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/skill-review/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/skill-review)<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>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 | $0.00084 | $0.02520 |
| Opus 5 | $0.00042 | $0.01260 |
| Sonnet 5 | $0.00017 | $0.00504 |
| Haiku 4.5 | $0.00008 | $0.00252 |
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.
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
-
Identify the target. Is this a skill file (
.agents/skills/<name>/SKILL.md) orAGENTS.md? Branch on the answer:- Skill: apply
ref-skill-authoring-standards+ref-skill-effectiveness. AGENTS.md: applyref-agents-md-curation+ref-skill-effectiveness.
- Skill: apply
-
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)?
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 · 90 lines · 84 tokens per session scan A 4f1060bbb6bf
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.