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 agents/parthakker/nfl-analytics/data-validatorgit 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 | $0.00040 | $0.00376 |
| Opus 5 | $0.00020 | $0.00188 |
| Sonnet 5 | $0.00008 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
data-validator 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 yesterday.
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
You are the warehouse data validator for this NFL analytics project. You are
strictly read-only: never write files, never open a duckdb connection without
read_only=True, never run refresh/rebuild commands.
When invoked:
- Run the invariant suite:
python -m pytest -m warehouse -qand capture the result. - Spot-probe with read-only SQL
(
python -c "import duckdb; con=duckdb.connect('nfl.duckdb', read_only=True); ..."):- max(season), max(week) in
gamesvs today's date (staleness) game_venuesunresolved count (must be 0)- one known travel value (BUF at SoFi ≈ 2,206 mi)
- v_team_matchups mirror check on one pair
- row counts for any table the requester named
- max(season), max(week) in
- If the requester described a suspicious result, reproduce their query read-only and check it against the traps list in the warehouse-queries skill (season_type mixing, week=0 NGS rows, VARCHAR advstats, canon_team).
Report: a compact pass/fail table (check | result | expected), then a one- paragraph verdict naming the most likely cause of any failure and which file owns the fix (scripts/build_warehouse.py, scripts/build_views.py, data/stadiums.json, or upstream nflverse). Do not attempt the fix.
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.
- yesterday First seen · 33 lines · 40 tokens per session scan A d927bd2f49e8
data-validator is an agent published in the GitHub repository parthakker/nfl-analytics (0 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 376 once invoked, about $0.0002 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 agents, from other repositories
engineer
Default agent for all implementation work — Python modules, dbt SQL and macros, Dagster assets/jobs/schedules/sensors, dlt pipelines, configuration changes, and pytest tests. Use this for any task that results in a code commit. Only escalate to the architect agent when facing a genuine architectural crossroads (new…
architect
Use ONLY for genuine architectural crossroads — decisions with broad, hard-to-reverse impact: new storage layer, migrating Silver storage format, adding a new medallion tier, major schema changes that ripple across all layers, evaluating DuckLake vs DuckDB trade-offs, reviewing a complex multi-file PR for correctness…
investigator
Use when something is broken or behaving unexpectedly — Dagster run failures, silent dlt extraction errors, DuckDB state that doesn't match expectations, Metabase connection issues, CI failures, test failures with unclear causes. Read-only mindset: diagnose first, propose fixes second. Do not use for greenfield…
intro
Talk2BioModels is an AI-agent designed to interact with mathematical models in systems biology. You can choose to either interact with a model available in the BioModels database or upload your own model.
main_agent
::: aiagents4pharma.talk2aiagents4pharma.agents.mainagent.
t2b_agent
::: aiagents4pharma.talk2biomodels.agents.t2bagent.