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 skillmds/skillmd --skill adpgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/adp)<a href="https://agentmods.dev/skills/skillmds/skillmd/adp"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/adp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/skillmds/skillmd/adp"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/adp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00181 | $0.03207 |
| Opus 5.5 | $0.00072 | $0.01283 |
| Sonnet 5 | $0.00036 | $0.00641 |
| Haiku 4.5 | $0.00018 | $0.00321 |
Grade A, and why
adp 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Data Plane
The Agentic Data Plane is Redpanda's governance infrastructure for AI agents and MCP servers. It is its own product surface: it runs on Redpanda and provisions its own environment when you add it. It provides a managed runtime for AI agents and MCP servers, a proxying AI Gateway for LLM providers, and governance surfaces (budgets, guardrails, Cedar access-control policies) to operate those workloads safely. This skill is written for an AI agent operating the platform programmatically via rpk ai and the Agentic Data Plane API or MCP tools. Optimize for correct field names and service names; confirm the live surface before acting.
Component overview
Maturity note: Redpanda Agentic Data Plane is generally available. Its APIs are on the v1alpha1 version path and carry no LaunchStage annotation in the protos, so treat field-level details as still evolving and confirm them live. The rpk ai CLI is in Preview; InsightsService is Experimental.
AI agents
Managed agents run inside the Agentic Data Plane platform. Self-managed (user-hosted) agents are registered as metadata-only records. Both are managed through AgentRegistryService (proto) or the AIAgentService MCP tool group (v1alpha3). Key fields: model, llm_provider, system_prompt, max_iterations (0-200), mcp_servers (max 32 refs), subagents (max 16). A2A agent cards are published at /.well-known/agent-card.json. Triggers (Teams, Cron) fire agents on external events.
See references/agents.md.
MCP servers
Each MCP server is either REMOTE (you own the upstream) or MANAGED (a pre-integrated catalog entry). The managed catalog covers 7 categories (AI, AWS, Communication, Database, Google, Streaming, Utility) with ~50 managed types; the exact set is gated per cluster, so use ListManagedMCPTypes for the live list. Enabling code_mode on a server adds {name}_search and {name}_execute tools, reducing token usage by 80-90% for large tool sets. Two API layers exist: adp.v1alpha1.MCPServerService (management plane, 9 RPCs) and dataplane.v1alpha3.MCPServerService (public Cloud API, 9 RPCs including Start/Stop/Lint). Knowledge bases are a separate v1alpha3 resource, not a sub-resource of MCP servers.
What ships with it
7 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.
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 · 147 lines · 181 tokens per session scan A c07b5c28b0ba
adp is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 181 tokens to every session and 3,207 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
slopless
Use Slopless to review English Markdown for deterministic AI and human slop signals, including vague phrasing, formulaic prose, weak rhythm, filler, and cliches.
suiko
A Japanese writing and review workflow for checking whether text sounds uniform, translated, unnatural, or difficult to read. It supports writing and editing documents such as reports, guides, meeting notes, proposals, and emails.
poly-lint-and-format
Running poly lint / poly fmt — --fix, --format pretty|json|toon, --exclude, --config, exit codes, inline suppression, and the check → read-json → fix → re-check loop.
poly-orchestrator
Use poly as the single lint/format gate instead of invoking ruff/oxlint/rustfmt directly — one poly.toml, poly hooks install, poly migrate, CI via the Goldziher/poly setup Action.
poly-mcp
The poly MCP server — the eleven tools and which are read-only vs mutating, the paths/exclude/config/format params, async Tasks for the whole-project phase, and the isError contract.
poly-tiers-and-scope
Five mechanisms decide what actually inspects a file (crates/poly-core/src/registry.rs).