pp-rentalcarspain

Rental Car Spain — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the rentalcarspain-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:
```
npx -y @mvanhorn/printing-press-library install rentalcarspain --cli-only
```
Verify: rentalcarspain-pp-cli --version
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 1.26.6 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/travel/rentalcarspain/cmd/rentalcarspain-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.

Rental Car Spain searches DoYouSpain (the aggregator that surfaces the cheapest rental companies in an area) and quotes every price with the Full Insurance / Zero Excess tier by default. It cross-checks Delpaso's own site with 'compare', tracks prices over time with 'drift', and alerts on drops with 'watch' — the AutoSlash workflow, for Spain, that no other tool offers.

When to Use This CLI

Use Rental Car Spain when renting a car in Malaga (or elsewhere in Spain) and you want the cheapest full-insurance price, want to track it over days, or want to confirm an aggregator price against the supplier directly. It is built around the workflow of watching DoYouSpain and booking with Delpaso, Record Go or Wiber.

Anti-triggers

Do not use this CLI for:

Do not use it to actually book or pay for a rental — it quotes prices only.
Do not use it for flights or hotels — it is car rental only.
Do not expect live standalone Record Go or Wiber quotes — those come through the DoYouSpain aggregator.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Per-airport recommendation with reviews

recommend [location] <pickup> <dropoff> — Review-aware per-airport view. Attaches customer ratings (Rentalcars primary, DoYouSpain fallback), then shows the top companies at that airport (rating-gated by --min-rating, ranked by trust, priced best-available), a small + bigger fully-insured pick plus cheap base+cover picks, and a full company trust table with caveats. Use it when the airport isn't Málaga and trust matters, not just price.

Cheapest fully-insured, across every source

best <pickup> <dropoff> — Rank the cheapest zero-excess options across all sources: direct companies at their own no-excess price, plus aggregator base rate + a standalone excess-insurance estimate (the money-saver, often cheaper than the rental firm's full cover). Every price shown is a genuine no-excess total. The estimate is a fixed base + per-day, modeled on real iCarHire single-trip quotes; rows leaning on it are tagged ~est. Use --real-only to rank on fully-quoted prices only, --direct-only for companies' own cover, and --excess-cover-base / --excess-cover-per-day to tune the estimate.
direct [location] <pickup> <dropoff> — Full-insurance quotes straight from the suppliers' own sites: Delpaso (Málaga only), Centauro, Drivalia, Clickrent, Goldcar, plus CICAR and Autoreisen (Canary Islands). --options N shows N cars per company. Multi-airport via IATA/name; companies not serving the airport are marked unavailable.

Driver age handled honestly

--driver-age N (on direct, best, recommend, delpaso, etc.) reflects each supplier's real young/senior policy, verified against live booking flows: Centauro adds Conductor joven (+€13/day under 25) / senior (+€7/day at 74+) to the quote; Drivalia adds its young-driver fee from the live offer API; Delpaso computes its published €12/day (min €36, max €100) rule; Clickrent and Goldcar add no online surcharge. Cars a young driver can't rent are shown but tagged ([min age 21] for Goldcar under-21 and Clickrent's per-car 18/21/30 gates). A per-supplier caveat prints under the results.

Skip a supplier you'd rather not contact

--disable-supplier <names> (any command, comma-separated) omits named suppliers from every layer — direct clients and aggregators — for anyone uneasy about a supplier's terms. See the CLI's NOTICE / README "Data sources & acceptable use" for the terms-of-service context.

Multi-source & multi-airport

search/suppliers take --source doyouspain|rentalcars|all to merge aggregators, and a location that can be an IATA code (AGP, ALC…), a DoYouSpain code, or an airport name (accents optional: malaga, coruna). Every offer carries its excess ('none' = fully insured). locations lists supported airports.
Coverage is all 32 of Spain's commercial airports — mainland, Balearics, Canaries and Melilla. Note palma resolves to Palma de Mallorca (PMI) and tenerife to Tenerife South (TFS); use the IATA code for La Palma (SPC) or Tenerife North (TFN).

The renter's ritual

compare — Compare DoYouSpain's cheapest offer for a supplier against that supplier's own booking site, side by side.

Reach for this to confirm the aggregator price is real before booking, the way a careful renter double-checks the company directly.
```
rentalcarspain-pp-cli compare 20/08/2026 27/08/2026 --agent
```
suppliers — One line per supplier — Delpaso, Record Go, Wiber, Sixt and the rest — each with its cheapest full-insurance offer, ranked.

Reach for this to see which of your usual companies is cheapest today without scrolling every offer.
```
rentalcarspain-pp-cli suppliers 20/08/2026 27/08/2026 --agent
```

Local price memory

drift — Show how a saved Malaga search's cheapest full-insurance price has moved across your local snapshots.

Reach for this to decide whether to book now or wait, based on the actual trend not a guess.
```
rentalcarspain-pp-cli drift agp-august --agent
```
watch — Re-quote a saved search and exit 0 when the cheapest full-insurance price is at or below your target, 10 otherwise.

Reach for this in a cron job to get alerted the moment a tracked Malaga rental drops to your price.
```
rentalcarspain-pp-cli watch agp-august --target-price 250 --agent
```
dates — Fan out searches across a date window for a fixed rental length and rank pickup dates by cheapest total.

Reach for this when your dates are flexible and you want the cheapest day to start the rental.
```
rentalcarspain-pp-cli dates --from 15/08/2026 --to 25/08/2026 --nights 7 --agent
```
saved — Name and store a recurring Malaga search so watch and drift can re-run it.

Reach for this to set up the searches that feed watch and drift.
```
rentalcarspain-pp-cli saved add agp-august MAL02 20/08/2026 27/08/2026
```

Command Reference

offers — Raw DoYouSpain offer listing for a location and date range (low-level; prefer the top-level 'search' command)

rentalcarspain-pp-cli offers — Fetch the raw DoYouSpain results HTML for an already-resolved search session

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

rentalcarspain-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.

Recipes

Cheapest week in August at Malaga Airport

rentalcarspain-pp-cli dates --from 10/08/2026 --to 24/08/2026 --nights 7 --sort cheapest --agent

Sweeps pickup dates across two weeks and ranks them by cheapest full-insurance total.

Only my usual companies

rentalcarspain-pp-cli search 20/08/2026 27/08/2026 --supplier delpaso,recordgo,wiber --agent

Filters the aggregator down to the three suppliers you book with.

Track a rental and alert on a drop

rentalcarspain-pp-cli watch agp-august --target-price 250 --agent

Re-quotes a saved search; exits 0 when at or below 250 EUR so cron can notify you.

Narrow the JSON for an agent

rentalcarspain-pp-cli search 20/08/2026 27/08/2026 --agent --select offers.supplier,offers.car,offers.total,offers.full_insurance_total

Returns only the fields an agent needs from a large result set.

Confirm the aggregator price directly

rentalcarspain-pp-cli compare 20/08/2026 27/08/2026 --agent

Puts DoYouSpain's cheapest Delpaso offer next to Delpaso's own quote with the delta.

Quote a young driver honestly

rentalcarspain-pp-cli direct AGP 15/09/2026 22/09/2026 --driver-age 20 --options 4

Adds each supplier's real young-driver surcharge and flags cars a 20-year-old can't rent ([min age 21]), with a per-supplier caveat under the table.

Trust only fully-quoted prices

rentalcarspain-pp-cli best AGP 15/09/2026 22/09/2026 --real-only

Ranks on genuine zero-excess totals only, hiding rows whose total includes the standalone-cover estimate (~est).

Leave out a supplier

rentalcarspain-pp-cli best AGP 15/09/2026 22/09/2026 --disable-supplier goldcar,doyouspain

Skips those suppliers across both the direct and aggregator layers.

Filter by brand or car type

rentalcarspain-pp-cli best AGP 15/09/2026 22/09/2026 --class bmw
rentalcarspain-pp-cli direct AGP 15/09/2026 22/09/2026 --class cabrio --options 3

--class (on best, direct, search, suppliers) matches brands (bmw, mercedes, "alfa romeo"), body types (cabrio, suv, estate, van, coupe, pickup) and sizes (mini, economy, compact, premium, luxury); comma = OR. It matches the model name and decodes ACRISS codes (so IFAR matches suv). On best/direct results stay zero-excess; add --real-only for fully-quoted prices only.

Auth Setup

No account or API key needed — the suppliers' sites are public. Rental Car Spain sends an honest, non-browser User-Agent (rentalcarspain-pp-cli/…) that identifies the tool rather than impersonating a browser; 'doctor' verifies connectivity. See the README "Data sources & acceptable use" for the terms-of-service considerations before running it.

Run rentalcarspain-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:
```
rentalcarspain-pp-cli offers --s example-value --b example-value --agent --select id,name,status
```
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
Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Response envelope

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.

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

Use --home <dir> for one invocation, or set RENTALCARSPAIN_HOME=<dir> to relocate all four path kinds under one root.
Use per-kind env vars only when a specific kind must diverge: RENTALCARSPAIN_CONFIG_DIR, RENTALCARSPAIN_DATA_DIR, RENTALCARSPAIN_STATE_DIR, RENTALCARSPAIN_CACHE_DIR.
Resolution order is per-kind env var, --home, RENTALCARSPAIN_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 rentalcarspain-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": {
    "rentalcarspain": {
      "command": "rentalcarspain-pp-mcp",
      "env": {
        "RENTALCARSPAIN_HOME": "/srv/rentalcarspain"
      }
    }
  }
}

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use RENTALCARSPAIN_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 RENTALCARSPAIN_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:

rentalcarspain-pp-cli recall "<user's question>" --agent

The 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>", "rentalcarspain-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.

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 <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 `rentalcarspain-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; rentalcarspain-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:<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 rentalcarspain-pp-cli sync to refresh entity lookups.
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:

rentalcarspain-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.

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:

# Common case: record both the resource learning AND the playbook in one call.
rentalcarspain-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).
rentalcarspain-pp-cli teach-playbook \
  --query "<user's question>" \
  --playbook-file ~/playbooks/<shape>.json \
  --notes-file ~/playbooks/<shape>-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.

rentalcarspain-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:

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]: <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).

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

rentalcarspain-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.
RENTALCARSPAIN_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:

rentalcarspain-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
rentalcarspain-pp-cli feedback --stdin < notes.txt
rentalcarspain-pp-cli feedback list --json --limit 10

Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless RENTALCARSPAIN_FEEDBACK_ENDPOINT is set AND either --send is passed or RENTALCARSPAIN_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 <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.

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.

rentalcarspain-pp-cli profile save briefing --json
rentalcarspain-pp-cli --profile briefing offers --s example-value --b example-value
rentalcarspain-pp-cli profile list --json
rentalcarspain-pp-cli profile show briefing
rentalcarspain-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
5	API error (upstream issue)
7	Rate limited (wait and retry)
10	Config error

Argument Parsing

Parse $ARGUMENTS:

Empty, help, or --help → show rentalcarspain-pp-cli --help output
Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

Install the MCP server:

go install github.com/mvanhorn/printing-press-library/library/travel/rentalcarspain/cmd/rentalcarspain-pp-mcp@latest

claude mcp add rentalcarspain-pp-mcp -- rentalcarspain-pp-mcp

Verify: claude mcp list

Direct Use

Check if installed: which rentalcarspain-pp-cli If not found, offer to install (see Prerequisites at the top of this skill).
Match the user query to the best command from the Unique Capabilities and Command Reference above.

Execute with the --agent flag:

rentalcarspain-pp-cli <command> [subcommand] [args] --agent

If ambiguous, drill into subcommand help: rentalcarspain-pp-cli <command> --help.