# Pp Ynab > Every YNAB feature, plus a local mirror that makes reconciliation, payee trend analysis, and a ready-made ProjectionLab export instant instead of manual. Trigger phrases: `check my YNAB budget`, `what's left in my dining category`, `sync my YNAB balances`, `reconcile my checking account`, `will I overspend this month`, `export my YNAB balances`, `use ynab`, `run ynab`. - Skill: `mvanhorn-printing-press-libra/pp-ynab` (Agent Skill) - Install (CLI): `npx skillmds add mvanhorn-printing-press-libra/pp-ynab` - Raw SKILL.md: https://api.skillmd.com/api/skills/mvanhorn-printing-press-libra/pp-ynab/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Finance & Business - License: Apache-2.0 - Author: mvanhorn (https://skillmd.com/u/mvanhorn-printing-press-libra) - Updated: 2026-09-09 - Page: https://skillmd.com/skills/mvanhorn-printing-press-libra/pp-ynab --- # YNAB — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `ynab-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first: 1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install ynab --cli-only ``` 2. Verify: `ynab-pp-cli --version` 3. Ensure the reported install directory is on `$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 1.26.5 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/other/ynab/cmd/ynab-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. This CLI mirrors your budget locally so bank reconciliation and payee spend history become instant, offline, agent-native commands instead of manual math against a live API and a 200-request-per-hour ceiling. It also ships a one-shot export shaped for downstream net-worth tools like ProjectionLab. ## When to Use This CLI Reach for this CLI for anything touching a YNAB budget: reading balances/categories/transactions, entering or approving transactions, funding categories, and — distinctly — trend/forecast/reconciliation questions that need history the live API doesn't retain. ## Anti-triggers Do not use this CLI for: - Do not use this CLI to manage non-YNAB institutions (bank, brokerage, credit union) directly — it only talks to YNAB. - Do not use this CLI to create YNAB categories, category groups, or payees — the YNAB API itself doesn't support that; use the YNAB app. - Do not use 'export balances' as a general-purpose account API; it's shaped specifically for downstream net-worth tooling. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Agent-native plumbing - **`export balances`** — One-shot export of current account balances reshaped into ProjectionLab's expected schema, ready to sync into a net-worth projection tool. _Use this to feed another finance tool's import step; it's the direct replacement for a hand-maintained account-mapping script._ ```bash ynab-pp-cli export balances --format projectionlab --agent ``` ### Local state that compounds - **`accounts reconcile`** — Diff the local cleared-transaction total against a bank statement balance and surface the transaction(s) most likely responsible for the gap. _Use this monthly instead of eyeballing a statement line by line._ ```bash ynab-pp-cli accounts reconcile a1b2c3d4 --statement-balance 1042.17 --agent ``` - **`payees profile`** — Aggregated monthly spend stats, average transaction size, and typical categories for a single payee. _Use this to understand a recurring payee's spend pattern rather than scanning raw transaction lists._ ```bash ynab-pp-cli payees profile a1b2c3d4 --period 6m --agent ``` ## Command Reference **accounts** — The accounts for a plan. Every transaction belongs to an account, and an account is either "on budget", where its activity is categorized and planned, or a tracking account, where only its balance is tracked (see the on_budget flag). - `ynab-pp-cli accounts create` — Creates a new account - `ynab-pp-cli accounts get` — Returns all accounts - `ynab-pp-cli accounts get-by-id` — Returns a single account **categories** — The categories for a plan, organized into category groups. Category amounts (assigned, activity, available) are specific to a month, and can be read and updated through the month-scoped category endpoints. - `ynab-pp-cli categories create-category` — Creates a new category - `ynab-pp-cli categories get` — Returns all categories grouped by category group. Amounts (assigned, activity, available, etc. - `ynab-pp-cli categories get-category-by-id` — Returns a single category. Amounts (assigned, activity, available, etc.) are specific to the current plan month (UTC). - `ynab-pp-cli categories update-category` — Update a category **category-groups** — Manage category groups - `ynab-pp-cli category-groups create` — Creates a new category group - `ynab-pp-cli category-groups update` — Update a category group **money-movement-groups** — Manage money movement groups - `ynab-pp-cli money-movement-groups ` — Returns all money movement groups **money-movements** — Money movements record money moved between two categories, or between a category and Ready to Assign, within a plan month. Movements performed together as a single action are linked by a money movement group. - `ynab-pp-cli money-movements ` — Returns all money movements **months** — Each plan contains one or more months, which is where Ready to Assign, Age of Money and category (assigned / activity / available) amounts are available. - `ynab-pp-cli months get-plan` — Returns all plan months - `ynab-pp-cli months get-plan-plans` — Returns a single plan month **payee-locations** — When you enter a transaction and specify a payee on the YNAB mobile apps, the GPS coordinates for that location are stored, with your permission, so that the next time you are in the same place (like the Grocery store) we can pre-populate nearby payees for you! It’s handy and saves you time. This resource makes these locations available. Locations will not be available for all payees. - `ynab-pp-cli payee-locations get` — Returns all payee locations - `ynab-pp-cli payee-locations get-by-id` — Returns a single payee location **payees** — The payees for a plan. Transfers between accounts are represented with special transfer payees; a payee with transfer_account_id set is the transfer payee for that account. - `ynab-pp-cli payees create` — Creates a new payee - `ynab-pp-cli payees get` — Returns all payees - `ynab-pp-cli payees get-by-id` — Returns a single payee - `ynab-pp-cli payees update` — Update a payee **plans** — Plans are the top-level container for your YNAB data; accounts, categories, payees, and transactions all belong to a plan. Most endpoints require a plan_id, which can be obtained from "Get all plans". Alternatively, "last-used" can be used in place of a plan_id to specify the most recently used plan, and "default" can be used if [default plan selection](https://api.ynab.com/#oauth-default-plan) is enabled. - `ynab-pp-cli plans get` — Returns plans list with summary information - `ynab-pp-cli plans get-by-id` — Returns a single plan with all related entities. This resource is effectively a full plan export. **scheduled-transactions** — The scheduled transactions for a plan; upcoming and recurring transactions that have not yet been entered into an account. Each has a frequency along with the first and next dates it will occur (date_first and date_next). - `ynab-pp-cli scheduled-transactions create` — Creates a single scheduled transaction (a transaction with a future date). - `ynab-pp-cli scheduled-transactions delete` — Deletes a scheduled transaction - `ynab-pp-cli scheduled-transactions get` — Returns all scheduled transactions - `ynab-pp-cli scheduled-transactions get-by-id` — Returns a single scheduled transaction - `ynab-pp-cli scheduled-transactions update` — Updates a single scheduled transaction **settings** — Manage settings - `ynab-pp-cli settings ` — Returns settings for a plan **transactions** — The transactions for a plan. Transaction amounts are specified in [milliunits format](https://api.ynab.com/#formats). Split transactions are represented with subtransactions, and transfers between accounts are represented with transfer payees. - `ynab-pp-cli transactions create` — Creates a single transaction or multiple transactions. - `ynab-pp-cli transactions delete` — Deletes a transaction - `ynab-pp-cli transactions get` — Returns plan transactions, excluding any pending transactions - `ynab-pp-cli transactions get-by-id` — Returns a single transaction - `ynab-pp-cli transactions import` — Imports available transactions on all linked accounts for the given plan. - `ynab-pp-cli transactions update` — Updates multiple transactions, by `id` or `import_id`. - `ynab-pp-cli transactions update-plans` — Updates a single transaction **user** — The currently authenticated user - `ynab-pp-cli user` — Returns authenticated user information ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash ynab-pp-cli which "" ``` `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. ## Recipes ### Feed ProjectionLab ```bash ynab-pp-cli export balances --format projectionlab --agent --select accounts.name,accounts.balance,accounts.type ``` Narrow the ProjectionLab-shaped export down to just the fields the downstream tool needs, keeping agent context small. ### Batch-approve pending transactions ```bash ynab-pp-cli transactions get 550e8400-e29b-41d4-a716-446655440000 --type unapproved --json ``` List everything awaiting approval before approving in bulk. ### Reconcile against a bank statement ```bash ynab-pp-cli accounts reconcile --statement-balance 1042.17 --agent ``` Surfaces the exact transaction(s) causing a mismatch instead of scanning line by line. ### Understand a recurring payee ```bash ynab-pp-cli payees profile --period 6m --agent ``` Shows monthly spend, average transaction size, and typical categories for one payee instead of scanning raw transactions. ## Auth Setup Uses a YNAB Personal Access Token (Account Settings -> Developer Settings -> New Token in the YNAB web app). Set YNAB_API_TOKEN, or run auth login to store it in the OS keychain. Run `ynab-pp-cli doctor` to verify setup. ## Agent Mode 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: ```bash ynab-pp-cli accounts get mock-value --agent --select data ``` - **Previewable** — `--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 retries** — use `--idempotent` only when an already-existing create should count as success, and use `--ignore-missing` only when a missing delete target should count as success ### Response envelope Commands that read from the local store or the API wrap output in a provenance envelope: ```json { "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": } ``` 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. ## Paths and state Agents should treat the CLI's path resolver as part of the runtime contract: - Use `--home ` for one invocation, or set `YNAB_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `YNAB_CONFIG_DIR`, `YNAB_DATA_DIR`, `YNAB_STATE_DIR`, `YNAB_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `YNAB_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 `ynab-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: ```json { "mcpServers": { "ynab": { "command": "ynab-pp-mcp", "env": { "YNAB_HOME": "/srv/ynab" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `YNAB_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 `YNAB_HOME`, or `doctor` will not find credentials left under the former root. ## Automatic learning 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. ### Step 1: `recall` before any discovery Before list/search/drill commands on a new user question, run: ```bash ynab-pp-cli recall "" --agent ``` The response envelope: ```json { "query": "...", "normalized": "", "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": ["", "ynab-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$ENTITY"], "expected_tool_calls": 3 }, "slots_resolved": { "$ENTITY": { "token": "", "canonical": "" } }, "notes": "" }, "notes": "" } ``` 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. ### Step 2: decision tree 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 ` only after the trial verified the behavior. Reject a wrong candidate with `learnings reject `. -> 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 `ynab-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 ` prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. `learnings reject ` tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; `ynab-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. ### Step 3: always read `warnings` - `low_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:` (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. - Top-level `no_learnings_for_query_family`: the table had no rows above the Jaccard floor. Pure cold start. ### Step 4: `teach &` after finalizing your response - always Teaching 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: ```bash ynab-pp-cli teach --query "" --resource-type --resource --resource # (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. ### Step 5: playbooks - optional flags, automatic synthesis 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: ```bash # Common case: record both the resource learning AND the playbook in one call. ynab-pp-cli teach \ --query "" \ --resource \ --playbook-file ~/playbooks/.json \ --playbook-notes-file ~/playbooks/-notes.md # (append shell `&` to background it) # Alternate: playbook-only (no resource to record alongside). ynab-pp-cli teach-playbook \ --query "" \ --playbook-file ~/playbooks/.json \ --notes-file ~/playbooks/-notes.md ``` Playbook 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. ### Step 6: `playbook amend &` when your debug response identifies a correction If 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`. ```bash ynab-pp-cli playbook amend \ --query "" \ --add-note "" # (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: - A workaround for a CLI surface that silently drops or misorders a flag. - An undocumented endpoint shape (response wrapped in `{meta, results}`, payload nested two levels deeper than the docs claim). - Observed schema drift (a field renamed, an index that shifted between seasons, a category label that the API now returns lower-cased). What does NOT belong in notes: - The year-specific or entity-specific answer to the user's question. That's the response, not a learning. - Per-team / per-athlete / per-row data the playbook already retrieves at runtime. - Statements that paraphrase what the existing notes already say. The amend command appends to the family's existing notes with a timestamped marker (`[amend YYYY-MM-DDTHH:MMZ]: `). 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). #### PII discipline for amend notes `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: - **Do NOT embed** paths to user filesystems, personal API keys or tokens, user email addresses, user GitHub handles, or specific query histories tied to a single user. - **Acceptable**: endpoint shapes, undocumented field names, API gotchas, observed schema drift, workarounds for CLI surfaces, generalizable pagination or retry tactics. If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend. ### Measuring the loop `ynab-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. ### Disabling learning - `--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. - `YNAB_NO_LEARN=true` in the environment globally disables the pipeline. ## Agent Feedback When you (or the agent) notice something off about this CLI, record it: ``` ynab-pp-cli feedback "the --since flag is inclusive but docs say exclusive" ynab-pp-cli feedback --stdin < notes.txt ynab-pp-cli feedback list --json --limit 10 ``` Entries are stored locally as `feedback.jsonl` under the resolved data dir. They are never POSTed unless `YNAB_FEEDBACK_ENDPOINT` is set AND either `--send` is passed or `YNAB_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. ## Output Delivery Every command accepts `--deliver `. 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:` | Atomically write output to `` (tmp + rename) | | `webhook:` | 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. ## Named Profiles 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. ``` ynab-pp-cli profile save briefing --json ynab-pp-cli --profile briefing accounts get mock-value ynab-pp-cli profile list --json ynab-pp-cli profile show briefing ynab-pp-cli profile delete briefing --yes ``` Explicit 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. ## Exit Codes | 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 | ## Argument Parsing Parse `$ARGUMENTS`: 1. **Empty, `help`, or `--help`** → show `ynab-pp-cli --help` output 2. **Starts with `install`** → ends with `mcp` → MCP installation; otherwise → see Prerequisites above 3. **Anything else** → Direct Use (execute as CLI command with `--agent`) ## MCP Server Installation 1. Install the MCP server: ```bash go install github.com/mvanhorn/printing-press-library/library/other/ynab/cmd/ynab-pp-mcp@latest ``` 2. Register with Claude Code: ```bash claude mcp add ynab-pp-mcp -- ynab-pp-mcp ``` 3. Verify: `claude mcp list` ## Direct Use 1. Check if installed: `which ynab-pp-cli` If not found, offer to install (see Prerequisites at the top of this skill). 2. Match the user query to the best command from the Unique Capabilities and Command Reference above. 3. Execute with the `--agent` flag: ```bash ynab-pp-cli [subcommand] [args] --agent ``` 4. If ambiguous, drill into subcommand help: `ynab-pp-cli --help`.