Borrowing it
Nothing to install: this file belongs to deephaven/deephaven-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/deephaven/deephaven-mcp/main/.agents/skills/ref-skill-authoring-standards/SKILL.mdgit 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-skill-authoring-standards)<a href="https://agentmods.dev/skills/deephaven/deephaven-mcp/ref-skill-authoring-standards"><img src="https://agentmods.dev/badge/skills/deephaven/deephaven-mcp/ref-skill-authoring-standards.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 | $0.00073 | $0.05062 |
| Opus 5 | $0.00036 | $0.02531 |
| Sonnet 5 | $0.00015 | $0.01012 |
| Haiku 4.5 | $0.00007 | $0.00506 |
Grade A, and why
ref-skill-authoring-standards 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 6d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring Standards (Structural)
This document defines the structural standards for files under .agents/skills/<name>/SKILL.md. It is loaded by skill-add and skill-review. Content-quality rules (triggerability, actionability, clarity, anti-patterns) live in ref-skill-effectiveness; this document covers form and architecture.
The frontmatter description field is the only text the agent sees at decision time — every other concern here is downstream of getting the description right. Apply ref-skill-effectiveness Triggerability for description quality before applying any of the structural rules below.
Sources
These standards are a delta on published guidance, not a local invention. Where a rule below traces to a source, it is cited; where it has no upstream equivalent, it is a project-specific addition and says so. A rule with neither a source nor a named failure it prevents is folklore — delete it (ref-skill-effectiveness Anti-patterns checklist).
Precedence order, highest first:
- Agent Skills specification — the portable format. Binding for anything cross-agent.
- Skill authoring best practices — authoring guidance and the Checklist for effective Skills. The standing standard where sources conflict.
- Claude Code skills — Claude-specific frontmatter and invocation control.
- Cascade skills — Windsurf / Devin Desktop discovery and invocation.
- Context engineering for Claude 5 generation models — model-specific, and a blog rather than a spec. Cite only where a rule is genuinely blog-specific.
Inline the actionable rule; link the rationale. A skill must work offline, and an external URL is not a loadable disclosure level — it needs network the sandbox may not have and can redirect or 404. Copying upstream's worked examples in is the opposite error.
What ships with it
1 file 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.
- 6d ago First seen · 209 lines · 73 tokens per session scan A d8b6876843e0
ref-skill-authoring-standards is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 5,062 once invoked, about $0.0004 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…