory exist" comment doesn't add value. We can assume the reader knows fundamental built in APIs like fs.mkdir Having two fs.mkdir() calls is unnecessary

Read the full file on GitHub · 524 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 First seen · 524 lines · 4,307 tokens per session scan A afcebed73959

Subscribe to this mod's changes

typedai AGENTS.md is an instructions file published in the GitHub repository TrafficGuard/typedai (1,192 stars, last pushed 8mo ago), licensed MIT. It adds 4,307 tokens to every session, about $0.0215 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 2026-08-30.