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/platformrelay/mkurator/agents-mdgit clone --depth 1 https://github.com/PlatformRelay/MKuratorWhat 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 | $0.07028 | $0.07028 |
| Opus 5 | $0.03514 | $0.03514 |
| Sonnet 5 | $0.01406 | $0.01406 |
| Haiku 4.5 | $0.00703 | $0.00703 |
Grade A, and why
MKurator 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 2d 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 — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This document is the entry point for humans and AI agents working on the MKurator. It captures what the project is, how it is structured, and the conventions every change must follow. Read it before making changes, and keep it in sync when conventions evolve.
Documentation map
AGENTS.md (this file) — project context, conventions, toolchain, workflow.
Full doc index by role (with navigation emojis): docs/README.md.
| Document | What it covers | |
|---|---|---|
| 🎯 | docs/INSTALL_AND_USE.md | User guide: install, connect, CRs, troubleshooting. |
| 🎯 | docs/QUICKSTART.md | Fast path: install, connect, first queue. |
| 🎯 | docs/FAQ.md | Common questions (QMC, drift, suspend, webhooks). |
| 🎯 | docs/GLOSSARY.md | MQ and operator terminology. |
| 🎯 | docs/UPGRADE.md | Upgrade operator, CRDs, webhooks, cert-manager. |
| 🎯 | docs/OBSERVABILITY.md | Metrics, ServiceMonitor, Prometheus scrape. |
| 🏗️ | docs/LOGGING.md | Structured logging configuration. |
| ✉️ | docs/CONTRIBUTING.md | Developer guidelines, Conventional Commits, gitmoji. |
| 🔧 | config/samples/README.md | Annotated sample Secret, Connection, Queue, Topic, Channel YAML. |
| 🏗️ | docs/ARCHITECTURE.md | Components, runtime, CRDs, reconcile flow, security. |
| 🏗️ | docs/ATTRIBUTE_RECONCILIATION.md | DEFINE vs DISPLAY drift matrix per MQ object type. |
| 🛠️ | docs/LOCAL_SETUP.md | Install dev tools (Go, Task, kind, Terraform, …). |
| 🛠️ | docs/DEVELOPMENT.md | Prerequisites, inner loop, local cluster, test tiers. |
| 🛠️ | docs/DEVELOPER_GUIDE.md | CRD codegen checklist, test tiers per change, MQAdmin mocks. |
| 🧩 | docs/GO_MODULE.md | Go module layout, import layers, arch lint. |
| ⚙️ | docs/OPERATOR_RUNTIME.md | Manager wiring, probes, concurrency, shutdown. |
| 📋 | docs/ROADMAP.md | Phased delivery plan. |
| 📋 | docs/CICD.md | CI/CD pipeline and verify discipline. |
| 📋 | docs/NON_FUNCTIONAL_REQUIREMENTS.md | NFRs: security, reliability, observability, performance. |
| 🔒 | docs/ASSURANCE-CASE.md | Security claims and trust boundaries. |
| 🔒 | docs/SECURITY-REVIEW.md | Dated security self-review. |
| 📚 | docs/IBM_MQ_OBJECTS.md | MQSC research inventory (not the product API). |
| 📚 | docs/IBM_MQ_REST_API.md | How the mqweb REST API is consumed. |
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.
- 2d ago First seen · 460 lines · 7,028 tokens per session scan A 0a8fdfb1b2e1
MKurator AGENTS.md is an instructions file published in the GitHub repository PlatformRelay/MKurator (5 stars, last pushed 3d ago), licensed MIT. It adds 7,028 tokens to every session, about $0.0351 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
mariadb-operator AGENTS.md
Instructions for mariadb-operator/mariadb-operator, covering agents.md, project overview, simplicity, crds and repository structure.
bex CLAUDE.md
Instructions for bex-co/bex, covering claude.md, repo map, commands, local cluster workflow and environment variables.
ogo AGENTS.md
Instructions for aknochow/ogo, covering ogo - project context, documentation - read first, what this is, versioning - critical and tag strategy.
mariadb-operator CLAUDE.md
Instructions for mariadb-operator/mariadb-operator, a project described as: 🦭 Run and operate MariaDB in a cloud native way.
bex AGENTS.md
Instructions for bex-co/bex, a project described as: The open-source Render alternative — AI-native. Git push → build → deploy on your own infrastructure; agents are first-class users.
ogo CLAUDE.md
Instructions for aknochow/ogo, a project described as: OGO (OpenShell Gateway Operator): Deploy and manage NVIDIA OpenShell Gateway instances on OpenShift.