predictor-hand-skill

A reference guide for forecasting uncertain events using evidence, base rates, calibrated confidence, gradual updates, and reviews of past predictions.

In plain words
What is it for?
Use it to break broad questions into smaller ones, weigh competing signals, update forecasts as evidence changes, and review why predictions succeeded or failed.
Why use it?
It helps separate likely outcomes from compelling stories and makes confidence more measurable over time.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/rightnow-ai/openfang/predictor
Any agent
npx skills add RightNow-AI/openfang --skill predictor
Clone the repo
git clone --depth 1 https://github.com/RightNow-AI/openfang

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.02454
Opus 5 $0.00015 $0.01227
Sonnet 5 $0.00006 $0.00491
Haiku 4.5 $0.00003 $0.00245

Measured yesterday against content hash 959c2985e490, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

predictor-hand-skill 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.

crates/openfang-hands/bundled/predictor/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forecasting Expert Knowledge

Superforecasting Principles

Based on research by Philip Tetlock and the Good Judgment Project:

  1. Triage: Focus on questions that are hard enough to be interesting but not so hard they're unknowable
  2. Break problems apart: Decompose big questions into smaller, researchable sub-questions (Fermi estimation)
  3. Balance inside and outside views: Use both specific evidence AND base rates from reference classes
  4. Update incrementally: Adjust predictions in small steps as new evidence arrives (Bayesian updating)
  5. Look for clashing forces: Identify factors pulling in opposite directions
  6. Distinguish signal from noise: Weight signals by their reliability and relevance
  7. Calibrate: Your 70% predictions should come true ~70% of the time
  8. Post-mortem: Analyze why predictions went wrong, not just celebrate the right ones
  9. Avoid the narrative trap: A compelling story is not the same as a likely outcome
  10. Collaborate: Aggregate views from diverse perspectives

Signal Taxonomy

Signal Types

Type Description Weight Example
Leading indicator Predicts future movement High Job postings surge → company expanding
Lagging indicator Confirms past movement Medium Quarterly earnings → business health
Base rate Historical frequency High "80% of startups fail within 5 years"
Expert opinion Informed prediction Medium Analyst forecast, CEO statement
Data point Factual measurement High Revenue figure, user count, benchmark
Anomaly Deviation from pattern High Unusual trading volume, sudden hiring freeze
Structural change Systemic shift Very High New regulation, technology breakthrough
Sentiment shift Collective mood change Medium Media tone change, social media trend

Signal Strength Assessment

STRONG signal (high predictive value):
  - Multiple independent sources confirm
  - Quantitative data (not just opinions)
  - Leading indicator with historical track record
  - Structural change with clear causal mechanism

MODERATE signal (some predictive value):
  - Single authoritative source
  - Expert opinion from domain specialist
  - Historical pattern that may or may not repeat
  - Lagging indicator (confirms direction)

WEAK signal (limited predictive value):
  - Social media buzz without substance
  - Single anecdote or case study
  - Rumor or unconfirmed report
  - Opinion from non-specialist

Read the full file on GitHub · 273 lines

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. yesterday First seen · 273 lines · 29 tokens per session scan A 959c2985e490

Subscribe to this mod's changes

predictor-hand-skill is a skill published in the GitHub repository RightNow-AI/openfang (18,148 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 2,454 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 2026-08-30.