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 skills add redhat-developer/rhdh-skills --skill rhdh-localgit clone --depth 1 https://github.com/redhat-developer/rhdh-skillsWrote 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/skills/redhat-developer/rhdh-skills/rhdh-local)<a href="https://agentmods.dev/skills/redhat-developer/rhdh-skills/rhdh-local"><img src="https://agentmods.dev/badge/skills/redhat-developer/rhdh-skills/rhdh-local.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 | $0.00090 | $0.00960 |
| Opus 5 | $0.00045 | $0.00480 |
| Sonnet 5 | $0.00018 | $0.00192 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
rhdh-local 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 8d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RHDH Local
Own local execution and return evidence to the calling workflow. All commands use this skill's standalone CLI; another skill does not need to be installed.
Capability gate
- Run
uv run scripts/rhdh-local --help. - Locate
rhdh-local-setupthroughRHDH_LOCAL_SETUP_DIRor by walking from the current directory. Runuv run scripts/rhdh-local --json status. - If the setup is absent, state the required environment variable or checkout layout and stop only the runtime branch.
- Never read secrets from
.envinto conversation context. Ask only for missing variable names and let the container runtime consume their values.
Route by outcome
| Outcome | Load and follow |
|---|---|
| Enable a catalog or PR artifact | workflows/enable-plugin.md |
| Disable a plugin | workflows/disable-plugin.md |
| Switch pristine/customized mode | workflows/switch-mode.md |
| Verify a plugin end to end | workflows/test-plugin.md and references/dynamic-plugin-testing.md |
| Inspect status or enabled packages | Run uv run scripts/rhdh-local --json status or uv run scripts/rhdh-local --json plugins list |
| Apply customizations | Run uv run scripts/rhdh-local --json apply |
| Start or stop | Run uv run scripts/rhdh-local --json up [flags] or uv run scripts/rhdh-local --json down |
| Check health | Run uv run scripts/rhdh-local --json health |
| Back up or restore | Run uv run scripts/rhdh-local --json backup or uv run scripts/rhdh-local restore <archive>; restore is a dry run until --force |
| Troubleshoot startup, networking, or 504s | references/troubleshooting.md |
| Configure environment variables | references/env-reference.md |
Invariants
- Edit only source files under
rhdh-customizations/. Runapplyafter every edit so copies underrhdh-local/stay synchronized. - Use this CLI's
upanddowncommands when Lightspeed or Orchestrator is enabled; they own the compose lifecycle and shared networks. - Obtain package references from
spec.dynamicArtifactor from the reference the caller supplied. Never construct OCI references from naming conventions. - Preserve the
includes:block in dynamic plugin overrides. Put backend packages before their frontend packages. - A plugin test succeeds only with recorded installation, boot, health, and UI results relevant to the request. Distinguish an expected credential error from a load failure.
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 100 B
- references/customization-system.md 5.1 KB
- references/dynamic-plugin-testing.md 6.5 KB
- references/env-reference.md 5.3 KB
- references/troubleshooting.md 3.9 KB
- rhdh_local/__init__.py 1.2 KB runs code
- rhdh_local/backup.py 4.7 KB runs code
- rhdh_local/cli.py 24 KB runs code
- rhdh_local/compose.py 6.4 KB runs code
- rhdh_local/health.py 4.6 KB runs code
- rhdh_local/settings.py 3.0 KB runs code
- rhdh_local/support.py 7.7 KB runs code
- rhdh_local/sync.py 3.8 KB runs code
- scripts/fetch-plugin-metadata.py 22 KB runs code
- scripts/NOTICE 837 B
- scripts/rhdh-local 577 B
- workflows/disable-plugin.md 1.7 KB
- workflows/enable-plugin.md 5.6 KB
- workflows/switch-mode.md 3.8 KB
- workflows/test-plugin.md 3.7 KB
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.
- 8d ago First seen · 89 lines · 90 tokens per session scan A fdbf285b72b2
rhdh-local is a skill published in the GitHub repository redhat-developer/rhdh-skills (16 stars, last pushed 4d ago), licensed Apache-2.0. It adds 90 tokens to every session and 960 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.