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/openshift-online/agent-control-plane/claude-mdgit clone --depth 1 https://github.com/openshift-online/agent-control-planeWrote 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/openshift-online/agent-control-plane/claude-md)<a href="https://agentmods.dev/instructions/openshift-online/agent-control-plane/claude-md"><img src="https://agentmods.dev/badge/instructions/openshift-online/agent-control-plane/claude-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 | $0.02577 | $0.02577 |
| Opus 5 | $0.01288 | $0.01288 |
| Sonnet 5 | $0.00515 | $0.00515 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade A, and why
agent-control-plane CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Control Plane
Kubernetes-native AI automation platform that orchestrates agentic sessions through containerized microservices. Built with Go (API server, control plane), NextJS + Shadcn (UI), and Python (runner). PostgreSQL is the source of truth; the control plane reconciles via gRPC watch streams.
Some RBAC manifests still reference the
vteam.ambient-codeAPI group for backward compatibility.
Structure
components/ambient-api-server/- Go REST API microservice (rh-trex-ai framework), PostgreSQL-backedcomponents/ambient-control-plane/- Go service, watches API server via gRPC and reconciles sessions into K8s Jobscomponents/ambient-ui/- NextJS + Shadcn web UI for session management and monitoringcomponents/ambient-mcp/- MCP server integrationcomponents/runners/ambient-runner/- Python runner executing Claude Code CLI in Job podscomponents/ambient-cli/- Go CLI (acpctl), manages agentic sessions from the command linecomponents/ambient-sdk/- Go, Python, and TypeScript client SDKs generated from the OpenAPI speccomponents/credential-sidecars/- Per-provider credential sidecar containers (GitHub, Jira, K8s, Google)components/manifests/- Kustomize-based deployment manifests and overlaysdocs/- Astro Starlight documentation sitespecs/- Desired state of the system (platform, security, ui, standards)skills/- Agent skills: reconcile, spec, full-stack-pipeline, dev-cluster, pr-test, deploy-cluster, review, toolingapm.yml- APM manifest declaring upstream skill dependencies (fleet-sdlc).claude/skills/- APM-installed upstream skills (gitignored, runapm install).claude/commands/- APM-installed upstream commands (gitignored)
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.
- 4d ago First seen · 203 lines · 2,577 tokens per session scan A 8cbeb938e789
agent-control-plane CLAUDE.md is an instructions file published in the GitHub repository openshift-online/agent-control-plane (11 stars, last pushed yesterday), licensed MIT. It adds 2,577 tokens to every session, about $0.0129 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 2026-08-31.
Other instructions, from other repositories
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.
omk CLAUDE.md
Claude Code instructions for dmae97/omk, covering claude.md, precedence (read this first), omk runtime map (what you're operating inside), this repo: open-multi-agent-kit / omk monorepo and build / test / check commands.
icron CLAUDE.md
Instructions for zebbern/icron, covering icron, architecture, key directories, built-in tools and commands.
workstreams disposable.instructions.md
Guidelines for writing code using IDisposable.
relay CLAUDE.md
Claude Code instructions for simota/relay, covering claude.md, what this is, documentation map, runtime: bun-first and commands.