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 ilyasibrahim/claude-agents-coordination --skill data-quality-standardsgit clone --depth 1 https://github.com/ilyasibrahim/claude-agents-coordinationWrote 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/ilyasibrahim/claude-agents-coordination/data-quality-standards)<a href="https://agentmods.dev/skills/ilyasibrahim/claude-agents-coordination/data-quality-standards"><img src="https://agentmods.dev/badge/skills/ilyasibrahim/claude-agents-coordination/data-quality-standards/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/ilyasibrahim/claude-agents-coordination/data-quality-standards"><img src="https://agentmods.dev/badge/skills/ilyasibrahim/claude-agents-coordination/data-quality-standards.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.01512 |
| Opus 5 | $0.00029 | $0.00756 |
| Sonnet 5 | $0.00012 | $0.00302 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
data-quality-standards 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Quality Standards for Somali Dialect Classifier
Quality Dimensions
1. Completeness
- All required fields present (text, label, source, timestamp)
- No null or empty text fields
- Labels properly assigned (Northern/Southern/Central)
2. Accuracy
- Text is in Somali (not English, Arabic, or other languages)
- Labels match actual dialect (validated by native speakers)
- Geographic metadata aligns with dialect labels
3. Consistency
- Uniform text encoding (UTF-8)
- Consistent label format (standardized names)
- Timestamp format standardized (ISO 8601)
4. Uniqueness
- No exact duplicates
- Near-duplicate detection (>95% similarity flagged)
- Source URL deduplication
5. Validity
- Text length within acceptable range (10-5000 characters)
- No corrupted/garbled text
- No HTML tags or formatting artifacts
Quality Metrics
Critical Metrics
Language Purity:
- Target: >98% Somali text
- Method: Language detection (langdetect, fastText)
- Action: Remove non-Somali text
Duplicate Rate:
- Target: <2% duplicates
- Method: Exact match + fuzzy matching (Levenshtein distance)
- Action: Keep first occurrence, remove duplicates
Label Confidence:
- Target: >90% inter-annotator agreement
- Method: Multiple annotators for sample
- Action: Re-label low-confidence examples
Text Quality Score:
- Target: Average score >7/10
- Components: Length, vocabulary richness, grammar
- Action: Filter texts with score <5
Validation Pipeline
Stage 1: Basic Validation
def basic_validation(record):
checks = {
'has_text': bool(record.get('text', '').strip()),
'has_label': record.get('label') in ['Northern', 'Southern', 'Central'],
'valid_length': 10 <= len(record.get('text', '')) <= 5000,
'valid_encoding': is_valid_utf8(record['text'])
}
return all(checks.values()), checks
Stage 2: Language Detection
from langdetect import detect
def validate_language(text):
try:
lang = detect(text)
return lang == 'so' # Somali ISO code
except:
return False
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 · 241 lines · 58 tokens per session scan A 2764279fca0c
data-quality-standards is a skill published in the GitHub repository ilyasibrahim/claude-agents-coordination (83 stars, last pushed 3mo ago), licensed Unlicense. It adds 58 tokens to every session and 1,512 once invoked, about $0.0003 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
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.