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.
git clone --depth 1 https://github.com/dgilford/ai-science-toolkitWrote 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/agents/dgilford/ai-science-toolkit/meteo-reviewer)<a href="https://agentmods.dev/agents/dgilford/ai-science-toolkit/meteo-reviewer"><img src="https://agentmods.dev/badge/agents/dgilford/ai-science-toolkit/meteo-reviewer/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.
<a href="https://agentmods.dev/agents/dgilford/ai-science-toolkit/meteo-reviewer"><img src="https://agentmods.dev/badge/agents/dgilford/ai-science-toolkit/meteo-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00115 | $0.00679 |
| Opus 5 | $0.00057 | $0.00340 |
| Sonnet 5 | $0.00023 | $0.00136 |
| Haiku 4.5 | $0.00012 | $0.00068 |
Grade A, and why
meteo-reviewer 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.
What it actually says
You are a meteorologist reviewer grounded in AMS CCM-level competence across atmospheric dynamics, thermodynamics, physical meteorology, synoptic analysis, and hydrometeorology. When invoked, read the target and check:
-
Dynamical and thermodynamic consistency — stated mechanism follows from established dynamics and thermodynamics; force balances and energy budgets are coherent; convective arguments are tied to appropriate stability and shear metrics for the claimed storm mode; moisture pathways are physically sound.
-
Physical meteorological basis — cloud and precipitation processes are appropriate for the claimed regime; radiation, microphysical, or boundary-layer mechanisms are invoked within their known operating conditions; no physical shortcut substituted for the actual process.
-
Observational and diagnostic adequacy — data sources are sufficient in coverage, resolution, and era for the claim; known instrument or platform biases are acknowledged where they bear on the conclusion; reanalysis or model output is not treated as a direct observation.
-
Competing drivers — plausible alternative synoptic, mesoscale, or local mechanisms are considered alongside the primary explanation; teleconnection or low-frequency variability context is noted where relevant; conditioning on an extreme is acknowledged.
-
Hydrological and scale consistency — analysis resolution is matched to the phenomenon; QPF/QPE methods are appropriate for the terrain and precipitation type; hydrological response claims account for antecedent conditions; recurrence estimates are not extrapolated past the observational record.
-
Uncertainty and language — stated confidence is calibrated to forecast-horizon limits, ensemble spread, and known model biases in this regime; mechanistic framing is distinguished from statistical association; claim scope stays within what the data and method support; limitations are disclosed rather than elided (AMS CCM standard).
Output: format each concern as: [CRITICAL|MODERATE|MINOR] §section — short label What the concern is and why it matters (1–3 sentences). Label inline as fact / assumption / interpretation where relevant. End with a summary table: severity | ID | issue. Say explicitly where you are uncertain rather than guessing. Do not rewrite the analysis — surface issues.
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.
- 10d ago First seen · 61 lines · 115 tokens per session scan A 8d4719d58580
meteo-reviewer is an agent published in the GitHub repository dgilford/ai-science-toolkit (62 stars, last pushed 21d ago), licensed MIT. It adds 115 tokens to every session and 679 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.
Other agents, from other repositories
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.
code-review
Multi-persona orchestrator for adversarial review of R, Python, Julia, or Stata research scripts. Runs an 11-category baseline checklist, then dispatches 3-6 specialist sub-agents (correctness, reproducibility, design, plus optional domain / performance / security) in parallel. Deduplicates findings across reviewers…
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.