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 oaustegard/claude-skills --skill hallucinating-labelsgit clone --depth 1 https://github.com/oaustegard/claude-skillsWrote 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/oaustegard/claude-skills/hallucinating-labels)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/hallucinating-labels"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/hallucinating-labels/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/oaustegard/claude-skills/hallucinating-labels"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/hallucinating-labels.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 | $0.00186 | $0.02962 |
| Opus 5 | $0.00093 | $0.01481 |
| Sonnet 5 | $0.00037 | $0.00592 |
| Haiku 4.5 | $0.00019 | $0.00296 |
Grade A, and why
hallucinating-labels 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 9d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hallucinating-labels
Ask a cheap model to write a plausible label for the item. Snap that label onto the real vocabulary with an embedder. The model never sees the label set.
Doug Turnbull's pattern (softwaredoug.com, 2026-08-10), with the two prompt and boundary corrections that measurement produced.
Check the boundary first
If the whole vocabulary fits in a prompt, do not use this skill. Ship the label list and ask for a constrained choice. Measured on WANDS (860 labels, 468 queries, one gold label each, gemini-3.5-flash-lite):
| approach | acc@1 | acc@3 | input tokens/item |
|---|---|---|---|
| structured output, all 860 labels shipped | 0.701 | 0.744 | 5,265 |
| this skill | 0.564 | 0.690 | 6 |
| embed the item directly, no model | 0.417 | 0.564 | 0 |
Shipping the vocabulary is 14 points more accurate and 880× more expensive. Take the accuracy unless the tokens are the problem. The tokens are the problem when the vocabulary does not fit, when a provider enum cap rejects it, or when per-call cost at volume dominates — a 5,000-label vocabulary is roughly 30k tokens on every single call.
This skill still beats every model-free baseline by a wide margin, so it is the right tool whenever shipping the vocabulary is off the table.
Procedure
1. Write the vocabulary to a file, one label per line, and index it once.
python3 scripts/snap.py build --vocab categories.txt --out .snap-index.pkl
Default backend is tfidf — sklearn only, no download. Pass --backend minilm when
sentence-transformers and a ~90 MB download are available and the items share no wording
with the labels; it scored 0.564 to tfidf's 0.528 on WANDS. Where items literally contain
their own label words, tfidf wins outright (0.416 vs 0.356 on a memory-tag corpus).
2. Write the labels yourself, in batches of 40, using the register prompt below. Write them to a file, one per line, in the same order as the items.
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.
- 9d ago First seen · 217 lines · 186 tokens per session scan A 504f0a4c678e
hallucinating-labels is a skill published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed yesterday), licensed MIT. It adds 186 tokens to every session and 2,962 once invoked, about $0.0009 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
recsys-pipeline-architect
Designs composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by X's open-sourced For You algorithm. Use this skill when the user wants to build any system that picks "the top K items for a user/context" — content feeds…
prompt-engineering
Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. This skill should be used when users request prompt creation, optimization, or improvement for any LLM task, or when users need help translating vague requirements into effective prompts through collaborative dialogue and…
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.
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…
shap
Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global SHAP visualizations.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…