sdk-roark-analytics-node: Instructions file for Codex

AGENTS.md

sdk-roark-analytics-node AGENTS.md is an instructions file for Codex, OpenCode from roarkhq/sdk-roark-analytics-node. It costs 459 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for a TypeScript SDK whose API-facing code is generated from an OpenAPI specification. They explain which files agents may edit and how hand-written configuration helpers relate to generated types.

In plain words
What is it for?
Use them when changing the SDK, its configuration helpers, examples, or code-generation-related files.
Why use it?
They prevent changes to generated files from being overwritten and clarify where new API resource types need corresponding code. This reduces avoidable mistakes when maintaining the SDK.

Instructions file for CodexOpenCode

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

This is roarkhq/sdk-roark-analytics-node's own configuration. It tells Codex and OpenCode how to work on sdk-roark-analytics-node 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 sdk-roark-analytics-node configures →

Reuse

Borrowing it

Nothing to install: this file belongs to roarkhq/sdk-roark-analytics-node. 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/roarkhq/sdk-roark-analytics-node/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/roarkhq/sdk-roark-analytics-node

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 sdk-roark-analytics-node AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/roarkhq/sdk-roark-analytics-node/agents-md/github.svg)](https://agentmods.dev/instructions/roarkhq/sdk-roark-analytics-node/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/roarkhq/sdk-roark-analytics-node/agents-md"><img src="https://agentmods.dev/badge/instructions/roarkhq/sdk-roark-analytics-node/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 sdk-roark-analytics-node AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/roarkhq/sdk-roark-analytics-node/agents-md"><img src="https://agentmods.dev/badge/instructions/roarkhq/sdk-roark-analytics-node/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 459 This file is loaded in full into every session.
When invoked 459 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 $0.00459 $0.00459
Opus 5.5 $0.00184 $0.00184
Sonnet 5.5 $0.00092 $0.00092
Haiku 4.5 $0.00046 $0.00046

Measured 9d ago against content hash b3c00874d69f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdk-roark-analytics-node 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 9d 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 · 33 lines

What it actually says

AGENTS.md

Guidance for AI coding agents (Claude Code, Codex, Cursor, etc.) working in this repository.

Generated code and hand-written code

Most of this SDK is generated from the Roark API's OpenAPI spec by app-agent-codegen, which opens a PR here when the API changes. Don't hand-edit generated files: the next generation overwrites them. Only src/lib/ and examples/ are hand-written and never touched by codegen (see CONTRIBUTING.md).

Config-as-code helpers (src/lib/config.ts)

The define* helpers (defineAgent, defineMetric, defineScriptedFlow, ...) are hand-written. Their input types are derived from the generated ConfigApplyParams, so:

  • A new field on an existing resource type reaches TypeScript on the next codegen with no change here.
  • A new resource type does not. A new kind, or a new variant of an existing kind (a second kind: metric shape such as an API check with calculationType: HTTP_REQUEST, a second flow type), arrives in ConfigApplyParams as a new type that no helper accepts. YAML supports it, and define* doesn't type-check.

When a codegen PR adds a resource type to ConfigApplyParams['resources'], add in the same PR:

  1. A friendly alias next to the others (export type XConfig = ConfigApplyParams.XConfig;).
  2. A define* helper that fills in kind and every fixed discriminator (type, template, calculationType), following defineScriptedFlow and defineQaSimulationPlan.
  3. The helper's return type in DefinedResource in tests/lib/config.test.ts, plus a test that it fills in its discriminators.

tests/lib/config.test.ts enforces this at type-check time: a resource type without a helper fails tsc with an error naming the type, which turns the codegen PR red until the helper exists.

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. 9d ago First seen · 33 lines · 459 tokens per session scan A b3c00874d69f

Subscribe to this mod's changes

sdk-roark-analytics-node AGENTS.md is an instructions file published in the GitHub repository roarkhq/sdk-roark-analytics-node (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 459 tokens to every session, about $0.0018 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 2026-10-28.

Related

sdk-roark-analytics-node AGENTS.md compared with instructions from other repositories

sdk-roark-analytics-node AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sdk-roark-analytics-node AGENTS.mdroarkhq/sdk-roark-analytics-nodeInstructions file7yesterdayApache-2.0A459Codex, 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