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/deephaven/deephaven-mcp/ref-cli-design-prior-artnpx skills add deephaven/deephaven-mcp --skill ref-cli-design-prior-artgit clone --depth 1 https://github.com/deephaven/deephaven-mcpWrote 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/deephaven/deephaven-mcp/ref-cli-design-prior-art)<a href="https://agentmods.dev/skills/deephaven/deephaven-mcp/ref-cli-design-prior-art"><img src="https://agentmods.dev/badge/skills/deephaven/deephaven-mcp/ref-cli-design-prior-art.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 | $0.00060 | $0.00751 |
| Opus 5 | $0.00030 | $0.00376 |
| Sonnet 5 | $0.00012 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
ref-cli-design-prior-art 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI design prior art
dhcli is a resource-oriented CLI competing for muscle memory with kubectl, docker, gh, aws, gcloud, and git. A user who already knows those tools should be able to guess how this one behaves. Every design decision either follows an established convention or deliberately departs from one — and the difference must be visible in the artifact, not just in the author's head.
The rule
When a design decision has an established convention in a comparable tool, follow it, and cite the tool and the specific behavior.
- Cite the behavior, not the vibe. "
kubectl deleteprompts only under--interactive" is a citation. "kubectl-style" is not — it conveys nothing a reader can check or apply. - A citation must be verifiable. Name the flag, the subcommand, or the observable behavior, so a reader can confirm it against that tool's documentation or source. An uncheckable citation is worse than none: it borrows authority it has not earned.
- When diverging, say so and give the reason. A departure is a legitimate design choice; an undocumented departure reads as ignorance of the convention and invites someone to "fix" it later.
- Do not invent a convention. If no comparable tool does the thing, that is worth knowing — say the decision is ours and justify it on its own terms. Asserting an unattributed "this is conventional" is folklore (
ref-skill-effectivenessAnti-patterns checklist).
What is in scope
Noun and verb naming, flag naming and short forms, argument-versus-flag choices, default values, confirmation and interactivity behavior, output-format conventions, and exit-code semantics.
Where the decisions live
This skill holds the rule. The decisions and their rationale live in docs/design/CLI_TOOL_WRAPPING.md — that is the document to read for what was already decided and why, and the document to extend when a new decision is made.
Canonical citations already in the codebase:
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 · 37 lines · 60 tokens per session scan A 6fc495e49132
ref-cli-design-prior-art is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 751 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…