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/parthakker/nfl-analytics/refresh-datanpx skills add parthakker/nfl-analytics --skill refresh-datagit clone --depth 1 https://github.com/parthakker/nfl-analyticsWhat 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 | $0.00014 | $0.00259 |
| Opus 5 | $0.00007 | $0.00130 |
| Sonnet 5 | $0.00003 | $0.00052 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
refresh-data 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.
What it actually says
Refresh data
- Preflight: make sure nothing holds a write lock — explore.cmd (DuckDB UI)
must be closed; check
logs/refresh.logtail for an already-running refresh. - Run
python -m nfl_analytics.cli refresh $ARGUMENTS- no flag: weekly mode (current + last season assets + schedules)
--full: every season in the manifest--bootstrap: fresh-clone download (~2 GB, resumable) This downloads, runs fetch_weather, rebuilds warehouse + views, snapshots Vegas lines.
- Verify: the build output must end with "All tables loaded" and
"travel sanity OK"; then run
python -m pytest -m warehouse -q. - Report: assets fetched, any FAILURES lines, row-count anomalies, and the refresh.log line. If a download failed with "no candidate matched", nflverse likely renamed an asset — check their releases page before editing the manifest in scripts/refresh_data.py.
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 · 24 lines · 14 tokens per session scan A 84839b722905
refresh-data is a skill published in the GitHub repository parthakker/nfl-analytics (0 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 259 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 2026-08-31.
Other skills, from other repositories
portaljs-add-geo
Auto-ingest a geospatial file (GeoJSON, Shapefile, GeoPackage, KML/KMZ, FlatGeobuf, CSV-with-geometry) into a PortalJS portal on the user's own machine, with no server. Normalizes CRS to EPSG:4326, derives a PMTiles render tier and a GeoParquet query tier, pushes all three artifacts to Cloudflare R2 via Git LFS, and…
generate-mdl
Generate a Wren MDL project by exploring a database with available tools (SQLAlchemy, database drivers, MCP connectors, or raw SQL). Guides agents through schema discovery, type normalization, and MDL YAML generation using the wren CLI. Use when: user wants to create or set up a new MDL, onboard a new data source, or…
genbi
Turn a Wren project's context layer into a shareable, browser-side GenBI web app and deploy it to the user's Vercel or Cloudflare account. Orchestrates the full flow: wren genbi build returns a project-hydrated build instruction, the agent authors the app from scratch into apps/ /, then register → verify → deploy…
operator-run
Run Operator ETL locally — MVP demo, pytest, FOIA graph pipeline, Streamlit dashboard. Use when proving the system works or demoing to reviewers.
operator-extend
Extend Operator ETL — new sources, domains, gold SQL marts, gov contracts. Use when adding pipelines beyond the FOIA or orders demos.
agilab-local-llm
Guidance for using local LLM backends (Ollama/GPT-OSS) inside AGILAB with correctness-first prompts.