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 rules/benwilcock/rhdh-lab/core-architecturegit clone --depth 1 https://github.com/benwilcock/rhdh-labWrote 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/rules/benwilcock/rhdh-lab/core-architecture)<a href="https://agentmods.dev/rules/benwilcock/rhdh-lab/core-architecture"><img src="https://agentmods.dev/badge/rules/benwilcock/rhdh-lab/core-architecture.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 5.1 | $0.01156 | $0.01156 |
| Opus 5 | $0.00578 | $0.00578 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
core-architecture 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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RHDH Local Project - Core Architecture & Critical Rules
Project Context
This workspace wraps RHDH Local -- a development and testing environment for Red Hat Developer Hub (RHDH). It enables platform engineers to run RHDH locally using Podman or Docker containers, testing software catalogs, TechDocs, plugins, templates, and configurations without a Kubernetes cluster.
RHDH Local is for development and testing only, NOT production use.
- Official project repository:
https://github.com/redhat-developer/rhdh-local.git - Built-in TechDocs at
http://localhost:7007when running - Online docs: https://docs.redhat.com/en/documentation/red_hat_developer_hub/
Critical Rules (MUST follow without exception)
- Always Use the CLI: Use
./lab upand./lab downfor container lifecycle -- NEVER usepodman compose restart/up/downdirectly when orchestrator or lightspeed are enabled - Network Namespace Sharing: Lightspeed containers share RHDH's network namespace via
network_mode: "service:rhdh"-- restarting one requires restarting all - Edit in
rhdh-customizations/: All configuration edits go inrhdh-customizations/;./lab upautomatically syncs copies intorhdh-local/ - Pristine Project: Never modify files in
rhdh-local/directly -- it must always match the upstream git repository - Always Document: Every significant change must be documented. Update relevant docs in
docs/, READMEs, and inline comments so humans can understand what was done and why
Why These Rules Exist
- Breaking Rule 1 or 2: Causes 504 Gateway Timeout errors (network namespace desynchronization)
- Breaking Rule 3: Changes don't take effect, or git conflicts occur
- Breaking Rule 4: Makes the project un-updatable via
git pull - Breaking Rule 5: Creates hidden knowledge lost between sessions and invisible to human collaborators
Copy-Sync Customization System (Overview)
The fundamental architectural pattern of this workspace:
rhdh-local/-- Official RHDH Local git repository (PRISTINE, never modified)rhdh-customizations/-- All your configuration files, overrides, and settingsapply-customizations.sh-- Copies files fromrhdh-customizations/intorhdh-local/so containers can read them (containers only see mounted dirs, so symlinks to external paths would break)remove-customizations.sh-- Deletes the copies fromrhdh-local/to restore pristine state
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.
- 5d ago First seen · 78 lines · 1,156 tokens per session scan A 44fd7ea23be4
core-architecture is a cursor rule published in the GitHub repository benwilcock/rhdh-lab (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,156 tokens to every session, about $0.0058 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 cursor rules, from other repositories
python-containerization-cursorrules-prompt-file
Cursor rules for Python development with containerization integration.
aws-ecs
Definitive guidelines for building, deploying, and operating applications on AWS ECS, emphasizing immutable containers, secure secrets management, and robust operational patterns.
general
Cursor rule "general" from Screenly/Anthias, covering general, project structure, code generation and docker.
hack
Hack v3 is local-first. This project uses hack for local runtime orchestration (compose + DNS/TLS + logs + sessions). Prefer hack when shell access is available. Use MCP only when shell access is unavailable.
colima-docker-runtime
This workspace uses Colima for Docker; use compose-backed tests when Colima is running.
local-compose-db-lifecycle-for-web-tests
Keep local compose DB lifecycle ready for web tests.