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 agentmods add skills/ngocsangyem/meowkit/llmsnpx skills add ngocsangyem/MeowKit --skill llmsgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/llms)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/llms"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/llms.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 | $0.00046 | $0.00989 |
| Opus 5 | $0.00023 | $0.00495 |
| Sonnet 5 | $0.00009 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
mk:llms 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 yesterday.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llms.txt Generator
Generate llms.txt files — LLM-friendly markdown indexes of project documentation.
Path convention: Commands below assume cwd is
$CLAUDE_PROJECT_DIR(project root). Prefix paths with"$CLAUDE_PROJECT_DIR/"when invoking from subdirectories.
When to Use
- Project needs LLM-friendly documentation index
- User asks for "llms.txt", "LLM documentation", "AI-friendly docs"
- Publishing docs site and want AI discoverability
- After major documentation updates (Phase 6 Reflect)
Explicit: /mk:llms [path] [--full]
Workflow Integration
Operates in Phase 6 (Reflect) or on-demand. Output supports the documenter agent.
Arguments
| Flag | Effect |
|---|---|
| (no args) | Scan ./docs directory |
path |
Scan specific directory |
--full |
Also generate llms-full.txt with inline content |
--output path |
Custom output location (default: project root) |
--url base |
Base URL prefix for links |
Scripts
Script-first approach — the Python script handles all deterministic work (scanning, extracting, categorizing, generating). Claude only reviews and improves the output.
# Generate llms.txt (script does the heavy lifting)
.claude/skills/.venv/bin/python3 .claude/skills/llms/scripts/generate-llms-txt.py \
--source ./docs [--output .] [--base-url https://example.com/docs] [--full]
# Preview metadata first (Claude reviews before generating)
.claude/skills/.venv/bin/python3 .claude/skills/llms/scripts/generate-llms-txt.py \
--source ./docs --json
Process
- Run script — execute
generate-llms-txt.py --source <path> --jsonto preview metadata - Review metadata — check project name, description, file categorization
- Generate — run script again without
--jsonto produce llms.txt - Review output — read generated llms.txt, improve descriptions if needed
- Validate — check: H1 present, blockquote summary, valid link format, Optional section last
- If
--full: review llms-full.txt for completeness
What ships with it
2 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.
- yesterday First seen · 114 lines · 46 tokens per session scan A 987d620024fa
mk:llms is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 989 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
umap-learn
Use UMAP-learn for nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows.
bulk-rnaseq
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and…
genomic-intelligence
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
pysam
Python/HTSlib workflows for genomic files. Use when reading, querying, filtering, or writing SAM/BAM/CRAM, VCF/BCF, FASTA/FASTQ, or tabix data with pysam, including pileup, coverage, indexing, and CRAM references.