oraclaw-calibrate

oraclaw-calibrate is a skill for Claude Code, Codex from Whatsonyourmind/oraclaw. It costs 39 tokens per session (553 once invoked), scanned A, original, MIT.

A prediction-checking skill that measures how accurate forecasts were and whether several sources agree. It uses Brier and log scores, which are standard ways to judge probability forecasts.

In plain words
What is it for?
Use it to review past forecasts, compare models or forecasters, detect an outlier source, and assess prediction-market positions.
Why use it?
It shows whether predictions are well calibrated—meaning their stated probabilities match how often events actually happen—and flags conflicting sources.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: positional $N argument; built for openclaw.

Good fit Use it to review past forecasts, compare models or forecasters, detect an outlier source, and assess prediction-market positions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/whatsonyourmind/oraclaw/oraclaw-calibrate
Install

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.

Any agent
npx skills add Whatsonyourmind/oraclaw --skill oraclaw-calibrate
Clone the repo
git clone --depth 1 https://github.com/Whatsonyourmind/oraclaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for oraclaw-calibrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/whatsonyourmind/oraclaw/oraclaw-calibrate/github.svg)](https://agentmods.dev/skills/whatsonyourmind/oraclaw/oraclaw-calibrate)
Your own site
<a href="https://agentmods.dev/skills/whatsonyourmind/oraclaw/oraclaw-calibrate"><img src="https://agentmods.dev/badge/skills/whatsonyourmind/oraclaw/oraclaw-calibrate/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.

agentmods 80×15 button for oraclaw-calibrate

Your own site · 80×15
<a href="https://agentmods.dev/skills/whatsonyourmind/oraclaw/oraclaw-calibrate"><img src="https://agentmods.dev/badge/skills/whatsonyourmind/oraclaw/oraclaw-calibrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 553 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00553
Opus 5 $0.00019 $0.00277
Sonnet 5 $0.00008 $0.00111
Haiku 4.5 $0.00004 $0.00055

Measured 12d ago against content hash f23d926264d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

oraclaw-calibrate 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.

mission-control/packages/clawhub-skills/oraclaw-calibrate/SKILL.md · 69 lines

What it actually says

OraClaw Calibrate — Prediction Quality for Agents

You are a calibration agent that scores prediction accuracy and detects when information sources disagree.

When to Use This Skill

Use this when you need to:

  • Score how accurate past predictions were (Brier score, log score)
  • Check if multiple data sources, models, or forecasters agree
  • Find the outlier source that disagrees with consensus
  • Compare forecast quality across different models or approaches
  • Evaluate prediction market positions

Tools

score_calibration — Accuracy Scoring

Input: arrays of predictions (0-1) and outcomes (0 or 1). Output: Brier score (0=perfect, 1=worst) and log score.

score_convergence — Multi-Source Agreement

Input: array of prediction sources with probabilities. Output: convergence score (0-1), outlier detection, consensus probability, spread.

Example: Model Comparison

{
  "predictions": [0.80, 0.65, 0.30, 0.90, 0.55],
  "outcomes": [1, 1, 0, 1, 0]
}

Response: brier_score: 0.082 — excellent calibration.

Rules

  1. Brier score < 0.1 = excellent, < 0.2 = good, < 0.3 = fair, > 0.3 = poor
  2. Convergence score > 0.7 = strong agreement, < 0.5 = significant disagreement
  3. Outlier sources are flagged automatically when their Hellinger distance exceeds threshold
  4. Volume-weighted consensus gives more weight to high-liquidity sources

Pricing

$0.02 per scoring call (USDC on Base via x402). Free tier: 3,000 calls/month with API key.

Files

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.

Changes

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.

  1. 12d ago First seen · 69 lines · 39 tokens per session scan A f23d926264d4

Subscribe to this mod's changes

oraclaw-calibrate is a skill published in the GitHub repository Whatsonyourmind/oraclaw (13 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 553 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 2026-08-30.

Related

Other skills, from other repositories

causal

Analyze cause-and-effect relationships in the Semantica knowledge graph — causal chains, interventions, counterfactuals, and causal influence scores.

semantica-agi/semantica · 31 tokens

fastify

Production Fastify (TypeScript) patterns: schema validation, plugins, typed routes, error handling, security hardening, logging, testing with inject, and graceful shutdown.

bobmatnyc/claude-mpm-skills · 36 tokens

openephemeris

This skill should be used when a user asks for astrology or astronomical chart calculations — natal charts, transits, synastry/compatibility, progressions, solar/lunar returns, eclipses, moon phases, electional (auspicious-timing) astrology, Human Design, Vedic/Jyotish, Chinese BaZi, astrocartography, or chart…

openephemeris/openephemeris-MCP · 109 tokens

openephemeris-setup

Install and configure the OpenEphemeris MCP server. Use when a user wants to set up OpenEphemeris, get an API key, troubleshoot installation, or connect Claude / Cursor / Windsurf / ChatGPT to the planetary calculation API.

openephemeris/openephemeris-MCP · 56 tokens

darto-write-middleware

Write and register middleware in a Darto (Dart) app — the Middleware factory pattern, global/path-scoped/route-level registration, short-circuiting, per-request state, and global error/404 handlers. Use when adding cross-cutting behavior (auth, logging, CORS, timing) or configuring app.onError / app.notFound in a…

evandersondev/darto · 86 tokens

darto-add-route

Add or modify HTTP endpoints in a Darto (Dart) web app — verbs, path/query params, request-body reading, route groups, and Context response helpers. Use when building or changing API routes in a project that depends on the darto package (import 'package:darto/darto.dart'). Not for Express/Node — Darto handlers take a…

evandersondev/darto · 90 tokens