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/cxcscmu/skilllearnbench/data-filteringnpx skills add cxcscmu/SkillLearnBench --skill data-filteringgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/data-filtering)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/data-filtering"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/data-filtering.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 | $0.00014 | $0.01251 |
| Opus 5 | $0.00007 | $0.00626 |
| Sonnet 5 | $0.00003 | $0.00250 |
| Haiku 4.5 | $0.00001 | $0.00125 |
Grade A, and why
data-filtering 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 2d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Filtering Skill
Overview
Filter travel data by specific criteria like pet-friendly status, cuisine type, location, and price range.
Common Filter Scenarios
Accommodations
- Pet-friendly filter
- Price range (budget, mid-range, luxury)
- Location (city, zip code)
- Amenities (WiFi, parking, breakfast)
Restaurants
- Cuisine type (American, Mediterranean, Chinese, Italian, etc.)
- Location/city
- Price range
- Rating/reviews
Attractions
- City location
- Category (museum, park, historical, etc.)
- Open during trip dates
Python Code Example
from typing import List, Dict
import re
def filter_pet_friendly_accommodations(
accommodations: List[Dict],
pet_friendly_field: str = 'pet_friendly'
) -> List[Dict]:
"""Filter accommodations that allow pets"""
result = []
for acc in accommodations:
pet_field = acc.get(pet_friendly_field, '').lower()
# Handle various formats: 'yes', 'true', '1', 'pet-friendly'
if pet_field in ['yes', 'true', '1', 'pet friendly', 'pets allowed']:
result.append(acc)
elif 'pet' in pet_field and 'no' not in pet_field:
result.append(acc)
return result
def filter_by_cuisine(
restaurants: List[Dict],
cuisine_type: str,
cuisine_field: str = 'Cuisine'
) -> List[Dict]:
"""Filter restaurants by cuisine type"""
result = []
cuisine_lower = cuisine_type.lower()
for rest in restaurants:
cuisines = rest.get(cuisine_field, '').lower()
# Handle comma-separated cuisines
if ',' in cuisines:
cuisines_list = [c.strip() for c in cuisines.split(',')]
if any(cuisine_lower in c for c in cuisines_list):
result.append(rest)
elif cuisine_lower in cuisines:
result.append(rest)
return result
def filter_by_city(
data: List[Dict],
city: str,
city_field: str = 'City'
) -> List[Dict]:
"""Filter data by city"""
result = []
city_lower = city.lower()
for item in data:
item_city = item.get(city_field, '').lower()
if item_city == city_lower:
result.append(item)
return result
def filter_by_price_range(
data: List[Dict],
min_price: float,
max_price: float,
price_field: str = 'Price'
) -> List[Dict]:
"""Filter data by price range"""
result = []
for item in data:
try:
price = float(item.get(price_field, 0))
if min_price <= price <= max_price:
result.append(item)
except (ValueError, TypeError):
continue
return result
def filter_attractions_by_city(
attractions: List[Dict],
city: str,
city_field: str = 'City'
) -> List[Dict]:
"""Filter attractions by city"""
return filter_by_city(attractions, city, city_field)
def combine_filters(
data: List[Dict],
filters: Dict
) -> List[Dict]:
"""
Apply multiple filters to data.
filters dict: {'city': 'Cleveland', 'price_max': 100, ...}
"""
result = data
# Apply city filter
if 'city' in filters:
result = filter_by_city(
result,
filters['city'],
filters.get('city_field', 'City')
)
# Apply price range filter
if 'price_min' in filters or 'price_max' in filters:
min_price = filters.get('price_min', 0)
max_price = filters.get('price_max', float('inf'))
result = filter_by_price_range(
result,
min_price,
max_price,
filters.get('price_field', 'Price')
)
# Apply cuisine filter
if 'cuisine' in filters:
result = filter_by_cuisine(
result,
filters['cuisine'],
filters.get('cuisine_field', 'Cuisine')
)
return result
def select_diverse_options(
data: List[Dict],
num_selections: int,
key_field: str = 'Name'
) -> List[Dict]:
"""Select diverse options avoiding duplicates"""
seen = set()
result = []
for item in data:
key = item.get(key_field, '').lower()
if key not in seen:
seen.add(key)
result.append(item)
if len(result) >= num_selections:
break
return result
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.
- 2d ago First seen · 201 lines · 14 tokens per session scan A b6d82fb61207
data-filtering is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 1,251 once invoked, about $0.0001 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
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.
content-creator-setup
One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.
github
GitHub API integration via HTTP tool with automatic credential injection.
idea-parking
Park interesting ideas for later consideration, resurface them periodically, and promote to commitments when ready.
agentsop-llamaindex
Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers…
agentsop-llm-artifact-versioning
Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model snapshot pins + retrieval config + eval-set version, versioned together so a deploy is reproducible and rollback is atomic. Activate when preparing to deploy an LLM app, when asking "what exactly is…