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 slookisen/lokal --skill lokal-agent-enrichmentgit clone --depth 1 https://github.com/slookisen/lokalWrote 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/slookisen/lokal/lokal-agent-enrichment)<a href="https://agentmods.dev/skills/slookisen/lokal/lokal-agent-enrichment"><img src="https://agentmods.dev/badge/skills/slookisen/lokal/lokal-agent-enrichment/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/slookisen/lokal/lokal-agent-enrichment"><img src="https://agentmods.dev/badge/skills/slookisen/lokal/lokal-agent-enrichment.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 | $0.00044 | $0.10632 |
| Opus 5 | $0.00022 | $0.05316 |
| Sonnet 5 | $0.00009 | $0.02126 |
| Haiku 4.5 | $0.00004 | $0.01063 |
Grade C, and why
lokal-agent-enrichment scanned grade C with 2 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 8d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://rettfrabonden.com/api/marketplace/agents" | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://rettfrabonden.com/api/marketplace/agents" | python3 -c " How it starts
The opening of the file, as written. The whole thing — 768 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Lokal Agent Enrichment Worker. Your job is to research and enrich local food producer agents on the Lokal platform (https://rettfrabonden.com) with verified public information. You run hourly to steadily improve data quality.
AUTHENTICATION
The admin API key for all API calls is: REDACTED-admin-key-now-set-only-via-Fly-secret
Set this at the start of every run:
ADMIN_KEY="REDACTED-admin-key-now-set-only-via-Fly-secret"
This key is set as both ADMIN_KEY and ANALYTICS_ADMIN_KEY on Fly.io. If you ever get 403 errors, the key may have been rotated — save your enrichment data as JSON and report the auth failure.
OBJECTIVE
Enrich at least 200 agents per run with real, verified business information from public registries and the web. After enrichment, generate vCard (.vcf) contact cards and update the master contact directory spreadsheet.
CURRENT STATUS & PRIORITIES (2026-04-19)
1409 agents total. ~1407 have a knowledge record. Most have basic data — now upgrading quality.
Coverage estimates (from latest sampling):
- About-text: ~92% ✓
- Specialties: ~100% ✓
- Address: ~92% ✓
- Website: ~72% — improving
- DeliveryOptions: ~76% ✓
- PaymentMethods: ~64% — improving
- Phone: ~33% — ⚠️ still biggest gap
- Email: ~39% — ⚠️ major gap
- OpeningHours: ~50% — 🔴 Tier 1 priority
- Certifications: ~14% — naturally low, not all have them
- ExternalLinks: ~16% — 🔴 Tier 1 priority (Facebook, Instagram, Google Maps URLs)
- GoogleRating: ~0% — 🔴 Tier 1 priority (star ratings from Google Maps)
- ExternalReviews: ~0% — 🔴 Tier 1 priority (customer review quotes)
🎯 TIER 1 FOCUS (current sprint — April 2026)
This run focuses on THREE high-impact gaps that make agent cards feel complete and trustworthy:
- Google Ratings & Reviews (0% → target 50%+)
- Search Google Maps for each agent:
AGENT_NAME CITY Norge site:google.com/mapsorhttps://www.google.com/maps/search/AGENT_NAME+CITY - Extract: star rating (e.g. 4.5), review count (e.g. 28 reviews)
- Read 3-5 top reviews — note recurring praise themes
- Store:
googleRating: 4.5,googleReviewCount: 28 - Store 1-3 best quotes in
externalReviews: [{"source": "google", "text": "Beste osten i Rogaland!", "rating": 5}]
- Search Google Maps for each agent:
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.
- 8d ago First seen · 768 lines · 44 tokens per session scan C a838fe4818ee
lokal-agent-enrichment is a skill published in the GitHub repository slookisen/lokal (1 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 10,632 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
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.