reviewer-2

reviewer-2 is a skill for Claude Code from dgilford/ai-science-toolkit. It costs 124 tokens per session (1,164 once invoked), scanned A, original, MIT.

A critical review approach for testing whether claims in a result or manuscript section are supported. It compares each claim with a baseline, considers what would happen without the proposed cause or intervention, and checks alternative explanations and uncertainty.

In plain words
What is it for?
Use it to review research findings, scientific writing, climate or causal claims, and any argument that needs a careful check of evidence and uncertainty.
Why use it?
It exposes weak comparisons, missing explanations, and confidence that is stronger than the evidence. It is deliberately skeptical rather than agreeable.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ai-science-toolkit plugin — 21 skills, 4 agents shipped together

Good fit Use it to review research findings, scientific writing, climate or causal claims, and any argument that needs a careful check of evidence and uncertainty.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add dgilford/ai-science-toolkit
Claude Code
/plugin install ai-science-toolkit

Made for: Claude Code.

Or install ai-science-toolkit, the plugin that ships this one along with the rest of its 21 skills, 4 agents.

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 reviewer-2

README.md
[![agentmods](https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/reviewer-2/github.svg)](https://agentmods.dev/skills/dgilford/ai-science-toolkit/reviewer-2)
Your own site
<a href="https://agentmods.dev/skills/dgilford/ai-science-toolkit/reviewer-2"><img src="https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/reviewer-2/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reviewer-2

Your own site · 80×15
<a href="https://agentmods.dev/skills/dgilford/ai-science-toolkit/reviewer-2"><img src="https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/reviewer-2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,164 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 $0.00124 $0.01164
Opus 5 $0.00062 $0.00582
Sonnet 5 $0.00025 $0.00233
Haiku 4.5 $0.00012 $0.00116

Measured 10d ago against content hash 8bd6b36c348b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reviewer-2 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 10d 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.

skills/reviewer-2/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.

Stance

Adversarial, not agreeable. Surfacing weakness is the function. Do not soften findings.

Read the material fresh. Do not carry the user's framing into the review — treat author intent as irrelevant to whether the claim holds.

If the user supplies an inline mode definition in the conversation, adopt that stance fully over these defaults.

Per-claim analysis

For each claim:

  • Baseline — what is being compared against (e.g., pre-industrial frequency, late-20th-century mean)
  • Counterfactual — what the result looks like under natural forcing only, or absent the intervention
  • Alternative explanations — plausible competing interpretations (e.g., urban heat island, land-use change, multidecadal variability)
  • Uncertainty consistency — does stated confidence match the strength of the claim? (yes/no + why)

Example: "Heat extremes in the Southwest are more frequent due to climate change."

  • Baseline: late-20th-century event frequency
  • Counterfactual: frequency under natural forcing only
  • Alternatives: urban heat island; land-use change; multidecadal variability (AMO/PDO)
  • Uncertainty: is stated confidence consistent with formal attribution literature?

Anti-Rationalization

Excuse Reality
"This claim looks well-supported" Did I name the specific counterfactual, or just gesture at it?
"The confidence sounds right" Did I check stated uncertainty against what formal attribution requires, not just the prose framing?
"I don't see an alternative explanation" Did I actively try to construct one, or merely fail to recall one?
"The baseline is obvious" Did I name it explicitly, or assume the reader already knows?

Report

Prioritized concern list, most load-bearing weakness first. For each concern: what it undermines and why it matters.

Claims needing source verification: flag for /lit-review; do not verify here.

Stop when findings become trivial or the user overrides. Do not manufacture concerns to fill space.

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. 10d ago First seen · 90 lines · 124 tokens per session scan A 8bd6b36c348b

Subscribe to this mod's changes

reviewer-2 is a skill published in the GitHub repository dgilford/ai-science-toolkit (62 stars, last pushed 21d ago), licensed MIT. It adds 124 tokens to every session and 1,164 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

metforge-model-diagnose

Diagnose atmospheric-model and dynamical-core experiments. Use for idealized tests, balanced flow, hydrostatic rest, density currents, advection, gravity/acoustic waves, mountain waves, baroclinic instability, conservation and budget closure, error growth, convergence, timestep/resolution/domain/MPI sensitivity…

yuanruichen/MetForge · 135 tokens

metforge-analysis

Perform reproducible atmospheric-science calculations and statistical diagnostics. Use when the agent needs to calculate established or custom climate indices, derive meteorological variables, compute trends, detrend or filter time series, perform EOF/PCA, regression, correlation, composites, bootstrap or significance…

yuanruichen/MetForge · 138 tokens

metforge-data

Acquire and prepare atmospheric, climate, and Earth-system datasets reproducibly. Use when the agent needs to find an authoritative dataset, choose among ERA5/CMIP/GPM/MERRA-2/NOAA or similar products, download or subset NetCDF/GRIB/Zarr data, write CDS/Earthdata/ESGF/OPeNDAP acquisition code, inspect coordinates and…

yuanruichen/MetForge · 119 tokens

metforge-figure

Design, create, revise, and audit atmospheric-science figures. Use for maps, map differences, vertical sections, Hovmöller diagrams, profiles, spectra, budgets, convergence plots, conservation/error-growth diagnostics, ensemble comparisons, and publication multi-panel figures from NetCDF/xarray or tabular data. Also…

yuanruichen/MetForge · 121 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

omh-rust

This is a Hermes-native rust workflow skill.

rlaope/oh-my-hermes · 69 tokens