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/enterprise-data-retrievalnpx skills add cxcscmu/SkillLearnBench --skill enterprise-data-retrievalgit 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/enterprise-data-retrieval)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/enterprise-data-retrieval"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/enterprise-data-retrieval.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 | $0.00015 | $0.01074 |
| Opus 5 | $0.00008 | $0.00537 |
| Sonnet 5 | $0.00003 | $0.00215 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
enterprise-data-retrieval 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 6d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enterprise Data Retrieval
Overview
Techniques for finding specific information across multiple enterprise data files (employee records, product files, team information) and aggregating results.
Use Cases
- Finding team members involved in specific projects/products
- Identifying authors and reviewers of documents
- Extracting URLs and resources shared in team communications
- Cross-referencing employee IDs with their information
- Building answer sets from multiple data sources
Directory Structure
/root/DATA/
├── metadata/
│ ├── employee.json # Employee records with IDs and names
│ ├── customers_data.json # Customer information
│ └── salesforce_team.json # Sales team information
└── products/
├── ContentForce.json # Product-specific data (Slack, docs, etc.)
├── SecurityForce.json # Other products...
└── ...
Code Examples
Load All Metadata
import json
import os
def load_metadata():
"""Load all metadata files"""
metadata_path = '/root/DATA/metadata'
metadata = {}
for file in os.listdir(metadata_path):
if file.endswith('.json') and not file.endswith(':Zone.Identifier'):
with open(os.path.join(metadata_path, file), 'r') as f:
metadata[file.replace('.json', '')] = json.load(f)
return metadata
# Usage
metadata = load_metadata()
employees = metadata['employee']
Find Product Data
import json
def load_product_data(product_name):
"""Load product JSON data"""
path = f'/root/DATA/products/{product_name}.json'
with open(path, 'r') as f:
return json.load(f)
# Usage
contentforce_data = load_product_data('ContentForce')
Identify Competitors and Resources
import json
import re
def find_competitor_mentions(product_data):
"""Find all mentions of competitor products"""
competitors = {}
messages = product_data.get('slack', [])
for msg in messages:
text = msg.get('Message', {}).get('text', '')
# Look for competitor product mentions (heuristic: Force/Genie products)
if 'demo' in text.lower() or 'url' in text.lower():
# Extract URLs
urls = re.findall(r'https?://[^\s\)]+', text)
if urls:
user_id = msg.get('Message', {}).get('User', {}).get('userId')
competitors[user_id] = urls
return competitors
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.
- 6d ago First seen · 174 lines · 15 tokens per session scan A bfa6a6a7d777
enterprise-data-retrieval is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,074 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 2026-08-30.
Other skills, from other repositories
agentsop-crewai
SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when modeling agent teams with clear roles and task pipelines.
agentsop-dify
SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. Use when shipping LLM apps fast with a "no-code to pro-code" gradient, especially when non-engineers need to co-author the flow.
agentsop-dspy
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts…
agentsop-framework-selection
Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, not competitors — a…
agentsop-hybrid-retrieval
Enhancement-overlay SOP for adding sparse (BM25 / keyword) retrieval alongside dense (embedding) retrieval. Activate when a calling agent is building, reviewing, or debugging a retrieval pipeline whose corpus contains exact-match tokens — identifiers, error codes, SKUs, API/function names, proper nouns, citations…
agentsop-idempotent-ingestion
Re-ingest-correctness SOP for production RAG. Activate when a calling agent builds, reviews, or debugs an ingestion pipeline that runs more than once over a changing corpus — scheduled re-index, incremental updates, CI re-ingest, or a "retrieval has duplicates / shows deleted docs" bug. Encodes the rule — ingestion…