Sqlite Specialist
FerroxLabs/wayland
SQLite expertise for application development covering WAL mode configuration, concurrent access patterns, FTS5 full-text search, JSON support, virtual tables, PRAGMA optimization, backup strategies…
Every Splitwise feature, plus an offline SQLite ledger that powers balance, debt-aging, spend analytics, fairness, and full-text search no other Splitwise tool has.
$ npx skills add mvanhorn/printing-press-library --skill pp-splitwise -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mvanhorn/printing-press-library pp-splitwise --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-splitwise .claude/skills/pp-splitwise && 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-splitwise" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-splitwise into .claude/skills/pp-splitwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-splitwise", 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-splitwiseType 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-splitwise -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mvanhorn/printing-press-library pp-splitwise --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-splitwise .agents/skills/pp-splitwise && 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-splitwise" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-splitwise into .agents/skills/pp-splitwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-splitwise", 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-splitwise -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mvanhorn/printing-press-library pp-splitwise --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-splitwise .cursor/skills/pp-splitwise && 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-splitwise" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-splitwise into .cursor/skills/pp-splitwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-splitwise", 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-splitwise--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-splitwise -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mvanhorn/printing-press-library pp-splitwise --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-splitwise .gemini/skills/pp-splitwise && 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-splitwise" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-splitwise into .gemini/skills/pp-splitwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-splitwise", 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-splitwiseInstalls 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-splitwise -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-splitwise .github/skills/pp-splitwise && 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-splitwise" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-splitwise into .github/skills/pp-splitwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-splitwise", 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-splitwise -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-splitwise --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-splitwise .opencode/skills/pp-splitwise && 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-splitwise" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-splitwise into .opencode/skills/pp-splitwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-splitwise", 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-splitwiseEvery Splitwise feature, plus an offline SQLite ledger that powers balance, debt-aging, spend analytics, fairness, and full-text search no other Splitwise tool has.
Pp Splitwise is an agent skill from mvanhorn/printing-press-library. Every Splitwise feature, plus an offline SQLite ledger that powers balance, debt-aging, spend analytics, fairness, and full-text search no other Splitwise tool has. Trigger phrases: what do I owe on splitwise, who owes me money, split this expense, settle up the trip, how much did we spend on food, use splitwise, run splitwise.
Its SKILL.md is about 9.7k 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 Backend & APIs, covering Search implementation. It works with SQLite. 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.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 7638ad4. 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:
claudenpxFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
secure.splitwise.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
SPLITWISE_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pp Splitwise loads about 9.7k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 4,262 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 7638ad4, republished under its Apache-2.0 licence (© mvanhorn). 4,262 words, ~9,690 tokens.
.claude/skills/pp-splitwise/SKILL.md (or your agent's skills folder).<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/payments/splitwise/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 splitwise-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:npx -y @mvanhorn/printing-press-library install splitwise --cli-onlysplitwise-pp-cli --version$PATH for the agent/runtime that will invoke this skill.If the npx install fails before this CLI has a public-library category, install Node or use the category-specific Go fallback after publish.
If --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.
splitwise-pp-cli wraps the full Splitwise API — expenses, groups, friends, comments, settle-ups — and keeps a local copy of your whole ledger. That local store powers a net balances view, debts --aged (who never pays you back), spend rollups by category or month, offline search, a group ledger with running balances, fairness and net for who's carrying cost and how balances collapse across groups, and a settle-up plan that minimizes transfers. brief gives an agent one bounded state digest, and reconcile verifies the local store still matches Splitwise before you trust any of it. Fuzzy name resolution means you never paste a numeric ID.
Reach for splitwise-pp-cli when a task involves shared expenses, group trips, roommate bills, or settling up — logging an expense, checking who owes whom, aging a stale debt, rolling up spend by category, finding a past expense, checking who's carrying more than their share, or computing a settle-up plan. It is the right tool when you want offline analytics or a verified local copy of a Splitwise account, not a one-off live lookup. Under --agent every command wraps its payload as {"meta": {...}, "results": ...}; --json returns the bare payload.
Do not use this CLI for:
These capabilities aren't available in any other tool for this API.
balances — See everything you owe and are owed across every friend and group in one net-position view.
Reach for this instead of separate get-groups + get-friends calls when an agent needs the user's overall money position.
splitwise-pp-cli balances --by-currency --agentdebts — List who owes you (and whom you owe) sorted by how long the balance has gone unsettled.
Use when the task is 'who never pays me back' or chasing stale IOUs, not just the current balance.
splitwise-pp-cli debts --aged --agentnet — Collapse a person's balance across every group and non-group expense into the minimum set of real-world transfers.
Use when one person's balance is scattered across multiple groups and one-off expenses and you want the fewest real transfers, not a per-group snapshot.
splitwise-pp-cli net --agentledger — Every expense in a group, in date order, with a cumulative running balance per member.
Use to audit how a group's balances got to where they are, not just the snapshot. Add --friend to replay one person across every group instead of one group's members.
splitwise-pp-cli ledger "Tahoe Trip" --agentbalances — See one row per group per currency for every non-zero balance, without the noise of settled groups.
Use when the question is scoped to 'which groups do I still owe in', not the single net number.
splitwise-pp-cli balances --by-group --agentsettle-up — Compute the minimum set of transfers that zeroes out balances in a group, then optionally record the payments (print-only by default; --record writes real payment expenses to your Splitwise account).
Use when a group wants the fewest transfers to get everyone to zero, previewed before anything is recorded.
splitwise-pp-cli settle-up "Tahoe Trip" --agentaudit — Catch duplicate settlement rows and abnormal expense amounts before you trust a settle-up plan.
Run this before settle-up or report so a duplicate settlement or an outlier expense doesn't get baked into a transfer plan.
splitwise-pp-cli audit --since 90d --agentsplit — Build and preview the exact expense split (equal, exact, percentage, or shares) before recording it.
Reach for this to turn 'I paid $84, split equally with the trip' into a ready-to-record expense without hand-building the share arrays. Add --record to submit it.
splitwise-pp-cli split "Tahoe Trip" --amount 84 --equal --agentfairness nudge — Post a payment reminder as a comment on the actual open expense thread, previewed before it sends (print-only by default; --send posts a real comment your friend will see).
Use to nudge one person about a specific unpaid expense instead of a generic message outside Splitwise.
splitwise-pp-cli fairness nudge "Jordan"reconcile — Verify the local store actually matches Splitwise before you trust a settle-up or report (calls the live Splitwise API; needs SPLITWISE_API_KEY and network).
Run this before a settle-up or report when a number looks wrong, or as a routine pre-settle check.
splitwise-pp-cli reconcile --since 30d --agentspend — Total shared spend broken down by category, group, or month from your synced history.
Use for any 'how much did we spend on X' question instead of paging the whole expense list.
splitwise-pp-cli spend --group-by category --since 30d --agentfairness — See who's carrying more than their share of cost, and how likely a stale balance is to actually get paid.
Use when the question is who's owed the most relative to what they've paid, not just the raw balance.
splitwise-pp-cli fairness --by collectability --agentreport — Turn synced trip or period spend into a shareable summary plus per-person and per-category export.
Use for an end-of-trip or end-of-month writeup, or as a generic JSON/CSV sink into an external workflow tool.
splitwise-pp-cli report --group "Tahoe Trip" --format mdrecurring — Surface repeating charges (rent, utilities, subscriptions) from your synced history and flag a cycle missing an expected entry.
Use to catch a shared monthly bill nobody remembered to log this cycle.
splitwise-pp-cli recurring --agentforecast — See what shared bills are expected next, projected from your recurring-expense history.
Use for 'what's coming up' instead of recurring, which only detects the pattern of bills already logged.
splitwise-pp-cli forecast --agentnormalize — Express multi-currency spend in one base currency, using rates you supply, with anything unconverted called out honestly.
Use when spend spans more than one currency and you want one honest number, not a silently-dropped or auto-converted total.
splitwise-pp-cli normalize --base USD --rate EUR=1.08 --agentbrief — Get one compact digest of net position, the stalest debts, and what changed since last sync in a single call.
Reach for this first at the start of a session instead of three separate calls; use balances, debts --aged, or activity directly when you need the full detail behind one of these numbers.
splitwise-pp-cli brief --agent --compactactivity — Show what changed since your last sync — new, edited, and deleted expenses to review.
Use to reconcile recent account activity before settling or reporting.
splitwise-pp-cli activity --agentadd-user-to-group — Manage add user to group
splitwise-pp-cli add-user-to-group — Note: 200 OK does not indicate a successful response. You must check the success value of the response.create-comment — Manage create comment
splitwise-pp-cli create-comment — Create a commentcreate-expense — Manage create expense
splitwise-pp-cli create-expense — Creates an expense. You may either split an expense equally (only with group_id provided), or supply a list of shares.create-friend — Manage create friend
splitwise-pp-cli create-friend — Adds a friend. If the other user does not exist, you must supply user_first_name.create-friends — Manage create friends
splitwise-pp-cli create-friends — Add multiple friends at once.create-group — Manage create group
splitwise-pp-cli create-group — Creates a new group. Adds the current user to the group by default.delete-comment — Manage delete comment
splitwise-pp-cli delete-comment <id> — Deletes a comment. Returns the deleted comment.delete-expense — Manage delete expense
splitwise-pp-cli delete-expense <id> — Note: 200 OK does not indicate a successful response. The operation was successful only if success is true.delete-friend — Manage delete friend
splitwise-pp-cli delete-friend <id> — Given a friend ID, break off the friendship between the current user and the specified user.delete-group — Manage delete group
splitwise-pp-cli delete-group <id> — Delete an existing group. Destroys all associated records (expenses, etc.)get-categories — Manage get categories
splitwise-pp-cli get-categories — Returns a list of all categories Splitwise allows for expenses.get-comments — Manage get comments
splitwise-pp-cli get-comments — Get expense commentsget-currencies — Manage get currencies
splitwise-pp-cli get-currencies — Returns a list of all currencies allowed by the system.get-current-user — Manage get current user
splitwise-pp-cli get-current-user — Get information about the current userget-expense — Manage get expense
splitwise-pp-cli get-expense <id> — Get expense informationget-expenses — Manage get expenses
splitwise-pp-cli get-expenses — List the current user's expensesget-friend — Manage get friend
splitwise-pp-cli get-friend <id> — Get details about a friendget-friends — Manage get friends
splitwise-pp-cli get-friends — Note: group objects only include group balances with that friend.get-group — Manage get group
splitwise-pp-cli get-group <id> — Get information about a groupget-groups — Manage get groups
splitwise-pp-cli get-groups — Note: Expenses that are not associated with a group are listed in a group with ID 0.get-notifications — Manage get notifications
splitwise-pp-cli get-notifications — Return a list of recent activity on the users account with the most recent items first.get-user — Manage get user
splitwise-pp-cli get-user <id> — Get information about another userremove-user-from-group — Manage remove user from group
splitwise-pp-cli remove-user-from-group — Remove a user from a group. Does not succeed if the user has a non-zero balance.undelete-expense — Manage undelete expense
splitwise-pp-cli undelete-expense <id> — Note: 200 OK does not indicate a successful response. The operation was successful only if success is true.undelete-group — Manage undelete group
splitwise-pp-cli undelete-group <id> — Restores a deleted group. Note: 200 OK does not indicate a successful response.update-expense — Manage update expense
splitwise-pp-cli update-expense <id> — Updates an expense.update-user — Manage update user
splitwise-pp-cli update-user <id> — Update a userThis printed CLI owns bounded freshness only for registered store-backed read command paths. In --data-source auto mode, those paths check sync_state and may run a bounded refresh before reading local data. --data-source local never refreshes. --data-source live reads the API and does not mutate the local store. Set SPLITWISE_NO_AUTO_REFRESH=1 to skip the freshness hook without changing source selection.
Covered paths:
splitwise-pp-cli get-categoriessplitwise-pp-cli get-categories getsplitwise-pp-cli get-categories listsplitwise-pp-cli get-categories searchsplitwise-pp-cli get-commentssplitwise-pp-cli get-comments getsplitwise-pp-cli get-comments listsplitwise-pp-cli get-comments searchsplitwise-pp-cli get-currenciessplitwise-pp-cli get-currencies getsplitwise-pp-cli get-currencies listsplitwise-pp-cli get-currencies searchsplitwise-pp-cli get-current-usersplitwise-pp-cli get-current-user getsplitwise-pp-cli get-current-user listsplitwise-pp-cli get-current-user searchsplitwise-pp-cli get-expensessplitwise-pp-cli get-expenses getsplitwise-pp-cli get-expenses listsplitwise-pp-cli get-expenses searchsplitwise-pp-cli get-friendssplitwise-pp-cli get-friends getsplitwise-pp-cli get-friends listsplitwise-pp-cli get-friends searchsplitwise-pp-cli get-groupssplitwise-pp-cli get-groups getsplitwise-pp-cli get-groups listsplitwise-pp-cli get-groups searchsplitwise-pp-cli get-notificationssplitwise-pp-cli get-notifications getsplitwise-pp-cli get-notifications listsplitwise-pp-cli get-notifications searchWhen JSON output uses the generated provenance envelope, freshness metadata appears at meta.freshness. Treat it as current-cache freshness for the covered command path, not a guarantee of complete historical backfill or API-specific enrichment.
When you know what you want to do but not which command does it, ask the CLI directly:
splitwise-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. --json (and other machine formats) keep that exit-2 contract and write {"matches":[]} on stdout so agents can inspect the envelope without treating a miss as success.
splitwise-pp-cli balances --agent --select by_currencyReturns just the headline numbers an agent needs to report the user's overall money position.
splitwise-pp-cli get-groups --agent --select name,members.first_name,members.balance.amountget-groups returns deeply nested members and balance arrays; --select with dotted paths keeps only the fields you need so an agent doesn't burn context on the full payload.
splitwise-pp-cli reconcile --since 30d --agentDiffs the local store against live get_expenses and reports anything missing, stale, or deleted remotely before you build a settle-up or report on it.
splitwise-pp-cli brief --agent --compactReturns net position, the stalest debts, and recent activity in one bounded call instead of three separate fan-out calls.
splitwise-pp-cli settle-up "Tahoe Trip"Prints the minimum-transfer settle-up plan; add --record to create the payment expenses.
splitwise-pp-cli fairness --by contribution --group "Tahoe Trip" --agentClassifies each member as carrier or rider from paid vs owed shares; --by risk and --by collectability switch lenses. The --agent output is wrapped as {meta, results}.
splitwise-pp-cli resolve "Alex Kim" --type friend --agentUse resolve whenever you need an id for a name: it matches the local store (no network) and returns the candidate records. Do not page through get-friends or get-groups and grep for a name; resolve is the id lookup.
Splitwise authenticates with a personal API key used as an HTTP Bearer token. Register an app at https://secure.splitwise.com/apps to get your key, then set SPLITWISE_API_KEY. The Splitwise API also offers OAuth 2.0 (authorization-code) for multi-user apps, but this CLI authenticates as a single user with a personal API key only — there is no OAuth login flow in the binary.
Run splitwise-pp-cli doctor to verify setup.
Add --agent to any command. Expands to: --json --compact --no-input --no-color.
Global format flags share one contract on promoted, novel, sync, and --deliver paths:
--json — one JSON document on stdout (sync progress events go to stderr)
--compact — keep identity/status/timestamp fields; does not change the document vs stream shape
--csv / --plain — tabular rows (collection envelopes unwrap to the row array)
--quiet — one identity value per row, no envelope
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:
splitwise-pp-cli get-categories --agentPreviewable — --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
Explicit confirmation — --agent does not imply --yes; pass --yes separately only after the target, arguments, and side effects are clear
Explicit retries — use --idempotent only when an already-existing create should count as success
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 AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.
Agents should treat the CLI's path resolver as part of the runtime contract:
Use --home <dir> for one invocation, or set SPLITWISE_HOME=<dir> to relocate all four path kinds under one root.
Use per-kind env vars only when a specific kind must diverge: SPLITWISE_CONFIG_DIR, SPLITWISE_DATA_DIR, SPLITWISE_STATE_DIR, SPLITWISE_CACHE_DIR.
Resolution order is per-kind env var, --home, SPLITWISE_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.
config contains settings like config.toml and profiles. data contains credentials.toml, data.db, cookies, and auth sidecars. state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.
Stored secrets live in credentials.toml under the data dir. Existing legacy config.toml secrets are read for compatibility and leave config.toml on the first auth write.
Run splitwise-pp-cli doctor --fail-on warn to surface path and credential-location warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.
For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:
{
"mcpServers": {
"splitwise": {
"command": "splitwise-pp-mcp",
"env": {
"SPLITWISE_HOME": "/srv/splitwise"
}
}
}
}Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use SPLITWISE_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing SPLITWISE_HOME, or doctor will not find credentials left under the former root.
This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.
recall before any discoveryBefore list/search/drill commands on a new user question, run:
splitwise-pp-cli recall "<user's question>" --agentThe response envelope:
{
"query": "...",
"normalized": "<normalized form>",
"query_entities": ["..."],
"found": true | false,
"match_score": 0.0,
"results": [
{ "resource_id": "...", "resource_type": "...", "venue": "...",
"confidence": 2, "entity_match": "exact|partial|unknown",
"source": "taught|preseed|pattern", "warnings": ["..."] }
],
"mismatches": [ /* only when --debug-mismatches */ ],
"warnings": [ /* top-level */ ],
"candidates": [
{ "id": 12, "class": "flag_alias | playbook_candidate",
"summary": "...", "sightings": 3, "last_seen": "...",
"rationale": "...",
"next_action": ["<trial command>", "splitwise-pp-cli learnings confirm 12"] }
],
"playbook": {
"query_family": "...",
"playbook": {
"steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
"entity_slots": ["$ENTITY"],
"expected_tool_calls": 3
},
"slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
"notes": "<workarounds + gotchas for this query family>"
},
"notes": "<duplicate surface for non-playbook callers>"
}Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.
Read candidates, playbook, notes, results[0], and warnings in that order:
if Candidates present (warnings include "candidates_present"):
-> candidates are try-then-confirm, never facts. Follow each candidate's
two-step next_action verbatim: run the trial command first, then run
`learnings confirm <id>` only after the trial verified the behavior.
Reject a wrong candidate with `learnings reject <id>`.
-> NEVER re-teach something recall surfaced as a candidate; confirm or
reject that candidate instead of teaching a duplicate.
-> candidates ride alongside playbooks and resource hits, not instead of
them; continue with the branches below after acting on them.
if Playbook present:
-> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
-> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
for the entity slot tokens. If a step's slot is unresolved, fall back to
discovery for that step only.
-> the Playbook's expected_tool_calls is a budget; if you find yourself running
materially more, record the divergence via `splitwise-pp-cli playbook amend`
at end-of-session.
elif Notes present (no Playbook):
-> read Notes verbatim before any discovery step; they carry known gotchas
for this query family even when no structured choreography exists yet.
elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
-> skip discovery; fetch live data for Results[*].ResourceID in parallel
elif Found AND Results[0].EntityMatch == "partial":
-> candidate hint, NOT a hit; read the resource title to validate before trusting
elif (any row in Mismatches[] when --debug-mismatches was passed):
-> treat as cold start; the stored learning is for a different entity
(different canonical resolved from query_entities)
else: // Found == false, no playbook, no notes
-> cold start; run discovery normally; teach the answer afterward (Step 4).
If the family has no playbook yet, that teach auto-synthesizes a
playbook candidate from this session's journal - you do not need to
record one by hand.Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.
Candidate judgment details: learnings confirm <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; splitwise-pp-cli learnings candidates lists the full open set.
Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.
warningslow_confidence: row exists at confidence<2. Treat as a hint, not a skip-discovery hit.resource_not_in_store: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate.cross_alias_match (per-result): the row was taught under a different alias and matched the live query's canonical via entity_lookups (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id.similar_shape_different_entity:<canonical> (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results.ambiguous_alias (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource.candidates_present (top-level): the envelope carries a candidates section. Handle it via the candidates branch in Step 2 before anything else.lookup_refresh_available (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run splitwise-pp-cli sync to refresh entity lookups.no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.teach & after finalizing your response - alwaysTeaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell & so the call returns immediately:
splitwise-pp-cli teach --query "<user's question>" --resource-type <type> --resource <id1> --resource <id2>
# (append shell `&` to background it)Silent on success. Errors only land in teach.log under the resolved state dir. Teach the most specific resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded entity_lookups for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically.
PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning.
You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a playbook_candidate from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the integrated one-call form - record the resource learning and the playbook in the same teach invocation:
# Common case: record both the resource learning AND the playbook in one call.
splitwise-pp-cli teach \
--query "<user's question>" \
--resource <id> \
--playbook-file ~/playbooks/<shape>.json \
--playbook-notes-file ~/playbooks/<shape>-notes.md
# (append shell `&` to background it)
# Alternate: playbook-only (no resource to record alongside).
splitwise-pp-cli teach-playbook \
--query "<user's question>" \
--playbook-file ~/playbooks/<shape>.json \
--notes-file ~/playbooks/<shape>-notes.mdPlaybook files are JSON with steps, entity_slots, expected_tool_calls. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: --playbook-json and --playbook-notes on the integrated teach form, --playbook-json and --notes on teach-playbook. On the integrated teach form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone teach-playbook form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with slots_resolved binding the live query's canonical at recall time.
When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with slots_resolved substitutions, skip the discovery that the choreography already documents, and read notes before any step.
playbook amend & when your debug response identifies a correctionIf your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire playbook amend BEFORE emitting your user-facing response. Same fire-and-forget posture as teach.
splitwise-pp-cli playbook amend \
--query "<exact recall query string>" \
--add-note "<your concrete correction>"
# (append shell `&` to background it)What counts as worth amending: a behavior you OBSERVED this session that future-you would benefit from knowing. Examples worth amending:
{meta, results}, payload nested two levels deeper than the docs claim).What does NOT belong in notes:
The amend command appends to the family's existing notes with a timestamped marker ([amend YYYY-MM-DDTHH:MMZ]: <text>). Multiple amends accumulate; the audit trail is visible. If no playbook exists yet for the family, amend creates a notes-only one (so cold-start corrections still land).
playbook amend notes are designed to potentially flow upstream as shared knowledge in future versions of the Printing Press. Keep them clean of user-identifying content so the upstream-contribution path stays open without retroactive scrubbing:
If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend.
splitwise-pp-cli learnings stats reports recall hit rate, teach-to-reuse, playbook resolution rate, and candidate confirm/reject counts from the local learn_events table. Rates are null until they have a denominator; everything stays on this machine. Use it to check whether the loop is earning its keep for this CLI.
--no-learn on a single command short-circuits both recall and the teach write path. Use for deterministic agent flows or tests that must not be affected by accumulated learnings.SPLITWISE_NO_LEARN=true in the environment globally disables the pipeline.When you (or the agent) notice something off about this CLI, record it:
splitwise-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
splitwise-pp-cli feedback --stdin < notes.txt
splitwise-pp-cli feedback list --json --limit 10Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless SPLITWISE_FEEDBACK_ENDPOINT is set AND either --send is passed or SPLITWISE_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). Binary-response commands write decoded payload bytes (not the base64 JSON envelope) and print a small JSON receipt on stdout; --json/--csv do not refuse when this sink is set. |
webhook:<url> | POST the output body to the URL (application/json) |
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 or recurring agent reuses the same saved flags while providing different input each run.
splitwise-pp-cli profile save briefing --json
splitwise-pp-cli --profile briefing get-categories
splitwise-pp-cli profile list --json
splitwise-pp-cli profile show briefing
splitwise-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 splitwise-pp-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)Install the MCP binary from this CLI's published public-library entry or pre-built release, then register it:
claude mcp add splitwise-pp-mcp -- splitwise-pp-mcpVerify: claude mcp list
which splitwise-pp-cli
If not found, offer to install (see Prerequisites at the top of this skill).--agent flag:splitwise-pp-cli <command> [subcommand] [args] --agentsplitwise-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-splitwise of mvanhorn/printing-press-library.
Open the folder on GitHubat commit 7638ad4
Pp Splitwise 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 Splitwise this skillmvanhorn/printing-press-library | 2.1k | — | ~9.7k | Automated safety check: Notes | Apache-2.0 | |
| Sqlite SpecialistFerroxLabs/wayland | 608 | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | |
| Firecrawl Search Integrationfirecrawl/firecrawl | 189k | 1 repos | ~1.1k | Automated safety check: Pass | ISC | |
| Durable Objectshodgef/apiker | 127 | 4 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Product Full-Text Searchlobehub/lobehub | 83k | — | ~4.1k | Automated safety check: Pass | Custom licence | |
| Fd Auditmarketcalls/openalgo | 2.8k | — | ~2.1k | Automated safety check: Pass | AGPL-3.0 |
FerroxLabs/wayland
SQLite expertise for application development covering WAL mode configuration, concurrent access patterns, FTS5 full-text search, JSON support, virtual tables, PRAGMA optimization, backup strategies…
firecrawl/firecrawl
Guidance for adding Firecrawl's /search endpoint to product code and agent workflows when a feature starts from a query rather than a URL.
hodgef/apiker
Create and review Cloudflare Durable Objects. An agent skill from hodgef/apiker.
lobehub/lobehub
Guides work on LobeHub's own product search: the shared search repository, provider choice, Elasticsearch mappings, change syncing and reindexing.
marketcalls/openalgo
Audit a change for resource leaks in OpenAlgo — file descriptors AND unbounded memory growth.
marcus/sidecar
Create conversation adapters for importing AI chat history from different tools (Claude Code, Cursor, Warp, Codex, etc.).
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
Every Splitwise feature, plus an offline SQLite ledger that powers balance, debt-aging, spend analytics, fairness, and full-text search no other Splitwise tool has. Pp Splitwise is an agent skill from mvanhorn/printing-press-library. Every Splitwise feature, plus an offline SQLite ledger that powers balance, debt-aging, spend analytics, fairness, and full-text search no other Splitwise tool has.
Pp Splitwise fits situations like: phrases: what do I owe on splitwise; who owes me money; split this expense; settle up the trip.
Run `npx skills add mvanhorn/printing-press-library --skill pp-splitwise -a claude-code`. Or copy the skill folder (cli-skills/pp-splitwise in mvanhorn/printing-press-library) into .claude/skills/pp-splitwise in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mvanhorn/printing-press-library --skill pp-splitwise -a codex`. Or copy the skill folder (cli-skills/pp-splitwise in mvanhorn/printing-press-library) into .agents/skills/pp-splitwise 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-splitwise -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-splitwise, .gemini/skills/pp-splitwise, .github/skills/pp-splitwise and .opencode/skills/pp-splitwise in your project.
Going by SKILL.md and its folder, Pp Splitwise needs the command-line tools its instructions call (claude and npx) and credentials named SPLITWISE_API_KEY. Our summary lists: Node.js; A credential in SPLITWISE_API_KEY. Its frontmatter pre-approves these tools: Read, Bash.
SKILL.md names 1 domain. As links in the text: secure.splitwise.com. 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 Splitwise 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 9.7k tokens (SKILL.md is roughly 39k 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 Splitwise: Sqlite Specialist (FerroxLabs/wayland, 608 stars), Firecrawl Search Integration (firecrawl/firecrawl, 189k stars), Durable Objects (hodgef/apiker, 127 stars) and Product Full-Text Search (lobehub/lobehub, 83k 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 2,053 GitHub stars. The repository holds 505 skills in this directory. The repository was last updated on October 6, 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.