Digital Oracle
komako-workshop/digital-oracle
Answer prediction questions using market trading data, not opinions.
Trade prediction markets, persist tick data, and answer category-level P&L questions Kalshi.com cannot.
$ npx skills add mvanhorn/printing-press-library --skill pp-kalshi -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kalshi --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-skills/pp-kalshi .claude/skills/pp-kalshi && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pp-kalshi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kalshi into .claude/skills/pp-kalshi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kalshi", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kalshiType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mvanhorn/printing-press-library --skill pp-kalshi -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kalshi --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cli-skills/pp-kalshi .agents/skills/pp-kalshi && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pp-kalshi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kalshi into .agents/skills/pp-kalshi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kalshi", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mvanhorn/printing-press-library --skill pp-kalshi -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kalshi --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cli-skills/pp-kalshi .cursor/skills/pp-kalshi && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pp-kalshi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kalshi into .cursor/skills/pp-kalshi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kalshi", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mvanhorn/printing-press-library.git --path cli-skills/pp-kalshi--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mvanhorn/printing-press-library --skill pp-kalshi -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kalshi --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cli-skills/pp-kalshi .gemini/skills/pp-kalshi && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pp-kalshi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kalshi into .gemini/skills/pp-kalshi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kalshi", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mvanhorn/printing-press-library pp-kalshiInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mvanhorn/printing-press-library --skill pp-kalshi -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .github/skills && cp -r skills-src/cli-skills/pp-kalshi .github/skills/pp-kalshi && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pp-kalshi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kalshi into .github/skills/pp-kalshi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kalshi", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mvanhorn/printing-press-library --skill pp-kalshi -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kalshi --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cli-skills/pp-kalshi .opencode/skills/pp-kalshi && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pp-kalshi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kalshi into .opencode/skills/pp-kalshi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kalshi", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
pp-kalshiTrade prediction markets, persist tick data, and answer category-level P&L questions Kalshi.com cannot.
Pp Kalshi is an agent skill from mvanhorn/printing-press-library. Trade prediction markets, persist tick data, and answer category-level P&L questions Kalshi.com cannot. Trigger phrases: kalshi market price, track prediction market, kalshi portfolio P&L, kalshi correlate markets, use kalshi, run kalshi.
Its SKILL.md is about 6.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Business, Finance & HR. It works with Kalshi. The repository describes itself as: Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed. The licence is Apache-2.0.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit d9a1696. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadBashFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
goclaudenpxFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
KALSHI_API_KEYKALSHI_PRIVATE_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pp Kalshi loads about 6.6k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 2,990 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, BashAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from mvanhorn/printing-press-library at commit d9a1696, republished under its Apache-2.0 licence (© mvanhorn). 2,990 words, ~6,641 tokens.
.claude/skills/pp-kalshi/SKILL.md (or your agent's skills folder).<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/payments/kalshi/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
This skill drives the kalshi-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:npx -y @mvanhorn/printing-press-library install kalshi --cli-onlykalshi-pp-cli --version$PATH for the agent/runtime that will invoke this skill.If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:
go install github.com/mvanhorn/printing-press-library/library/payments/kalshi/cmd/kalshi-pp-cli@latestIf --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.
Every Kalshi feature, plus a local SQLite store that records market prices on every sync — so movers, correlations, and price history work offline. Honest about read-only vs read/write keys, with --dry-run on every mutator and a global --read-only safe-mode lock for newsroom and bot deployments.
Reach for kalshi-pp-cli when an agent needs price-over-time or category-level analytics on Kalshi markets — the public API only returns current prices and flat positions, so historical and aggregated questions require the local snapshot store. Use it for daily portfolio reconciliation, signal discovery via correlation across markets, and safe scripting against read-only API credentials.
These capabilities aren't available in any other tool for this API.
portfolio attribution — See your realized P&L broken down by market category and series over any time window — answer 'did politics actually make money this quarter?' in one command.
Use when an agent needs realized P&L sliced by Kalshi taxonomy — the API returns flat fills and settlements; this command joins them with the category metadata required to attribute correctly.
kalshi-pp-cli portfolio attribution --since 2026-01-01 --by category --jsonmarkets history — Show how a market's yes/no price moved over time, with a sparkline rendering — built from snapshots captured by every markets sync.
Use when an agent asks 'how did this market move' or needs price-over-time for backtesting; the API only returns current price.
kalshi-pp-cli markets history KXPRES-2028-DJT --since 2026-04-01 --sparklineportfolio winrate — Calculate your win/loss ratio, expected value, and ROI across all settled positions, optionally sliced by category.
Use when an agent evaluates trading-strategy performance; no Kalshi tool computes this.
kalshi-pp-cli portfolio winrate --category sports --since 2026-01-01 --jsonportfolio calendar — See upcoming settlements with your positions, expected payouts, and category breakdown over the next N days.
Use when an agent needs to plan around upcoming settlements; the API surfaces positions and event expiries on different endpoints.
kalshi-pp-cli portfolio calendar --days 14markets movers — Find markets with the biggest price swings since the last sync — sorted by absolute delta or by volume change.
Use when an agent needs to surface notable market activity; the API has no 'recent movers' endpoint.
kalshi-pp-cli markets movers --window 24h --category politics --jsonmarkets correlate — Compute Pearson correlation of two markets' price histories — find correlated events for hedging or signal discovery.
Use when an agent investigates cross-market relationships; no API endpoint or other tool computes correlation across Kalshi markets.
kalshi-pp-cli markets correlate KXFEDFUNDS-26FEB KXCPI-26FEB --window 30d --jsonportfolio exposure — Break down total exposure by category with concentration warnings when any bucket exceeds a configurable risk threshold.
Use when an agent needs portfolio-level risk; the API doesn't aggregate exposure by Kalshi taxonomy.
kalshi-pp-cli portfolio exposure --by category --warn-threshold 0.4 --jsonwatch diff — Maintain a local watchlist of tickers; watch diff shows price/volume change vs the last sync per watched market — Riley's daily-snapshot ritual reduced to one command.
Use when an agent tracks a stable set of markets across runs; the API has no watchlist concept.
kalshi-pp-cli watch diff --since 24h--read-only — Global env-var/flag lock that blocks every mutating command client-side regardless of which key tier is loaded — pair with --dry-run on every mutator for safe scripting against read-only credentials.
Use when an agent runs against an unknown Kalshi key tier — the read-only key tier exists and mid-script 403s are common; this surfaces the constraint client-side before the API is hit.
kalshi-pp-cli --read-only portfolio create-order --ticker KXTEST --side yes --count 1 --yes-price 50 --dry-runsubaccounts rollup — Aggregate positions, fills-today, balance, and exposure-by-category across every subaccount you can see — household view of risk and resting orders.
Use when an FCM-tier user needs aggregate risk across subaccounts; no Kalshi tool surfaces a household view.
kalshi-pp-cli subaccounts rollup --by category --jsonaccount — Manage account
kalshi-pp-cli account get-api-limits — Endpoint to retrieve the API tier limits associated with the authenticated user.kalshi-pp-cli account get-endpoint-costs — Lists API v2 endpoints whose configured token cost differs from the default cost. Endpoints that use the default...api-keys — API key management endpoints
kalshi-pp-cli api-keys create — Endpoint for creating a new API key with a user-provided public key. This endpoint allows users with Premier or...kalshi-pp-cli api-keys delete — Endpoint for deleting an existing API key. This endpoint permanently deletes an API key. Once deleted, the key can...kalshi-pp-cli api-keys generate — Endpoint for generating a new API key with an automatically created key pair. This endpoint generates both a public...kalshi-pp-cli api-keys get — Endpoint for retrieving all API keys associated with the authenticated user. API keys allow programmatic access to...communications — Request-for-quote (RFQ) endpoints
kalshi-pp-cli communications accept-quote — Endpoint for accepting a quote. This will require the quoter to confirmkalshi-pp-cli communications confirm-quote — Endpoint for confirming a quote. This will start a timer for order executionkalshi-pp-cli communications create-quote — Endpoint for creating a quote in response to an RFQkalshi-pp-cli communications create-rfq — Endpoint for creating a new RFQ. You can have a maximum of 100 open RFQs at a time.kalshi-pp-cli communications delete-quote — Endpoint for deleting a quote, which means it can no longer be accepted.kalshi-pp-cli communications delete-rfq — Endpoint for deleting an RFQ by IDkalshi-pp-cli communications get-id — Endpoint for getting the communications ID of the logged-in user.kalshi-pp-cli communications get-quote — Endpoint for getting a particular quotekalshi-pp-cli communications get-quotes — Endpoint for getting quoteskalshi-pp-cli communications get-rfq — Endpoint for getting a single RFQ by idkalshi-pp-cli communications get-rfqs — Endpoint for getting RFQsevents — Event endpoints
kalshi-pp-cli events get — Get all events. This endpoint excludes multivariate events. To retrieve multivariate events, use the GET...kalshi-pp-cli events get-eventticker — Endpoint for getting data about an event by its ticker. An event represents a real-world occurrence that can be...kalshi-pp-cli events get-multivariate — Retrieve multivariate (combo) events. These are dynamically created events from multivariate event collections....exchange — Exchange status and information endpoints
kalshi-pp-cli exchange get-announcements — Endpoint for getting all exchange-wide announcements.kalshi-pp-cli exchange get-schedule — Endpoint for getting the exchange schedule.kalshi-pp-cli exchange get-status — Endpoint for getting the exchange status.kalshi-pp-cli exchange get-user-data-timestamp — There is typically a short delay before exchange events are reflected in the API endpoints. Whenever possible,...fcm — FCM member specific endpoints
kalshi-pp-cli fcm get-fcmorders — Endpoint for FCM members to get orders filtered by subtrader ID. This endpoint requires FCM member access level and...kalshi-pp-cli fcm get-fcmpositions — Endpoint for FCM members to get market positions filtered by subtrader ID. This endpoint requires FCM member access...historical — Manage historical
kalshi-pp-cli historical get-cutoff — Returns the cutoff timestamps that define the boundary between live and historical data. ## Cutoff fields -...kalshi-pp-cli historical get-fills — Endpoint for getting all historical fills for the member. A fill is when a trade you have is matched.kalshi-pp-cli historical get-market — Endpoint for getting data about a specific market by its ticker from the historical database.kalshi-pp-cli historical get-market-candlesticks — Endpoint for fetching historical candlestick data for markets that have been archived from the live data set. Time...kalshi-pp-cli historical get-markets — Endpoint for getting markets that have been archived to the historical database. Filters are mutually exclusive.kalshi-pp-cli historical get-orders — Endpoint for getting orders that have been archived to the historical database.kalshi-pp-cli historical get-trades — Endpoint for getting all historical trades for all markets. Trades that were filled before the historical cutoff are...incentive-programs — Incentive program endpoints
kalshi-pp-cli incentive-programs — List incentives with optional filters. Incentives are rewards programs for trading activity on specific markets.kalshi-trade-manual-search — Manage kalshi trade manual search
kalshi-pp-cli kalshi-trade-manual-search — Retrieve available filters organized by sport. This endpoint returns filtering options available for each sport,...kalshi-trade-manual-search-2 — Manage kalshi trade manual search 2
kalshi-pp-cli kalshi-trade-manual-search-2 — Retrieve tags organized by series categories. This endpoint returns a mapping of series categories to their...live-data — Live data endpoints
kalshi-pp-cli live-data get — Get live data for multiple milestoneskalshi-pp-cli live-data get-by-milestone — Get live data for a specific milestone.kalshi-pp-cli live-data get-game-stats — Get play-by-play game statistics for a specific milestone. Supported sports: Pro Football, College Football, Pro...markets — Market data endpoints
kalshi-pp-cli markets batch-get-candlesticks — Endpoint for retrieving candlestick data for multiple markets. - Accepts up to 100 market tickers per request -...kalshi-pp-cli markets get — Filter by market status. Possible values: unopened, open, closed, settled. Leave empty to return markets...kalshi-pp-cli markets get-orderbooks — Endpoint for getting the current order books for multiple markets in a single request. The order book shows all...kalshi-pp-cli markets get-ticker — Endpoint for getting data about a specific market by its ticker. A market represents a specific binary outcome...kalshi-pp-cli markets get-trades — Endpoint for getting all trades for all markets. A trade represents a completed transaction between two users on a...milestones — Milestone endpoints
kalshi-pp-cli milestones get — Minimum start date to filter milestones. Format: RFC3339 timestampkalshi-pp-cli milestones get-milestoneid — Endpoint for getting data about a specific milestone by its ID.multivariate-event-collections — Manage multivariate event collections
kalshi-pp-cli multivariate-event-collections create-market-in — Endpoint for creating an individual market in a multivariate event collection. This endpoint must be hit at least...kalshi-pp-cli multivariate-event-collections get — Endpoint for getting data about multivariate event collections.kalshi-pp-cli multivariate-event-collections get-multivariateeventcollections — Endpoint for getting data about a multivariate event collection by its ticker.portfolio — Portfolio and balance information endpoints
kalshi-pp-cli portfolio amend-order — Endpoint for amending the max number of fillable contracts and/or price in an existing order. Max fillable contracts...kalshi-pp-cli portfolio amend-order-v2 — Endpoint for amending the price and/or remaining count of an existing event-market order using the V2...kalshi-pp-cli portfolio apply-subaccount-transfer — Transfers funds between the authenticated user's subaccounts. Use 0 for the primary account, or 1-32 for numbered...kalshi-pp-cli portfolio batch-cancel-orders — Endpoint for cancelling a batch of orders. The maximum batch size scales with your tier's write budget — see [Rate...kalshi-pp-cli portfolio batch-cancel-orders-v2 — Endpoint for cancelling a batch of event-market orders using the V2 response shape. The maximum batch size scales...kalshi-pp-cli portfolio batch-create-orders — Endpoint for submitting a batch of orders. The maximum batch size scales with your tier's write budget — see [Rate...kalshi-pp-cli portfolio batch-create-orders-v2 — Endpoint for submitting a batch of event-market orders using the V2 request/response shape. The maximum batch size...kalshi-pp-cli portfolio cancel-order — Endpoint for canceling orders. The value for the orderId should match the id field of the order you want to...kalshi-pp-cli portfolio cancel-order-v2 — Endpoint for cancelling event-market orders using the V2 response shape. Returns `{order_id, client_order_id,...kalshi-pp-cli portfolio create-order — Endpoint for submitting orders in a market. Each user is limited to 200 000 open orders at a time.kalshi-pp-cli portfolio create-order-group — Creates a new order group with a contracts limit measured over a rolling 15-second window. When the limit is hit,...kalshi-pp-cli portfolio create-order-v2 — Endpoint for submitting event-market orders using the V2 request/response shape (single-book bid/ask side and...kalshi-pp-cli portfolio create-subaccount — Creates a new subaccount for the authenticated user. Subaccounts are numbered sequentially starting from 1. Maximum...kalshi-pp-cli portfolio decrease-order — Endpoint for decreasing the number of contracts in an existing order. This is the only kind of edit available on...kalshi-pp-cli portfolio decrease-order-v2 — Endpoint for decreasing the remaining count of an existing event-market order using the V2 request/response shape....kalshi-pp-cli portfolio delete-order-group — Deletes an order group and cancels all orders within it. This permanently removes the group.kalshi-pp-cli portfolio get-balance — Endpoint for getting the balance and portfolio value of a member. Both values are returned in cents.kalshi-pp-cli portfolio get-fills — Endpoint for getting all fills for the member. A fill is when a trade you have is matched. Fills that occurred...kalshi-pp-cli portfolio get-order — Endpoint for getting a single order.kalshi-pp-cli portfolio get-order-group — Retrieves details for a single order group including all order IDs and auto-cancel status.kalshi-pp-cli portfolio get-order-groups — Retrieves all order groups for the authenticated user.kalshi-pp-cli portfolio get-order-queue-position — Endpoint for getting an order's queue position in the order book. This represents the amount of orders that need to...kalshi-pp-cli portfolio get-order-queue-positions — Endpoint for getting queue positions for all resting orders. Queue position represents the number of contracts that...kalshi-pp-cli portfolio get-orders — Restricts the response to orders that have a certain status: resting, canceled, or executed. Orders that have been...kalshi-pp-cli portfolio get-positions — Restricts the positions to those with any of following fields with non-zero values, as a comma separated list. The...kalshi-pp-cli portfolio get-resting-order-total-value — Endpoint for getting the total value, in cents, of resting orders. This endpoint is only intended for use by FCM...kalshi-pp-cli portfolio get-settlements — Endpoint for getting the member's settlements historical track.kalshi-pp-cli portfolio get-subaccount-balances — Gets balances for all subaccounts including the primary account.kalshi-pp-cli portfolio get-subaccount-netting — Gets the netting enabled settings for all subaccounts.kalshi-pp-cli portfolio get-subaccount-transfers — Gets a paginated list of all transfers between subaccounts for the authenticated user.kalshi-pp-cli portfolio reset-order-group — Resets the order group's matched contracts counter to zero, allowing new orders to be placed again after the limit...kalshi-pp-cli portfolio trigger-order-group — Triggers the order group, canceling all orders in the group and preventing new orders until the group is reset.kalshi-pp-cli portfolio update-order-group-limit — Updates the order group contracts limit (rolling 15-second window). If the updated limit would immediately trigger...kalshi-pp-cli portfolio update-subaccount-netting — Updates the netting enabled setting for a specific subaccount. Use 0 for the primary account, or 1-32 for numbered...series — Manage series
kalshi-pp-cli series get — Endpoint for getting data about a specific series by its ticker. A series represents a template for recurring events...kalshi-pp-cli series get-fee-changes — Get Series Fee Changeskalshi-pp-cli series get-list — Endpoint for getting data about multiple series with specified filters. A series represents a template for recurring...structured-targets — Structured targets endpoints
kalshi-pp-cli structured-targets get — Page size (min: 1, max: 2000)kalshi-pp-cli structured-targets get-structuredtargets — Endpoint for getting data about a specific structured target by its ID.When you know what you want to do but not which command does it, ask the CLI directly:
kalshi-pp-cli which "<capability in your own words>"which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.
kalshi-pp-cli portfolio attribution --since 2026-01-01 --by category --agent --select 'rows.category,rows.realized_pnl,rows.fills'Realized P&L attributed to Kalshi taxonomy; --select narrows the response to the three fields agents need.
kalshi-pp-cli watch add KXFEDFUNDS-26FEB && kalshi-pp-cli watch diff --since 24h --agentAdd ticker to local watchlist, then ask for the per-ticker delta since yesterday.
kalshi-pp-cli markets correlate KXFEDFUNDS-26FEB KXCPI-26FEB --window 30d --agentPearson r computed locally over snapshot price series for both markets.
kalshi-pp-cli portfolio create-order --ticker KXTEST-2026 --side yes --count 1 --yes-price 50 --action buy --dry-runBoth safety floors engaged: client-side read-only lock + dry-run; never reaches the API. (Pair with KALSHI_READ_ONLY=1 to engage the client-side safe-mode lock.)
kalshi-pp-cli markets movers --window 24h --category sports --limit 5 --agentComputes price deltas from market_price_history snapshots; works offline after a sync.
Kalshi requires composed RSA-PSS signature auth: a UUID access key id (KALSHI_API_KEY) plus an RSA private key file (KALSHI_PRIVATE_KEY_PATH or KALSHI_PRIVATE_KEY). Kalshi issues two key tiers — read-only and read/write — and the CLI honors KALSHI_READ_ONLY=1 (or --read-only) as a client-side lock that blocks every POST/PUT/PATCH/DELETE before signing, regardless of which tier is loaded. Write commands run against a read-only key will surface a 403 from Kalshi; pair with --dry-run while debugging.
Run kalshi-pp-cli doctor to verify setup.
Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.
Pipeable — JSON on stdout, errors on stderr
Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:
kalshi-pp-cli api-keys get --agent --select id,name,statusPreviewable — --dry-run shows the request without sending
Offline-friendly — sync/search commands can use the local SQLite store when available
Non-interactive — never prompts, every input is a flag
Commands that read from the local store or the API wrap output in a provenance envelope:
{
"meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
"results": <data>
}Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal — piped/agent consumers get pure JSON on stdout.
When you (or the agent) notice something off about this CLI, record it:
kalshi-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
kalshi-pp-cli feedback --stdin < notes.txt
kalshi-pp-cli feedback list --json --limit 10Entries are stored locally at ~/.kalshi-pp-cli/feedback.jsonl. They are never POSTed unless KALSHI_FEEDBACK_ENDPOINT is set AND either --send is passed or KALSHI_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.
Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.
Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:
| Sink | Effect |
|---|---|
stdout | Default; write to stdout only |
file:<path> | Atomically write output to <path> (tmp + rename) |
webhook:<url> | POST the output body to the URL (application/json or application/x-ndjson when --compact) |
Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.
A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.
kalshi-pp-cli profile save briefing --json
kalshi-pp-cli --profile briefing api-keys get
kalshi-pp-cli profile list --json
kalshi-pp-cli profile show briefing
kalshi-pp-cli profile delete briefing --yesExplicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.
| Code | Meaning |
|---|---|
| 0 | Success |
| 2 | Usage error (wrong arguments) |
| 3 | Resource not found |
| 4 | Authentication required |
| 5 | API error (upstream issue) |
| 7 | Rate limited (wait and retry) |
| 10 | Config error |
Parse $ARGUMENTS:
help, or --help → show kalshi-pp-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)go install github.com/mvanhorn/printing-press-library/library/payments/kalshi/cmd/kalshi-pp-mcp@latestclaude mcp add kalshi-pp-mcp -- kalshi-pp-mcpclaude mcp listwhich kalshi-pp-cli
If not found, offer to install (see Prerequisites at the top of this skill).--agent flag:kalshi-pp-cli <command> [subcommand] [args] --agentkalshi-pp-cli <command> --help.© mvanhorn, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in cli-skills/pp-kalshi of mvanhorn/printing-press-library.
Open the folder on GitHubat commit d9a1696
Pp Kalshi next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Pp Kalshi this skillmvanhorn/printing-press-library | 2.1k | — | ~6.6k | Automated safety check: Notes | Apache-2.0 | |
| Digital Oraclekomako-workshop/digital-oracle | 878 | — | ~5.9k | Automated safety check: Pass | MIT | |
| Dr Manhattanguzus/dr-manhattan | 204 | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Kalshi Traderyanfrigo/kalshi-ai-trading-bot | 613 | — | ~3.4k | Automated safety check: Pass | MIT | |
| Polymarket Tennislivetennisapi/livetennisapi-mcp | 152 | — | ~3k | Automated safety check: Pass | MIT | |
| Prediction Markets AnalysisOctagonAI/octagon-mcp-server | 147 | — | ~465 | Automated safety check: Pass | MIT |
komako-workshop/digital-oracle
Answer prediction questions using market trading data, not opinions.
guzus/dr-manhattan
Trade prediction markets (Polymarket, Kalshi, Opinion, Limitless, Predict.fun) using a unified CCXT-style API.
ryanfrigo/kalshi-ai-trading-bot
The disciplined process for autonomously and profitably trading the live Kalshi account on each /loop tick, with Claude as the decision-maker.
livetennisapi/livetennisapi-mcp
Build observe-only Polymarket and Kalshi tennis market tooling on the polymarket-tennis Python package (MIT) plus the Live Tennis API free tier.
OctagonAI/octagon-mcp-server
Generate Kalshi prediction market research reports or fetch structured event history.
alsk1992/CloddsBot
Real-time market data feeds from 8 prediction market platforms
mvanhorn/printing-press-library
Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.
mvanhorn/printing-press-library
Search, browse, and download Google Fonts from the terminal via the gfonts CLI.
mvanhorn/printing-press-library
The free, offline Trigger phrases: search 1688 for, find a factory on 1688 for, wholesale price on 1688 for, who is the cheapest supplier on 1688 for, compare 1688 suppliers for, use 1688, run 1688.
mvanhorn/printing-press-library
Inspect known Activity Japan plan IDs or URLs, compare dated prices and sessions, check language-sitemap coverage, and hand off to canonical booking pages.
mvanhorn/printing-press-library
Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...
mvanhorn/printing-press-library
macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.
Works with
Categories
Trade prediction markets, persist tick data, and answer category-level P&L questions Kalshi.com cannot. Pp Kalshi is an agent skill from mvanhorn/printing-press-library.com cannot.
Pp Kalshi fits situations like: phrases: kalshi market price; track prediction market; kalshi portfolio P&L; kalshi correlate markets.
Run `npx skills add mvanhorn/printing-press-library --skill pp-kalshi -a claude-code`. Or copy the skill folder (cli-skills/pp-kalshi in mvanhorn/printing-press-library) into .claude/skills/pp-kalshi in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mvanhorn/printing-press-library --skill pp-kalshi -a codex`. Or copy the skill folder (cli-skills/pp-kalshi in mvanhorn/printing-press-library) into .agents/skills/pp-kalshi in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mvanhorn/printing-press-library --skill pp-kalshi -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pp-kalshi, .gemini/skills/pp-kalshi, .github/skills/pp-kalshi and .opencode/skills/pp-kalshi in your project.
Going by SKILL.md and its folder, Pp Kalshi needs the command-line tools its instructions call (go, claude and npx) and credentials named KALSHI_API_KEY and KALSHI_PRIVATE_KEY. Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Bash.
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Pp Kalshi is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 6.6k tokens (SKILL.md is roughly 27k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Pp Kalshi: Digital Oracle (komako-workshop/digital-oracle, 878 stars), Dr Manhattan (guzus/dr-manhattan, 204 stars), Kalshi Trade (ryanfrigo/kalshi-ai-trading-bot, 613 stars) and Polymarket Tennis (livetennisapi/livetennisapi-mcp, 152 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mvanhorn (a GitHub user) maintains it in mvanhorn/printing-press-library, which has 2,056 GitHub stars. The repository holds 506 skills in this directory. The repository was last updated on October 9, 2026.
Source: mvanhorn/printing-press-library on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.