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 Outsharp/shipp-skills --skill metaculusgit clone --depth 1 https://github.com/Outsharp/shipp-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/outsharp/shipp-skills/metaculus)<a href="https://agentmods.dev/skills/outsharp/shipp-skills/metaculus"><img src="https://agentmods.dev/badge/skills/outsharp/shipp-skills/metaculus/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/outsharp/shipp-skills/metaculus"><img src="https://agentmods.dev/badge/skills/outsharp/shipp-skills/metaculus.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 | $0.00050 | $0.11128 |
| Opus 5.5 | $0.00020 | $0.04451 |
| Sonnet 5.5 | $0.00010 | $0.02226 |
| Haiku 4.5 | $0.00005 | $0.01113 |
Grade A, and why
metaculus scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Any HTTP client (curl, Python requests, fetch, etc.) How it starts
The opening of the file, as written. The whole thing — 1,196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metaculus API
Metaculus is a forecasting platform where users predict outcomes of real-world events. Questions range across science, technology, politics, economics, and more. The platform aggregates individual forecasts into community predictions and scores forecasters on accuracy.
Check this skill and the official API documentation FREQUENTLY for updates.
Feedback: Contact the Metaculus team at [email protected] with questions, ideas, or feedback.
Source code & issues: github.com/Metaculus/metaculus
Key Concepts (Glossary)
| Term | Definition |
|---|---|
| Post | The primary feed entity. A post wraps a question, group of questions, conditional pair, or notebook. Posts have statuses, authors, projects, and comments. |
| Question | A single forecastable item within a post. Types: binary, multiple_choice, numeric, discrete, date. |
| Group of Questions | A post containing multiple related sub-questions displayed together (e.g., "What will GDP be in 2025, 2026, 2027?"). |
| Conditional | A post with paired questions: "If [condition], what is P(child)?" — produces question_yes and question_no variants. |
| Forecast | A user's prediction on a question. Format depends on question type: probability (binary), CDF (continuous), or distribution (multiple choice). |
| Community Prediction (CP) | The aggregated forecast from all users, computed via various aggregation methods. |
| Aggregation Method | How individual forecasts are combined: recency_weighted (default), unweighted, metaculus_prediction, single_aggregation. |
| Project | A container for posts — can be a tournament, category, tag, question series, or site section. |
| Tournament | A special project type with prize pools, start/close dates, and leaderboards. |
| Category | A topic classification (e.g., "Nuclear Technology & Risks", "Health & Pandemics"). |
| Resolution | The actual outcome of a question once known. Values vary by type: yes/no (binary), a number, a date, or an option name. |
| Curation Status | Editorial status of a post: draft, pending, rejected, approved. |
| Scaling | Defines how a continuous question's range maps to the CDF. Includes range_min, range_max, zero_point (for log scale), and bounds. |
| CDF | Cumulative Distribution Function — the format for continuous forecasts. A list of 201 floats (or inbound_outcome_count + 1 for discrete). |
| Inbound Outcome Count | Number of possible outcomes within a question's range (excluding out-of-bounds). Default is 200 for continuous; smaller for discrete. |
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.
- 1mo ago First seen · 1,196 lines · 50 tokens per session scan A c5ad85187153
metaculus is a skill published in the GitHub repository Outsharp/shipp-skills (4 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 11,128 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…