deephaven-mcp: Skill for Claude Code

.agents/skills/skill-review/SKILL.md

skill-review is a skill for Claude Code, Codex from deephaven/deephaven-mcp. It costs 84 tokens per session (2,520 once invoked), scanned A, original, Apache-2.0.

A review tool for an agent skill file or AGENTS.md, the project instructions file used by coding agents.

In plain words
What is it for?
Use it when auditing or editing skills and project instructions, with findings grouped into architecture, effectiveness, and structure.
Why use it?
It finds unclear instructions, structural problems, duplicated guidance, and links that no longer fit together.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; installed under .agents/ (shared by several agents).

This is deephaven/deephaven-mcp's own configuration. It tells Claude Code and Codex how to work on deephaven-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything deephaven-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/deephaven/deephaven-mcp/main/.agents/skills/skill-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/deephaven/deephaven-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for skill-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/deephaven/deephaven-mcp/skill-review.svg)](https://agentmods.dev/skills/deephaven/deephaven-mcp/skill-review)
Your own site
<a href="https://agentmods.dev/skills/deephaven/deephaven-mcp/skill-review"><img src="https://agentmods.dev/badge/skills/deephaven/deephaven-mcp/skill-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,520 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.02520
Opus 5 $0.00042 $0.01260
Sonnet 5 $0.00017 $0.00504
Haiku 4.5 $0.00008 $0.00252

Measured 6d ago against content hash 4f1060bbb6bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-review 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.

.agents/skills/skill-review/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review an Agent Skill or AGENTS.md

Review like a senior engineer. Every finding must answer three questions in concrete terms: what is wrong, what is better, why the change is worth its cost. Be conscious of suggestions that do not serve a purpose.

Wraps ref-skill-authoring-standards (structural standards), ref-skill-effectiveness (content standards), and ref-agents-md-curation (when the target is AGENTS.md). Effectiveness and composition are co-headline audits; structure is the supporting audit.

The findings report has three subsections — Architecture, Effectiveness, Structure — so the user can act on each axis independently. Architecture findings extract or merge skills; effectiveness findings rewrite descriptions and bodies; structural findings are surgical fixes.

Steps

  1. Identify the target. Is this a skill file (.agents/skills/<name>/SKILL.md) or AGENTS.md? Branch on the answer:

    • Skill: apply ref-skill-authoring-standards + ref-skill-effectiveness.
    • AGENTS.md: apply ref-agents-md-curation + ref-skill-effectiveness.
  2. Composition audit (Architecture). Two non-negotiable refactoring questions; each gets an explicit answer in the report.

    • Should material in this skill move into a sub-skill? Triggers: a section covering a discrete sub-concern that a given invocation rarely needs; a section paraphrased in another skill; a section conceptually independent with its own trigger.
    • Should material in a sub-skill move out of it? Triggers: the sub-skill is referenced by exactly one parent, or has no independent trigger. Size is not a trigger on its own — a short skill that encodes one real gotcha is a good skill.
    • Are the children correct? Skills this one invokes must each contribute their concern. Drift signal: an Apply <skill> line that does not carry weight in the body.
    • Are the parents correct? Skills that invoke this one must each have a real reason to. Drift signal: a parent that wraps in name only.
    • Synthesis: would an agent invoking this skill waste tokens reading content it does not need (extract), or take an extra hop for content it always needs (merge)?

Read the full file on GitHub · 90 lines

Changes

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.

  1. 6d ago First seen · 90 lines · 84 tokens per session scan A 4f1060bbb6bf

Subscribe to this mod's changes

skill-review is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 84 tokens to every session and 2,520 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.