kybernetes AGENTS.md

kybernetes AGENTS.md is an instructions file for Codex, OpenCode from pariyar07/kybernetes. It costs 942 tokens per session, scanned A, original, MIT.

Repository instructions for Kybernetes, an open-source control layer for agent-run work such as coding, research, marketing, and operations.

In plain words
What is it for?
Use them when developing or reviewing Kybernetes skills, loop controls, verification runs, handoffs, or learning records.
Why use it?
They define the repository layout, public boundaries, and working rules so changes remain portable and do not depend on private projects or secrets.

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/pariyar07/kybernetes/agents-md
Clone the repo
git clone --depth 1 https://github.com/pariyar07/kybernetes

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 kybernetes AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pariyar07/kybernetes/agents-md.svg)](https://agentmods.dev/instructions/pariyar07/kybernetes/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pariyar07/kybernetes/agents-md"><img src="https://agentmods.dev/badge/instructions/pariyar07/kybernetes/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 942 This file is loaded in full into every session.
When invoked 942 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 $0.00942 $0.00942
Opus 5 $0.00471 $0.00471
Sonnet 5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured 5d ago against content hash 72000ddf5eab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kybernetes 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 5d 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 · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kybernetes - Agent Instructions

Kybernetes is an open-source steering layer for agentic work of any kind — coding, marketing campaigns, cold outreach, research, operations, or anything else an agent can run. Keep repository guidance generic, portable, and independent from any maintainer's private workspace.

Repository Shape

skills/
  kybernetes-loop-governor/  # canonical controller, `kybernetes:loop-governor`
  kybernetes-loop-architect/  # advisory execution-contract design
  kybernetes-loop-closeout/  # checkpoint, handoff, and retirement
  kybernetes-verify-run/  # independent rejection-capable verification
  kybernetes-capture-learning/  # evidence-gated constraint proposals
docs/
  architecture/              # runtime and boundary design
  product/                   # product model and non-goals
examples/                    # durable example control records
tests/
  pressure-scenarios/        # behavioral pressure scenarios for skill changes

Public Boundary

  • Public defaults must work for people who do not know the maintainer's private projects, vaults, or workflows.
  • Do not add private workspace content, customer context, secrets, credentials, internal URLs, or production data.
  • Do not make any personal knowledge base, issue tracker, chat service, or project-management tool the default persistence layer.
  • Runtime-specific assumptions belong in runtime binding references, not in generic loop-governor semantics.
  • New installable skills need pressure-scenario evidence before creating a SKILL.md; planned skills stay in docs/architecture/planned-skills.md.
  • Committed .kybernetes/ and .agent-runs/ live-run artifacts are out of bounds unless they are intentionally promoted examples under examples/ or tests.

Working Rules

  • Read PUBLIC_BOUNDARY.md before changes that could affect public/private scope.
  • Read CONTRIBUTING.md before changing skill behavior.
  • For skill changes, update or add a pressure scenario in tests/pressure-scenarios/, show the failure or gap, then change the smallest relevant skill text.
  • Keep skills/kybernetes-loop-governor/SKILL.md focused on operational instructions. Put deeper runtime details in references/.
  • Do not add placeholder folders under skills/; every folder there must contain a real SKILL.md.
  • Preserve the V1 control contract: kybernetes:loop-governor is the sole canonical lifecycle controller. Pressure-backed helper skills may inspect state and return owned outputs, but they cannot mutate parent canonical state or accept completion.
  • Before proposing a public merge, classify the change under docs/releases/evidence-gated-release-policy.md. Significant or unknown behavioral changes require a preregistered private evaluation and signed accepted attestation. Minor documentation, maintenance, security, or governance changes require an explicit signed exemption.
  • Never copy private evaluation contracts, fixtures, graders, transcripts, credentials, repository identities, or personal paths into this repository. Public release attestations contain only the safe allowlisted fields.
  • The evaluation runner and evidence reviewer must be different identities. Agents may prepare evidence but cannot self-review or sign their own run.

Read the full file on GitHub · 77 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. 5d ago First seen · 77 lines · 942 tokens per session scan A 72000ddf5eab

Subscribe to this mod's changes

kybernetes AGENTS.md is an instructions file published in the GitHub repository pariyar07/kybernetes (13 stars, last pushed 1mo ago), licensed MIT. It adds 942 tokens to every session, about $0.0047 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.