erstan-agent-tools-beta AGENTS.md

erstan-agent-tools-beta AGENTS.md is an instructions file for Codex, OpenCode from erstanai/erstan-agent-tools-beta. It costs 288 tokens per session, scanned A, original, Apache-2.0.

Repository instructions that tell contributors how to keep the Erstan beta add-on safe and consistent.

In plain words
What is it for?
Following contribution rules for files, authentication, versions, marketplace listings, and the hosted beta service.
Why use it?
They reduce mistakes such as exposing credentials, using the wrong service address, or creating naming conflicts between beta and production versions.

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/erstanai/erstan-agent-tools-beta/agents-md
Clone the repo
git clone --depth 1 https://github.com/erstanai/erstan-agent-tools-beta

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 erstan-agent-tools-beta AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/erstanai/erstan-agent-tools-beta/agents-md.svg)](https://agentmods.dev/instructions/erstanai/erstan-agent-tools-beta/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/erstanai/erstan-agent-tools-beta/agents-md"><img src="https://agentmods.dev/badge/instructions/erstanai/erstan-agent-tools-beta/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 288 This file is loaded in full into every session.
When invoked 288 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 $0.00288 $0.00288
Opus 5 $0.00144 $0.00144
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured 4d ago against content hash ab366ebab640, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

erstan-agent-tools-beta 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 · 25 lines

What it actually says

Contributor guidance

This is a public, allowlisted beta distribution repository. Keep it small and safe.

  • Never add credentials, customer data, production traces, private diagnostics, local environment files, or generated caches.
  • Keep the Codex and Claude plugin names and versions aligned with the package version and both marketplace entries.
  • Keep the hosted MCP URL exactly https://api-qa.erstan.com/v1/mcp unless an intentional release changes it everywhere.
  • Keep the plugin and marketplace identity exactly erstan-beta so it can be installed beside the production erstan plugin without a name collision.
  • Do not submit this temporary repository to a public plugin directory. Beta access is enforced by Erstan OAuth and server-side access policy.
  • Do not add static authentication headers, key fields, or token environment variables. Authentication is OAuth through the host.
  • Do not add .app.json without a real registered OpenAI app identifier and a deliberate publication review.
  • Put maintainer CLI tools and offline diagnostics in the separate toolkit, never in this plugin. Repository-owned distribution sync automation may stay here, but user-facing optimization belongs in hosted-MCP Skills rather than npm CLI commands.
  • Run npm run verify, the Codex plugin validator, all seven skill validators, and claude plugin validate . before release.
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 · 25 lines · 288 tokens per session scan A ab366ebab640

Subscribe to this mod's changes

erstan-agent-tools-beta AGENTS.md is an instructions file published in the GitHub repository erstanai/erstan-agent-tools-beta (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 288 tokens to every session, about $0.0014 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.