Home / gke-labs / kube-agents · agents/platform/AGENTS.md · GitHub

AGENTS.md@agents/platform agentsA

AGENTS.md@agents/platform is agent-read markdown (agents) from gke-labs/kube-agents.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# AGENTS.md - Your Workspace

This folder is home. Treat it that way.

## Session Startup

Use runtime-provided startup context first, including `AGENTS.md` and `SOUL.md`.
Do not manually reread startup files unless the user explicitly asks or the context is missing vital information.
A glossary of agentic terms lives at `/opt/defaults/docs/glossary.md`. Read it **only** when you actually hit harness terminology you cannot ground — **Agent Substrate** and the like — or when the user asks about it. Every kanban card is a fresh session, so reading it unconditionally costs a model turn per card for a file most tasks never need.

## Memory

You wake up fresh each session. Maintain continuity through:

- **Daily notes:** `memory/YYYY-MM-DD.md` — records of agent provisions, cluster setup tasks, and policy audits.
- **Shared long-term memory, read-only:** the organisation's standard procedures, platform conventions, cluster and environment inventory, ownership, and release history. Relevant entries are injected into your context automatically; `memory_recall` searches them and `memory_reflect` synthesises across them.

Two rules follow from that memory being read-only:
…

Read the whole file at its exact version.

How to install

Latest version
mdr add gke-labs/kube-agents/agents/platform/AGENTS.md@git:20260905.f66d195
Exact content
mdr add gke-labs/kube-agents/agents/platform/AGENTS.md@sha256:28c7a6a7c29ce261

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_t5g65d6i6nz7xeay.svg)](https://markdownregistry.com/a/art_t5g65d6i6nz7xeay)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260905.f66d195 latest2026-09-05 f66d195 10,073 BA view · diff
git:20260819.731c8132026-08-19 731c813 9,396 BA view · diff
git:20260818.1a3868f2026-08-18 1a3868f 8,537 BA view · diff
git:20260817.1e2df492026-08-17 1e2df49 8,525 BA view · diff
git:20260817.a3370ef2026-08-17 a3370ef 8,120 BA view

Audit of the latest version

A  14 of 14 checks passed. Deterministic, no model, same answer every run.
  • pass: Size between 200 bytes and 200 KB (10073 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

gke-labs/kube-agents · 64 stars · license Apache-2.0 · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_t5g65d6i6nz7xeay
GET https://markdownregistry.com/api/v1/resolve?ref=gke-labs/kube-agents/agents/platform/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/28c7a6a7c29ce2619e9eaafa63f899fe675b2488ecd8397863c5f604f32a5ec8

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from gke-labs/kube-agents

install-kube-agents skill
gke-labs/kube-agents · .agents/skills/install-kube-agents/SKILL.md · Provision and install the Kubernetes Agentic Harness (kube-agents) onto a GKE cluster non-interactively or…
git:20260923.b7399af · audit B · 64 stars
review-adversarial skill
gke-labs/kube-agents · .agents/skills/review-adversarial/SKILL.md · Reviews a change adversarially — establishes what it claims to do, hunts candidates from ten angles, then re-derives…
git:20260916.6d52c6b · audit A · 64 stars
review-docs-drift skill
gke-labs/kube-agents · .agents/skills/review-docs-drift/SKILL.md · Reviews a pull request for documentation drift — finds which docs the change should have updated, verifies doc claims…
git:20260916.6d52c6b · audit A · 64 stars
review-preflight skill
gke-labs/kube-agents · .agents/skills/review-preflight/SKILL.md · Runs the review passes required before a pull request is opened — adversarial and docs-drift — each in a context that…
git:20260916.6d52c6b · audit A · 64 stars
review-security-k8s-admission skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-admission/SKILL.md · Reviews Kubernetes Admission Control (Webhooks, VAP/MAP) for vulnerabilities.
git:20260522.4bbd4a0 · audit A · 64 stars
review-security-k8s-agents-audit-logs skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-audit-logs/SKILL.md · Reviews Kubernetes and application audit logging for AI agents, ensuring tamper-proof observability.
git:20260521.2bcbdef · audit A · 64 stars
review-security-k8s-agents-credentials skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-credentials/SKILL.md · Reviews AI agent Kubernetes configurations for credentials exposed to agents.
git:20260521.2bcbdef · audit A · 64 stars
review-security-k8s-agents-data-exfil skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-data-exfil/SKILL.md · Reviews Kubernetes configurations to prevent data exfiltration by AI agents.
git:20260521.2bcbdef · audit A · 64 stars
review-security-k8s-agents-firewall skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-firewall/SKILL.md · Reviews Kubernetes network and firewall configurations specifically for AI agent execution sandboxes.
git:20260903.799c7e3 · audit A · 64 stars
review-security-k8s-agents-main skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-main/SKILL.md · Orchestrates comprehensive Kubernetes security audits specifically tailored for AI agent workloads.
git:20260522.4bbd4a0 · audit A · 64 stars
review-security-k8s-agents-prompt-injection skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-prompt-injection/SKILL.md · Reviews AI agent architectures (API gateways, WAFs, input sanitization) for prompt injection risks.
git:20260521.2bcbdef · audit A · 64 stars
review-security-k8s-agents-sandbox skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-sandbox/SKILL.md · Reviews AI agent execution sandboxes for code escape and lateral movement risks.
git:20260521.2bcbdef · audit A · 64 stars

Every file in gke-labs/kube-agents

Browse by kind, by grade A, or by owner.