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 WingedGuardian/GENesis-AGI --skill forecastinggit clone --depth 1 https://github.com/WingedGuardian/GENesis-AGIWrote 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/wingedguardian/genesis-agi/forecasting)<a href="https://agentmods.dev/skills/wingedguardian/genesis-agi/forecasting"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/forecasting/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/wingedguardian/genesis-agi/forecasting"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/forecasting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.02162 |
| Opus 5.5 | $0.00008 | $0.00865 |
| Sonnet 5.5 | $0.00004 | $0.00432 |
| Haiku 4.5 | $0.00002 | $0.00216 |
Grade A, and why
forecasting 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 1mo 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forecasting
Purpose
Make specific, falsifiable predictions with calibrated confidence levels. Track accuracy over time using Brier scores. Apply superforecasting methodology (Tetlock/Good Judgment Project) to any domain — technology trends, project outcomes, market shifts, competitive moves, risk assessment.
When to Use
- User asks for a prediction or forecast on any topic.
- Strategic reflection identifies a decision that depends on uncertain futures.
- Surplus compute is available and a prediction review is due.
- A previously made prediction is approaching its resolution date.
- Deep reflection surfaces a trend worth formally tracking.
Superforecasting Principles
- Triage — Focus on questions where effort improves accuracy. Ignore questions that are either trivially knowable or fundamentally unknowable.
- Fermi decomposition — Break big questions into smaller, estimable components. "Will X happen?" → "What's the base rate? What's different this time? What signals would I expect to see?"
- Balance inside and outside views — Start with the reference class (base rate from historical analogues), then adjust with specific evidence. Never skip the outside view.
- Update incrementally — Bayesian updating. New evidence shifts confidence by small amounts, not dramatic swings. Avoid overreaction.
- Calibration over precision — A well-calibrated 60% is better than an overconfident 90%. Your 70% predictions should come true ~70% of the time.
- Distinguish noise from signal — Most new information is noise. Ask: does this actually change the probability, or does it just feel important because it's recent?
- Consider contrarian views — Actively seek evidence against your current position. What must be true for the opposite outcome?
- Post-mortem every resolution — When a prediction resolves, analyze WHY you were right or wrong, not just whether. Update process, not just beliefs.
- Express uncertainty numerically — "Likely" is ambiguous. 70% is not. Use the probability scale below.
- Separate confidence from conviction — High confidence (90%) means high probability. Strong conviction means you've thought deeply. You can have low confidence with strong conviction (you've analyzed it thoroughly and it's genuinely uncertain).
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.
- 1mo ago First seen · 225 lines · 19 tokens per session scan A 2a0b3dac317f
forecasting is a skill published in the GitHub repository WingedGuardian/GENesis-AGI (99 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 2,162 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
search
Unified academic paper search, citation chains, paper download (arXiv LaTeX/PDF, Sci-Hub), figure extraction from papers, LaTeX source reading, BibTeX fetching, web search, and browser automation for Cloudflare-protected sites (PRL, Science, Nature, Google Scholar).
qec-construct
Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever the project goal is a new or better code/construction — INCLUDING search-phrased goals ("find codes beating X"), where the construct-loop (propose algebraic rule → qverify → debug) is the…
memory
Cross-project research memory. Deep-dive past projects' notes and record corrections across all Luxas research projects.
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
compute-methods
Friction sheets for field-standard computational tools and simulators (frictions, smoke tests, how to measure a saved model). Injected at spawn time.
brain-ai-memory
Save, correct and recall project facts, exact state and session handoffs through Brain-AI Memory MCP when it is connected, or set up a project-local connection when requested.