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 jmschrei/tangermeme --skill datagit clone --depth 1 https://github.com/jmschrei/tangermemeWrote 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/jmschrei/tangermeme/data)<a href="https://agentmods.dev/skills/jmschrei/tangermeme/data"><img src="https://agentmods.dev/badge/skills/jmschrei/tangermeme/data/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/skills/jmschrei/tangermeme/data"><img src="https://agentmods.dev/badge/skills/jmschrei/tangermeme/data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00147 | $0.01179 |
| Opus 5.5 | $0.00059 | $0.00472 |
| Sonnet 5.5 | $0.00029 | $0.00236 |
| Haiku 4.5 | $0.00015 | $0.00118 |
Grade A, and why
tangermeme 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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tangermeme
Post-training analysis of any PyTorch sequence model: batched prediction, attribution, perturbation experiments, sequence design, on raw outputs with no distance baked in. This file routes; the reference files hold the signatures, defaults and silent failures. Read the file for the task before writing code: several defaults select the wrong output, return a variable number of objects, or run zero iterations without a word.
Task to reference file
| task | read |
|---|---|
| attribution via DeepLIFT/SHAP: which bases drive this prediction, logos, hypothetical scores for CWMs, references, memory | references/deep_lift_shap.md |
| a convergence delta warning, a transformer, attention pooling, a functional softmax or product, a custom module, "are these attributions correct" | references/deep_lift_shap-unhooked-ops.md and scripts/audit_deeplift.py |
ISM / saturation mutagenesis, fast=True |
references/saturation_mutagenesis.md |
| saliency (input x gradient, one backward pass) and dependency maps (epistasis, motif-flank interactions) | references/dependency_map.md |
| PISA: attribution of every output position | references/pisa.md |
| effect of a motif or region: marginalize, ablate, spacing; choosing backgrounds | references/motif-effects.md |
| variant effects from a VCF: substitution, deletion, insertion | references/variant-effect.md |
| seqlets from attributions, choosing a threshold with a control | references/seqlets.md |
| motif labels and counts: TOMTOM, co-occurrence, spacing | references/annotate.md |
| logos with seqlet or motif annotations | references/plot.md |
| a function over a product of inputs (sequence x cell state x depth) | references/product.md |
composing predict / attribution through a perturbation (func=, additional_func_kwargs, args=) |
references/func-pattern.md |
| a model with several inputs or outputs, a profile head, a control track; N models in one sweep | references/model-wrapping.md |
| loading loci, FASTA, bigWig, MEME, VCF; GC-matched background loci; window to genome coordinates | references/io-loci.md |
editing sequences: insert, substitute, delete, shuffle, random draws, reverse complement, one-hot, PackedSequence |
references/ersatz.md |
| designing sequences to a target output: screen, greedy, beam | references/design.md |
What ships with it
17 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.
- references/annotate.md 2.5 KB
- references/deep_lift_shap-unhooked-ops.md 5.6 KB
- references/deep_lift_shap.md 5.8 KB
- references/dependency_map.md 2.7 KB
- references/design.md 3.4 KB
- references/ersatz.md 2.6 KB
- references/func-pattern.md 2.5 KB
- references/io-loci.md 3.7 KB
- references/model-wrapping.md 2.5 KB
- references/motif-effects.md 3.0 KB
- references/pisa.md 1.3 KB
- references/plot.md 1.9 KB
- references/product.md 1.8 KB
- references/saturation_mutagenesis.md 2.6 KB
- references/seqlets.md 3.0 KB
- references/variant-effect.md 2.8 KB
- scripts/audit_deeplift.py 6.1 KB runs code
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.
- 4d ago Changed · -37 lines · +20 tokens per session 5353746af945
- 5d ago Changed · +4 lines c6470452a5f0
- 11d ago Changed a56271b90e7c
- 12d ago Changed · +1 lines 0e7efe837607
- 21d ago Changed ca7574e7854c
- 24d ago Changed · +2 lines e3f05c0e73c4
- 29d ago Changed · +2 lines 39eab7a84476
- 1mo ago Changed b79c5b91d0e3
- 1mo ago First seen · 90 lines · 127 tokens per session scan A e8b7311cee6b
tangermeme is a skill published in the GitHub repository jmschrei/tangermeme (329 stars, last pushed 3d ago), licensed MIT. It adds 147 tokens to every session and 1,179 once invoked, about $0.0006 per session on Opus 5.5. 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 skills, from other repositories
arboreto
Infers candidate gene regulatory networks from bulk or single-cell expression data using AertsLab Arboreto GRNBoost2 and GENIE3. Use for transcription factor-target association ranking, compatible Dask execution, sparse expression inputs, and network stability checks.
deepspot-m
Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1p-CPM expression from 224x224 tiles at about 20x, querying the released protein-coding gene panel by symbol, and whole-slide prediction after resolution-aware tiling with histolab.
torchdrug
Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
pyhealth
Builds and validates PyHealth clinical machine-learning pipelines for EHR, signals, imaging, and medical codes. Use for PyHealth dataset loading, MIMIC-III/IV, eICU or OMOP prediction tasks, patient-level evaluation, mortality/readmission/length-of-stay modeling, medication recommendation, sleep staging, Trainer…
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.