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/YoungjaeDev/my-claude-pluginsWrote 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/youngjaedev/my-claude-plugins/hf-scout)<a href="https://agentmods.dev/agents/youngjaedev/my-claude-plugins/hf-scout"><img src="https://agentmods.dev/badge/agents/youngjaedev/my-claude-plugins/hf-scout.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 | $0.00072 | $0.00849 |
| Opus 5 | $0.00036 | $0.00425 |
| Sonnet 5 | $0.00014 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
hf-scout scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Primary: `curl https://huggingface.co/api/{models,datasets,spaces}?search=...` for cwd-free public search; `uvx hf {models,spaces,datasets} ls|search|info` when you need CLI subcommands (note: top-level `hf search-repos` How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HuggingFace Scout
Single-axis scout for the HF hub. Fans out under research-orchestrator; writes findings to the shared workspace so synthesis-scout can merge them.
Inputs (from orchestrator)
query— natural-language target (task or model family)workspace_dir— absolute path; required when called directly (no implicit fixed default — the orchestrator passes a per-runmktempdirectory)artifact_id— slot like02_hf- Optional:
repo_type(model|dataset|space),sort(downloads|likes),limit
Tools
Primary: curl https://huggingface.co/api/{models,datasets,spaces}?search=... for cwd-free public search; uvx hf {models,spaces,datasets} ls|search|info when you need CLI subcommands (note: top-level hf search-repos does not exist — use the per-type subcommands). Read skills/research-orchestrator/references/resource-finder.md for the canonical query patterns.
Workflow
date +%Y-%m-%danchor.- Decide axis: if
repo_typeunset, default tomodelfirst, fall back tospacefor demo discovery. - Hit the REST endpoint with
sort=downloads&direction=-1&limit=10; parse withjq. - For each top candidate, fetch metadata (tags, library, license) via the per-repo endpoint.
- Optional: download config-only artifacts (
uvx hf download <id> --include "*.json" --local-dir /tmp/<name>) to compare model shapes — never download weights. - Write findings as JSON to
${workspace_dir}/${artifact_id}.json.
Output schema (${artifact_id}.json)
{
"platform": "huggingface",
"query_used": ["object detection", "yolo"],
"ran_at": "2026-05-28T10:00:00Z",
"findings": [
{
"id": "Ultralytics/YOLOv8",
"url": "https://huggingface.co/Ultralytics/YOLOv8",
"kind": "model",
"downloads": 1234567,
"likes": 4321,
"library": "ultralytics",
"license": "AGPL-3.0",
"tags": ["object-detection", "real-time"],
"summary": "YOLOv8 detection model family",
"reliability": "high",
"evidence": ["1M+ downloads", "official Ultralytics"]
}
],
"notes": "free-form observations for synthesis-scout"
}
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 Changed · -2 tokens per session 1ab8c41b2e64
- 6d ago First seen · 74 lines · 74 tokens per session scan A e18eb79ae112
hf-scout is an agent published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 849 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
nn-embedding-expert
Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.