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 gyanranjan/polyagent-skills --skill quantitative-sanity-checkergit clone --depth 1 https://github.com/gyanranjan/polyagent-skillsWrote 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/gyanranjan/polyagent-skills/quantitative-sanity-checker)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/quantitative-sanity-checker"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/quantitative-sanity-checker/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/gyanranjan/polyagent-skills/quantitative-sanity-checker"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/quantitative-sanity-checker.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 | $0.00068 | $0.01342 |
| Opus 5 | $0.00034 | $0.00671 |
| Sonnet 5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
quantitative-sanity-checker 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 12d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quantitative Sanity Checker
Purpose
Expose unrealistic claims, forecasts, or designs by running rough-order-of-magnitude arithmetic. The skill decomposes a claim into its implied quantities, grounds each in publicly available base rates, and checks whether the numbers hold together.
When to Use
- A claim includes specific numbers that seem too good (or too bad) to be true
- A predictive model or alert system is proposed without discussing precision, recall, or base rates
- A business plan projects revenue, users, or throughput without grounding in market size
- A system design implies resource consumption (storage, bandwidth, compute) that needs a reality check
- Someone asks "does this make sense?" about any quantitative statement
When NOT to Use
- The user needs a rigorous statistical analysis or formal proof (suggest a specialist)
- The claim is purely qualitative with no numbers to check
- The user explicitly asks for optimistic projections or brainstorming (don't rain on a brainstorm)
Inputs
Required:
- The claim, forecast, or design to sanity-check
Optional:
- Domain context or constraints (e.g., "this is for the US market only")
- Known base rates the user already has
- Desired confidence level or precision target
Process
Step 1: Extract the Claim
Restate the claim in one sentence, highlighting every explicit or implied number. If the claim is vague, ask the user to pin down the key quantities before proceeding.
Step 2: Identify Base Rates and Anchor Quantities
For each number in the claim, find a grounding reference:
- Event frequency — How often does this thing actually happen? (e.g., ~15 major earthquakes per year globally)
- Population / market size — What is the total pool? (e.g., 8 billion people, 330M in US, 30M small businesses)
- Conversion / success rates — What are typical rates in this domain? (e.g., 2-3% email click-through, ~1% SaaS free-to-paid)
- Physical / engineering limits — What do physics or infrastructure constrain? (e.g., speed of light latency, disk IOPS, human attention span)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 150 lines · 68 tokens per session scan A 2e32cfb1e431
quantitative-sanity-checker is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 68 tokens to every session and 1,342 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 2026-08-31.
Other skills, from other repositories
correlation-regime
Correlation-regime detection and crisis attribution — edge-density regime states with hysteresis, causal (no look-ahead) smoothing, regime-aware exposure context, first-mover crisis attribution with honest NAME / MACRO / AMBIGUOUS / ABSTAIN verdicts, and a correlation-rewiring leaderboard that catches slow bleed-outs.
behavioral-finance
Behavioral finance applications: theories of overreaction and underreaction, behavioral explanations for momentum and reversal, investor sentiment cycles, cognitive-bias checklists, and debiasing quantitative strategies.
performance-attribution
Performance attribution analysis — Brinson sector/stock-selection attribution, factor alpha/beta decomposition, market-timing evaluation, and benchmark comparison framework.
factor-research
Factor research framework with IC/IR analysis, quantile backtesting, and factor combination. Suitable for cross-sectional factor evaluation across multiple instruments.
global-macro
Global macro analysis framework (central bank policy transmission / FX forecasting / geopolitical risk / capital flows), used to build macro factor signals that drive cross-asset allocation.
macro-analysis
Macroeconomic cycle positioning and central-bank policy interpretation, including GDP/CPI/PMI/rates/FX analysis, with output in the form of major-asset allocation tilts.