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 skills/controlplane-com/ai-plugin/template-catalognpx skills add controlplane-com/ai-plugin --skill template-cataloggit clone --depth 1 https://github.com/controlplane-com/ai-pluginWhat 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 | $0.00049 | $0.02724 |
| Opus 5 | $0.00024 | $0.01362 |
| Sonnet 5 | $0.00010 | $0.00545 |
| Haiku 4.5 | $0.00005 | $0.00272 |
Grade A, and why
template-catalog 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Template Catalog
Tool availability:
preview_template(dry-run) androllback_templateare in thefullMCP toolset;browse_templates,get_template,install_template,upgrade_template,uninstall_template,list_installed_templates, andget_installed_templateare incore. If afulltool is not advertised, reconnect the MCP server with?toolsets=fullor use thecpln helmCLI fallback.
The Template Catalog ships production-tested charts (Helm under the hood) for databases, caches, queues, brokers, search, gateways, and more — persistent storage wired up, credentials generated as Control Plane secrets, a sane firewall posture, and HA variants where they matter. For any common component the catalog template is the default recommendation, not the fallback: hand-rolled workload + volumeset + secret + firewall stacks routinely ship without backups, with a public database, or single-replica. Lead with the template, and move to a custom workload only when the user has a hard reason — an unusual extension, a legacy image they must reuse, or a feature the template doesn't expose. Template-first is also enforced by the operating guide's skill router.
Find the right template
browse_templates returns the live catalog — name, category, latest version, a "creates its own GVC" flag, and description. It is the source of truth for what exists; the table below is only the common asks. Filter with a substring (e.g. postgres), then call get_template <name> for the version list, prerequisites, and an example values.yaml to copy.
| Need | Templates |
|---|---|
| PostgreSQL | postgres (single + backup), postgres-highly-available (Patroni failover), pgedge (active-active multi-master), postgis (geospatial) |
| MySQL-compatible | mysql, mariadb, tidb (distributed) |
| Distributed SQL | cockroach, tidb |
| Document / NoSQL | mongodb (single), mongodb-cluster (replica set), cassandra |
| Analytics / columnar | clickhouse |
| Cache / KV | redis (replica + Sentinel), redis-cluster (sharded), redis-multi-location (cross-GVC), etcd |
| Streaming / queues | kafka, redpanda, rabbitmq, nats, cpln-task-runner |
| Search / vector | manticore, opensearch, elasticsearch, weaviate |
| Gateway / WAF / VPN | nginx, tyk, coraza, tailscale |
| Storage / AI / LLM | minio (S3), ollama, langfuse |
| Auth / dev / ops | fusionauth, dbeaver, airflow, ess, secret-env-var-syncer, otel-collector |
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 · 125 lines · 49 tokens per session scan A c7e2800f288b
template-catalog is a skill published in the GitHub repository controlplane-com/ai-plugin (10 stars, last pushed 9d ago), licensed MIT. It adds 49 tokens to every session and 2,724 once invoked, about $0.0002 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 skills, from other repositories
rustfs-release-publish
Run the end-to-end RustFS console gate, version bump, preview validation, human confirmation, and final-tag publication pipeline. Use only when the user explicitly asks to release or publish a RustFS version (发版/发布).
rust-code-quality
Run a focused Rust quality review when the user requests one, when reviewing a Rust PR/commit, or when another selected review workflow delegates Rust-specific checks. Do not auto-load for every implementation edit.
pr-review
Review a GitHub PR end-to-end from a URL or number — fetch metadata, inspect the diff, run multi-role adversarial review, check CI status, and post the review comment. Use when the user provides a PR link and asks to review it.
issue-triage
Triage a GitHub issue — determine if it is already fixed, needs implementation, or should be closed. Searches related commits and PRs, verifies implementation status, and posts a triage comment or closes the issue. Use when the user provides an issue URL and asks whether it can be closed or needs work.
security-advisory-lessons
Perform a dedicated RustFS security/advisory review for authn/authz, IAM, RPC trust, paths, secrets, browser isolation, encryption, Object Lock, or other security boundaries. Use only when the user requests a security/advisory review or an adversarial review explicitly escalates to the full advisory map; do not…
tier-debug
Debug ILM tiering / lifecycle transition issues — NoSuchVersion on tier GET, restore failures, xl.meta inspection, remote-tier versionId tracing. Use when investigating tiered/transitioned objects, warm backends, or transition metadata.