orka AGENTS.md

orka AGENTS.md is an instructions file for Codex, OpenCode from orka-agents/orka. It costs 2,395 tokens per session, scanned A, original, MIT.

Project instructions for Orka, a Kubernetes-native platform that runs container and AI-agent tasks as Kubernetes Jobs and Pods. They cover security, generated files, scope, and release rules.

In plain words
What is it for?
Use them when changing Orka's task execution, Kubernetes integration, generated sources, secrets, transaction-token handling, or branch and release workflow.
Why use it?
They reduce the risk of leaking credentials, editing generated code, mishandling transaction tokens, or making unrequested platform changes.

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/orka-agents/orka/agents-md
Clone the repo
git clone --depth 1 https://github.com/orka-agents/orka

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 orka AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/orka-agents/orka/agents-md.svg)](https://agentmods.dev/instructions/orka-agents/orka/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/orka-agents/orka/agents-md"><img src="https://agentmods.dev/badge/instructions/orka-agents/orka/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,395 This file is loaded in full into every session.
When invoked 2,395 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 $0.02395 $0.02395
Opus 5 $0.01197 $0.01197
Sonnet 5 $0.00479 $0.00479
Haiku 4.5 $0.00239 $0.00239

Measured 4d ago against content hash 7766c223f497, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orka 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 · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Orka is a Kubernetes-native task execution platform that manages Jobs and Pods for container tasks and AI agent tasks.

Non-negotiables

  • Never commit, log, or print credentials — API keys, tokens, or secrets of any kind. Use Kubernetes Secrets or env vars.
  • No binaries in the repository — put build artifacts in bin/ (gitignored) or CI release pipelines.
  • Scope discipline — implement exactly what was asked, nothing more.
  • Never push to main. Push to the current branch after a change when it is not main.
  • Transaction-token integration is fail-closed — never store raw TxTokens in Task specs/status/logs. Use owner-referenced Secrets for child tokens, safe metadata/digests for audit, subset checks for child scopes, and fail-closed TTS exchanges for outbound scopes.
  • Never edit generated files (below), and never delete // +kubebuilder:scaffold:* comments.

Generated — do not edit

For non-trivial code changes, run $autoreview (.agents/skills/autoreview/SKILL.md) before final/commit/ship and keep going until there are no accepted/actionable findings, unless the change is trivial/docs-only, equivalent manual review already happened, or the human opts out.

  • Treat review output as advisory: verify every finding against the real code path before changing code.
  • If review-triggered fixes change code, rerun focused tests and rerun $autoreview.
  • Format before review when formatting can move line locations; focused tests and review may run in parallel only after formatting is stable.

PR Closeout

After creating or updating an agent-authored PR, use $pr-closeout (.agents/skills/pr-closeout/SKILL.md) by default, like $autoreview is used before landing. Resolve merge conflicts, fix failing CI, address or push back on unresolved review threads, reply on GitHub and resolve addressed comments, push the non-main PR branch, and repeat until current CI is green and no unresolved actionable review threads remain. Skip only when the human opts out, the PR is intentionally draft/WIP, or the remaining blocker is external/human-only. Do not merge or enable auto-merge unless explicitly asked.

Read the full file on GitHub · 101 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 · 101 lines · 2,395 tokens per session scan A 7766c223f497

Subscribe to this mod's changes

orka AGENTS.md is an instructions file published in the GitHub repository orka-agents/orka (21 stars, last pushed today), licensed MIT. It adds 2,395 tokens to every session, about $0.0120 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens