AGENTS.mdA

AGENTS.md from confighub/cub-scout is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned

mdr add confighub/cub-scout/AGENTS.md@git:20260918.063559f

Pins git:20260918.063559f in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 14 of 14 checks passed
Kind: AGENTS.md file
Repository: confighub/cub-scout
Path: AGENTS.md
Versions recorded: 2
Latest version: git:20260918.063559f, committed Sep 18, 2026
First version recorded: Sep 12, 2026
Size: 10,963 bytes
Repository stars: 14
License: MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# cub-scout

Read-only Kubernetes observer. Detects ownership (Flux, ArgoCD, Sveltos, Modelplane, Helm, Crossplane, kro, ConfigHub, Native).

## Read First

For a fresh coding session in this repo, read these in order:

1. [AI-README-FIRST.md](AI-README-FIRST.md)
2. [HANDOVER.md](HANDOVER.md)
3. [docs/reference/commands.md](docs/reference/commands.md)
4. [docs/reference/cli-contract.md](docs/reference/cli-contract.md)
5. [docs/reference/json-contracts.md](docs/reference/json-contracts.md)

## Related Abilities

- `cub-scout`: read-only cluster/GitOps observation, connected comparison, import preview, MCP serving
- `cub`: ConfigHub CLI for intended-state workflows, spaces/units/targets, `cub variant upload`
- `confighub/sdk`: renderer/bridge implementation detail used by `cub`

Important boundary:
- `cub-scout import --git-path` is a local structure/import-preview flow
- `cub variant upload` ingests **already rendered** resources (a directory, `-`,
  or an `oci://` bundle) and makes a space's units match them; the rendering is
  done by your own tooling (`helm template`, `kustomize build`, an installer)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add confighub/cub-scout/AGENTS.md@sha256:07420f6c3a04afa4

The line at the top of this page pins the label git:20260918.063559f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_wzopydoddnp5lz7n.svg)](https://markdownregistry.com/a/art_wzopydoddnp5lz7n)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 12, 2026 and Sep 18, 2026, about one every 6 days.

version	committed	commit	size	audit
git:20260918.063559f latest	2026-09-18	063559f	10,963 B	A	view · diff
git:20260912.5455da0	2026-09-12	5455da0	10,623 B	A	view

Audit of the latest version

A 14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Size between 200 bytes and 200 KB (10963 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

confighub/cub-scout · 14 stars · license MIT · pushed 2026-10-11 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wzopydoddnp5lz7n
GET https://markdownregistry.com/api/v1/resolve?ref=confighub/cub-scout/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/07420f6c3a04afa47ea20f9ac2739782e8e3b8a700559a140a4f7db57757f6e1

Your AI assistant 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.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from confighub/cub-scout

CLAUDE.md CLAUDE.md file

confighub/cub-scout · CLAUDE.md

git:20261006.4415352 · audit A · 14 stars

recorded-field-attribution SKILL.md skill

confighub/cub-scout · evals/recorded-mcp-probe/economy-skill/SKILL.md · Use when asked which manager is recorded for a field on a known Kubernetes resource, especially when the resource and…

git:20260930.dffb108 · audit A · 14 stars

ai-agent-readonly-context SKILL.md skill

confighub/cub-scout · skills/ai-agent-readonly-context/SKILL.md · Use when the user is WIRING CUB-SCOUT INTO AN AI AGENT (Claude / Codex / a custom LLM workflow) and needs the patterns…

git:20261011.81f7574 · audit A · 14 stars

audit-fleet-conformance SKILL.md skill

confighub/cub-scout · skills/audit-fleet-conformance/SKILL.md · Use when the user wants to verify CONFORMANCE ACROSS A FLEET — multiple namespaces, multiple clusters, or a defined…