Borrowing it
Nothing to install: this file belongs to parthakker/nfl-analytics. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/parthakker/nfl-analytics/main/.claude/skills/health-check/SKILL.mdgit clone --depth 1 https://github.com/parthakker/nfl-analyticsWrote 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/parthakker/nfl-analytics/health-check)<a href="https://agentmods.dev/skills/parthakker/nfl-analytics/health-check"><img src="https://agentmods.dev/badge/skills/parthakker/nfl-analytics/health-check/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/parthakker/nfl-analytics/health-check"><img src="https://agentmods.dev/badge/skills/parthakker/nfl-analytics/health-check.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 | $0.00041 | $0.00767 |
| Opus 5.5 | $0.00016 | $0.00307 |
| Sonnet 5.5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
health-check 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 2mo 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
Nightly health check
Run every step even if an earlier one fails — the report must cover all of them. Collect results, then write the report. Keep total runtime under ~10 minutes.
- Audit:
python -m nfl_analytics.cli audit— note "Real gaps found: N". - Tests:
python -m pytest -m "warehouse or api" -qagainst the real DB. - Smoke:
python -m nfl_analytics.cli smoke(live-HTTP surface). - Scheduler + logs:
schtasks /Query /TN <each NFL-* task> /FO LISTfor last-run results; read the tail of eachlogs/*.logfor errors. 4a. Query each task with its ownschtasks /Query /TN <name>call — noforeachloops or compound commands; the permission patterns only match single commands, and a denial here wastes the run. - Freshness: via
mcp__nfl__query_warehouse— max(season, week) in games vs today's date (in-season, data should trail by <8 days). Latest news published_ts viamcp__nfl__news_search/mcp__nfl__league_newsand latest kalshi snapshot viamcp__nfl__kalshi_markets— check the real data, not the poll logs; both should be <24h old.
Report — overwrite docs/health_report.md:
- Header: timestamp + one-word verdict (HEALTHY / DEGRADED / BROKEN).
- A check that could only be completed via a proxy or fallback (log tail instead of the real data, a denied tool, a skipped step) caps the verdict at DEGRADED — never report HEALTHY on evidence you couldn't actually collect, and list the missing permission under ACTION NEEDED.
- Status table: one row per step with pass/fail + the key number.
- Only if something failed: an "ACTION NEEDED" section — what broke, the exact error tail, and the suggested next command. No such section when green.
Log line — append to logs/health.log:
<ISO timestamp> health: <verdict> audit=<n_gaps> tests=<pass>/<total> smoke=<pass>/<total> freshness=<ok|stale>
If any step failed, end the run by stating the failure clearly (nonzero outcome). Do NOT attempt fixes that write to databases or git — report only; trivial fixes (e.g. a stale doc line) are allowed via Edit.
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.
- 2mo ago First seen · 44 lines · 41 tokens per session scan A 12f5f2f0b246
health-check is a skill published in the GitHub repository parthakker/nfl-analytics (1 stars, last pushed 11d ago), licensed MIT. It adds 41 tokens to every session and 767 once invoked, about $0.0002 per session on Opus 5.5. 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.
health-check compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| health-checkparthakker/nfl-analytics | Skill | 1 | 11d ago | MIT | A | 41 | Claude Code |
| developing-with-streamlitstreamlit/streamlit | Skill | 46k | yesterday | Apache-2.0 | A | 146 | Claude Code |
| network-data-analysisautomateyournetwork/netclaw | Skill | 715 | yesterday | Apache-2.0 | A | 64 | Claude Code, Codex |
| usageCanner/WrenAI | Skill | 18k | 2d ago | none | A | 156 | Claude Code, Codex |
| generate-mdlCanner/WrenAI | Skill | 18k | 2d ago | none | A | 82 | Claude Code, Codex |
| genbiCanner/WrenAI | Skill | 18k | 2d ago | none | A | 140 | Claude Code, Codex |
| analytical-databases-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 100 | Claude Code |