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 skills add yuanruichen/MetForge --skill metforge-model-diagnosegit clone --depth 1 https://github.com/yuanruichen/MetForgeWrote 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/yuanruichen/metforge/metforge-model-diagnose)<a href="https://agentmods.dev/skills/yuanruichen/metforge/metforge-model-diagnose"><img src="https://agentmods.dev/badge/skills/yuanruichen/metforge/metforge-model-diagnose.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 | $0.00135 | $0.01295 |
| Opus 5 | $0.00068 | $0.00647 |
| Sonnet 5 | $0.00027 | $0.00259 |
| Haiku 4.5 | $0.00014 | $0.00129 |
Grade A, and why
metforge-model-diagnose 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 7d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MetForge Model Diagnose
Turn model output into a falsifiable diagnosis. Prefer the next decisive check over a long catalog of generic plots.
Diagnostic workflow
- State the test contract:
- property or mechanism being tested
- expected solution, symmetry, invariant, or benchmark
- control and changed factor
- diagnostic time window and success criterion
- observation that would falsify the working explanation
- Inventory the actual run configuration and outputs. Compare namelists, compiler/precision, solver, grid, timestep, domain, boundary conditions, physics, diffusion, filters, and decomposition before interpreting differences.
- Establish the reference. Prefer an analytic solution, converged/high-resolution run, published benchmark, or internally consistent control. Do not call one arbitrary run “truth” without qualification.
- Climb the diagnostic ladder below. Stop when the evidence isolates the failure or when the next step requires new data.
- Classify each result as expected, numerically suspicious, physically inconsistent, configuration-dependent, or inconclusive.
- Produce an evidence table and recommend one next experiment with the largest discrimination value.
Diagnostic ladder
1. Integrity
Check file completeness, coordinates, units, time cadence, NaN/Inf, extrema, restart continuity, and whether the intended code path actually ran.
2. Invariants and equilibrium
Check mass, tracer mass, energy or energy-like quantities, hydrostatic/geostrophic balance residuals, symmetry, uniform-state preservation, and boundary fluxes as appropriate.
3. Error magnitude and growth
Use more than extrema. Select metrics from references/diagnostic-metrics.md, including weighted bias, RMS/L2, maximum norm, drift rate, relative error, pattern correlation, phase displacement, and conservation residual.
4. Structure
Examine the error field, cross-flow components, vertical structure, spectra, wavenumber content, propagation speed, fronts, and symmetry breaking. Scalar norms can miss compensating or phase-shifted errors.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 94 lines · 135 tokens per session scan A d07aa0b9c967
metforge-model-diagnose is a skill published in the GitHub repository yuanruichen/MetForge (4 stars, last pushed 25d ago), licensed MIT. It adds 135 tokens to every session and 1,295 once invoked, about $0.0007 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
lit-review
Search and synthesize scientific literature from Zotero, arxiv, bioRxiv, Google Scholar, and Consensus. Use when framing a research question, designing methods, interpreting results, mapping the field landscape, or identifying future directions.
figure-style
Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…
paper-narrative
Judge and reshape the story told by an entire paper figure deck. Use when writing or revising a paper to derive a grounded brief from the manuscript and captions, review the full deck as a handling editor, and hand an ordered figure arc to figure-composer.
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
esmfold2
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release…
literature-review
Find, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.