--- name: pp-teslatracker description: "Every used Tesla TeslaTracker lists, in a local store that answers questions the site cannot — price paths, cohort placement, warranty left, and what already left the lot. Trigger phrases: `find a used tesla`, `track tesla prices`, `what tesla dropped in price`, `how much warranty is left on this vin`, `is this tesla price good`, `use teslatracker`, `run teslatracker`." author: "michegz" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - teslatracker-pp-cli install: - kind: go bins: [teslatracker-pp-cli] module: github.com/mvanhorn/printing-press-library/library/commerce/teslatracker/cmd/teslatracker-pp-cli --- # TeslaTracker — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `teslatracker-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install teslatracker --cli-only ``` 2. Verify: `teslatracker-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/commerce/teslatracker/cmd/teslatracker-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. TeslaTracker aggregates used Teslas across Tesla, Carvana, CarMax and private sellers. This CLI mirrors that inventory into VIN-keyed SQLite and adds the layer the website has no way to offer: a recorded price path per car (price-history), where a price sits in its cohort (comps), how much warranty is genuinely left at delivery (warranty), and which cars quietly left inventory (gone). Every money figure is landed cost, including the real per-car transport fee. ## When to Use This CLI Use this CLI when the question is about used Tesla inventory over time rather than right now: whether a price has moved, how it compares to similar cars, how much warranty remains, or what has left the market. It is strongest after several syncs, because the price series and departure log accumulate locally. ## Anti-triggers Do not use this CLI for: - Do not use this to control or query a Tesla you already own — that is the Owner/Fleet API, not this. - Do not use this to buy a car; it has no checkout, no ordering, and no dealer contact. - Do not treat degradation output as a battery health test; it is the source's published rated-vs-actual spread. - Do not treat a departure in gone as a confirmed sale; listings can be pulled or reassigned. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Coverage and condition - **`warranty`** — See exactly how many months and miles of Tesla warranty are left on the day you would take delivery, and which limit runs out first. _Reach for this when the question is coverage or risk on one specific car, not price._ ```bash teslatracker-pp-cli warranty 5YJ3E1EA7LF745758 --agent ``` - **`degradation`** — Compare a car's actual range against its rated range, and see where that gap sits among every similar car in your local store. _Use for range condition. This is the source's published spread, not a measured battery test._ ```bash teslatracker-pp-cli degradation 5YJ3E1EA7LF745758 --agent ``` ### Price intelligence - **`comps`** — See where one car's landed cost sits in the distribution of comparable cars, with the sample size and the arithmetic shown. _The honest answer to 'is this price good' — placement and arithmetic, never a verdict._ ```bash teslatracker-pp-cli comps 5YJ3E1EA7LF745758 --agent ``` - **`premium`** — See what a configuration attribute actually costs across the market, computed within matched cohorts. _Answers 'can I afford HW4 at my ceiling'. Observational, not causal._ ```bash teslatracker-pp-cli premium --by hardwareVersion --agent ``` - **`stale`** — Rank the corpus by days listed and flag cars that are both long-listed and have never had a price cut. _Finds negotiation candidates. Deliberately does not judge whether the price is good._ ```bash teslatracker-pp-cli stale --limit 20 --agent ``` - **`radius`** — See how the price floor and median change as you widen your search radius, with real transport fees included at every step. _Answers 'is shopping farther actually worth it' in dollars. Returns a curve, not cars._ ```bash teslatracker-pp-cli radius --lat 30.2241 --lon -92.0198 --agent ``` ### Local state that compounds - **`gone`** — See which cars left inventory, at what landed price, and after how many days listed. _Calibrates a ceiling against what actually clears. A departure is not a sale._ ```bash teslatracker-pp-cli gone --agent ``` - **`price-history`** — See a single car's full observed price path: every cut, its size, and how long it has held the current price. _Use for one car's own history; use stale to find candidates across the corpus._ ```bash teslatracker-pp-cli price-history 5YJ3E1EA7LF745758 --agent ``` - **`watch`** — Save a named search and see only what is new, price-changed, or departed since the last time you ran it. _The right entry point for a recurring session instead of re-running search._ ```bash teslatracker-pp-cli watch run --all --agent ``` ### Agent-native plumbing - **`coverage`** — See how complete and how fresh your local mirror is, field by field, including whether any pages were dropped during sync. _Call before asserting any aggregate. Reports on the store, never on cars._ ```bash teslatracker-pp-cli coverage --agent ``` ## Command Reference **inventory** — Used Tesla listings, VIN-keyed - `teslatracker-pp-cli inventory get` — - `teslatracker-pp-cli inventory list` — - `teslatracker-pp-cli inventory report` — ## Freshness Contract This 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 `TESLATRACKER_NO_AUTO_REFRESH=1` to skip the freshness hook without changing source selection. Covered paths: - `teslatracker-pp-cli inventory` - `teslatracker-pp-cli inventory get` - `teslatracker-pp-cli inventory list` - `teslatracker-pp-cli inventory search` When 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. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash teslatracker-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 ### Rank the corpus by how long cars have been sitting ```bash teslatracker-pp-cli stale --limit 20 --agent --select vin,model,year,mileage,landed_usd ``` Ranks the local mirror by days listed, with landed cost attached. Staleness is a negotiating signal, not a price judgement — a car can sit simply because it is overpriced, so pair a VIN from here with `comps` before making an offer. ### Full-text search the local mirror ```bash teslatracker-pp-cli search "model 3 long range" --limit 20 --agent ``` FTS5 over everything synced, offline, no API call. ### Is this price defensible? ```bash teslatracker-pp-cli comps 5YJ3E1EA7LF745758 --agent ``` Returns the percentile, the median, the dollar gap and the sample size — never a bare score. ### How much car is left ```bash teslatracker-pp-cli warranty 5YJ3E1EA7LF745758 --annual-miles 12000 --agent ``` Months and miles remaining at delivery, naming whichever of the four limits binds first. ### What did I miss since yesterday ```bash teslatracker-pp-cli watch run --all --agent ``` New, price-changed and departed since each saved search's own cursor. ### Does the HW4 premium fit my budget ```bash teslatracker-pp-cli premium --by hardwareVersion --agent ``` The landed-price difference between hardware versions within matched model/year/trim cohorts, with n per cell. ## Auth Setup No authentication required. Run `teslatracker-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 teslatracker-pp-cli inventory list --agent ``` - **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: ```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 `TESLATRACKER_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `TESLATRACKER_CONFIG_DIR`, `TESLATRACKER_DATA_DIR`, `TESLATRACKER_STATE_DIR`, `TESLATRACKER_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `TESLATRACKER_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 `teslatracker-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": { "teslatracker": { "command": "teslatracker-pp-mcp", "env": { "TESLATRACKER_HOME": "/srv/teslatracker" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `TESLATRACKER_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 `TESLATRACKER_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 teslatracker-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": ["", "teslatracker-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 `teslatracker-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; `teslatracker-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. - `lookup_refresh_available` (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run `teslatracker-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 sa