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 agentmods add skills/outsharp/shipp-skills/manifoldnpx skills add Outsharp/shipp-skills --skill manifoldgit 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/manifold)<a href="https://agentmods.dev/skills/outsharp/shipp-skills/manifold"><img src="https://agentmods.dev/badge/skills/outsharp/shipp-skills/manifold.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.08713 |
| Opus 5 | $0.00030 | $0.04356 |
| Sonnet 5 | $0.00012 | $0.01743 |
| Haiku 4.5 | $0.00006 | $0.00871 |
Grade A, and why
manifold scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Any HTTP client (curl, Python requests, fetch, etc.) How it starts
The opening of the file, as written. The whole thing — 895 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manifold API
Manifold is a prediction market platform where users create and trade on questions about real-world events. It uses a combination of play-money (mana) and prize-cash, with automated market makers (CPMM) and a rich API for programmatic access.
Check this skill and the official documentation FREQUENTLY for updates. The API is still in alpha and may change without notice.
Community: Join the Manifold Discord for questions, bug reports, and to share what you build.
Source code: Manifold is open source. Type definitions live at common/src/api/schema.ts.
Key Concepts (Glossary)
| Term | Definition |
|---|---|
| Market (Contract) | A single tradeable question. Called "contract" in the codebase, "market" in the API. Has an outcome type (BINARY, MULTIPLE_CHOICE, PSEUDO_NUMERIC, BOUNTIED_QUESTION, POLL). |
| Mana (M$) | Play-money currency used for most markets. Cannot be withdrawn for real money. |
| Prize Cash (CASH) | Real-money currency available on select markets. Can be withdrawn. Identified by token: "CASH" on a market. |
| Sibling Contract | The mana or prize-cash counterpart of a market. Toggle between them via siblingContractId. |
| Topic (Group) | A tag applied to markets for categorization. Called "group" in the codebase and API. |
| CPMM | Constant Product Market Maker. The automated market maker used for binary (cpmm-1) and multi-answer (cpmm-multi-1) markets. |
| DPM | Dynamic Parimutuel Market — a legacy mechanism (dpm-2) used for older free-response markets. |
| Probability | A number between 0 and 1 representing the market's current implied probability of YES. |
| Pool | The liquidity pool of shares backing the market maker. For CPMM markets, shows YES and NO share counts. |
| Liquidity | Mana deposited into the AMM pool. More liquidity means less price impact per trade. |
| Bet | A trade on a market. Can be a market order or a limit order (when limitProb is specified). |
| Limit Order | A bet that only executes at a specified probability price or better. Remains open until filled, cancelled, or expired. |
| Shares | Units of a position. Winning YES shares pay out M$1 each; losing shares pay M$0. |
| Resolution | The final outcome of a market: YES, NO, MKT (probability), or CANCEL. |
| Answer | A possible outcome in a MULTIPLE_CHOICE or FREE_RESPONSE market. Each answer has its own probability. |
| Bounty | A BOUNTIED_QUESTION market where the creator distributes mana rewards to the best comments/answers. |
| Poll | A non-trading market type where users simply vote on options. |
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.
- 5d ago First seen · 895 lines · 60 tokens per session scan A c54253cf1abc
manifold is a skill published in the GitHub repository Outsharp/shipp-skills (4 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 8,713 once invoked, about $0.0003 per session on Opus 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
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.