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.
npx agentmods add instructions/googlecontainertools/config-sync/agents-mdgit clone --depth 1 https://github.com/GoogleContainerTools/config-syncWrote 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.
[](https://agentmods.dev/instructions/googlecontainertools/config-sync/agents-md)<a href="https://agentmods.dev/instructions/googlecontainertools/config-sync/agents-md"><img src="https://agentmods.dev/badge/instructions/googlecontainertools/config-sync/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00738 | $0.00738 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
config-sync 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repository. Human contributors should also read docs/contributing.md, docs/development.md, and docs/testing.md, which are the source of truth.
Project summary
Config Sync synchronizes configurations and policies from a source of truth (Git repository, OCI image, or Helm chart) to a Kubernetes cluster, ensuring consistency at scale. It simplifies and automates configuration management across single or multi-cluster environments, managing both cluster-scoped and namespace-scoped resources.
Key Technologies & Architecture:
- Language & Frameworks: Go, Kubernetes, Kubebuilder / Controller Runtime, Kustomize.
- Core Custom Resources:
RootSync(cluster-scoped synchronization) andRepoSync(namespace-scoped synchronization). - Reconciler Manager: Controller component that manages the lifecycle of individual reconciler deployments.
- Reconcilers: Specialized controllers spawned for each sync target that watch the upstream source and apply manifests to the cluster.
- Admission Webhook: Validates configuration and state changes for Config Sync custom resources.
- Nomos CLI: Command-line interface for inspecting status, troubleshooting, and interacting with Config Sync deployments.
Repository layout
| Path | What lives there |
|---|---|
| cmd/ | Main entrypoints for controllers (reconciler-manager, reconciler, admission-webhook) and the nomos CLI. |
| pkg/ | Core implementation logic: reconcilers, git/OCI sync logic, manifest parsers, validation logic, and webhook handlers. |
| manifests/ | Base Kubernetes manifests and Kustomize configurations used to deploy Config Sync components. |
| e2e/ | End-to-end test framework and test suites (Go-driven, runnable against kind or GKE). |
| docs/ | Documentation for usage, installation, contributing, development, and testing. |
| examples/ | Sample Git repositories and configurations used for tutorials and verification. |
| scripts/ | Shell scripts for CI, verification, and auxiliary build tasks. |
| build/ | Build setups, container entrypoints, base Dockerfiles, and build dependencies. |
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.
- today First seen · 47 lines · 738 tokens per session scan A 48f5bc4a7f6e
config-sync AGENTS.md is an instructions file published in the GitHub repository GoogleContainerTools/config-sync (278 stars, last pushed yesterday), licensed Apache-2.0. It adds 738 tokens to every session, about $0.0037 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 2026-09-04.
Other instructions, from other repositories
bex CLAUDE.md
Claude Code instructions for bex-co/bex, covering claude.md, repo map, commands, local cluster workflow and environment variables.
home-ops AGENTS.md
AGENTS.md instructions for gavinmcfall/home-ops, covering ai assistant configuration, 📚 documentation location, 📖 read first, ⚠️ critical invariants and capsule: gitopsreconciliation.
home-ops copilot-instructions.md
Instructions for GitHub Copilot when working with this homelab repository.
home-ops AGENTS.md
Instructions for edgard/home-ops, covering home ops, build & test, developer loop, project layout and conventions.
mcp-k8s-observability-argocd-server AGENTS.md
AGENTS.md instructions for peopleforrester/mcp-k8s-observability-argocd-server, covering argocd mcp server, commands, tool implementation guidelines, progressive disclosure tiers and safety patterns.
opsgentic CLAUDE.md
Claude Code instructions for lehuannhatrang/opsgentic: This repository uses a modular AI assistant configuration. All operational rules are defined in .claude/rules.md.