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-agents-md-curationnpx skills add deephaven/deephaven-mcp --skill ref-agents-md-curationgit 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-agents-md-curation)<a href="https://agentmods.dev/skills/deephaven/deephaven-mcp/ref-agents-md-curation"><img src="https://agentmods.dev/badge/skills/deephaven/deephaven-mcp/ref-agents-md-curation.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 | $0.00052 | $0.01103 |
| Opus 5 | $0.00026 | $0.00551 |
| Sonnet 5 | $0.00010 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
ref-agents-md-curation 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md Curation
AGENTS.md is the always-on ruleset loaded as a system memory at the start of every session. It is a distinct artifact from skills: skills are on-demand and triggered by description; AGENTS.md is unconditional and read by every reader. This skill defines what belongs in it, how it stays in sync with the skill catalog, and when content moves between the two.
Content quality of AGENTS.md bullets is governed by ref-skill-effectiveness (triggerability does not apply to AGENTS.md itself — every reader reads it — but actionability, outcome orientation, hedge-word audit, and clarity all do).
1. Role
AGENTS.md carries the universal facts every task needs before doing anything. It is read every session, by every reader. It is not a skill catalog and not a procedure manual.
2. What belongs in AGENTS.md
- Universal facts every task uses (Python floor pointer, server commands and ports, config directory layout,
uv run pytestconvention). - Project-wide conventions an agent must know unconditionally (
git mvfor renames,uv runfor tooling). - One-line pointers to authoritative sources:
pyproject.toml,docs/CLI.md, named skills.
3. What does NOT belong in AGENTS.md
- A procedure an agent follows only in a specific situation → factor into a workflow skill. The test is how often it is needed, not how many bullets it takes: the CLI and MCP-configuration sections here are long and stay, because every task touches them.
- Per-domain coding standards → factor into a
ref--prefixed reference skill (ref-python-coding-practices,ref-logging-standards, …). - Anything an agent needs only when working in a specific subsystem → load on demand via skill, not unconditionally.
4. Format conventions
- Terse bullets. Short H2 sections.
- When listing a fact that a skill owns, point to the skill rather than restating: "Apply
ref-configuration-conventionsbefore adding a new tunable." - JSON and code blocks follow the markdown documentation standards in
ref-markdown-documentation-standards. - No hedge words; no decorative language (
ref-skill-effectivenessClarity and writing standards).
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 · 68 lines · 52 tokens per session scan A 058c8bee1eb7
ref-agents-md-curation is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 1,103 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…