Pp Vehicle Safety

<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/other/vehicle-safety/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/". -->

Vehicle Safety — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the vehicle-safety-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:

   npx -y @mvanhorn/printing-press-library install vehicle-safety --cli-only

2. Verify: vehicle-safety-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 1.26.6 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/other/vehicle-safety/cmd/vehicle-safety-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.

Query NHTSA recalls, complaints, ratings, product catalogs, and VIN decoding, then preserve observations locally. Compound commands distinguish raw reports from rates and model-wide campaigns from VIN-specific open recalls.

When to Use This CLI

Use this CLI for vehicle recall, complaint, crash-rating, and VIN research that benefits from reproducible local history. Prefer its compound commands when an agent needs evidence and caveats, not merely one raw response.

Anti-triggers

Do not use this CLI for:

• Do not use it for bulk commercial VIN sweeps.
• Do not treat complaint counts as failure rates or the compound output as a safety certification.
• Do not use it to file complaints or perform vehicle repairs.

Unique Capabilities

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

Evidence-first vehicle research

• dossier — See identity, recall and complaint summaries, and available crash ratings in one source-attributed report; add --include-records for complete source records.

  Use this instead of stitching several NHTSA responses together manually.

  vehicle-safety-pp-cli dossier --year 2020 --make Honda --model Civic --agent

• signals — Place complaint and recall events on one normalized timeline and identify the official flat-file sources required for investigations and communications.

  Use this to inspect structured precursor signals without causal or rate claims.

  vehicle-safety-pp-cli signals --year 2020 --make Honda --model Civic --agent

• compare — Compare two model years while keeping raw complaint counts and missing denominators explicit.

  Use this for a defensible comparison rather than a synthetic risk score.

  vehicle-safety-pp-cli compare '2020 Honda Civic' '2020 Toyota Corolla' --agent

• recall-coverage — Decode one VIN, list matching model-level campaigns, and keep VIN eligibility and repair status explicitly unverified with a link to NHTSA's official lookup.

  Use this when model recall eligibility and VIN open-recall status must not be conflated.

  vehicle-safety-pp-cli recall-coverage 1HGCV1F34LA000001 --agent

Local history that compounds

• watch — Report newly observed recall campaigns and remedy changes for saved vehicles.

  Use this for finite, auditable fleet change detection.

  vehicle-safety-pp-cli watch --garage vehicles.csv --agent

• bulletin-bridge — Show structured complaint and manufacturer-communication co-occurrence candidates.

  Use this for auditable overlap without semantic or causal inference.

  vehicle-safety-pp-cli bulletin-bridge --year 2020 --make Honda --model Civic --communications-file communications.tsv --agent

Command Reference

complaints — Manage complaints

• vehicle-safety-pp-cli complaints — List owner complaints for a model year, make, and model

products — Manage products

• vehicle-safety-pp-cli products list-vehicle-makes — List makes for a model year and issue type
• vehicle-safety-pp-cli products list-vehicle-model-years — List vehicle model years for an issue type
• vehicle-safety-pp-cli products list-vehicle-models — List models for a make, model year, and issue type

recalls — Manage recalls

• vehicle-safety-pp-cli recalls get-campaign — Get a recall by NHTSA campaign number
• vehicle-safety-pp-cli recalls list-by-vehicle — List recalls for a model year, make, and model

safety-ratings — Manage safety ratings

• vehicle-safety-pp-cli safety-ratings get — Get crash ratings for a NHTSA vehicle ID
• vehicle-safety-pp-cli safety-ratings list-by-vehicle — List crash-rating vehicle variants

vehicles — Manage vehicles

• vehicle-safety-pp-cli vehicles <vin> — Decode a VIN into normalized vehicle attributes

Finding the right command

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

vehicle-safety-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

Narrow a recall response

vehicle-safety-pp-cli recalls list-by-vehicle --make Honda --model Civic --model-year 2020 --agent --select results.NHTSACampaignNumber,results.Component,results.Remedy

Return only campaign, component, and remedy evidence.

Compare two model years

vehicle-safety-pp-cli compare '2020 Honda Civic' '2020 Toyota Corolla' --agent

Compare source records without inventing a risk score.

Reconcile recall coverage

vehicle-safety-pp-cli recall-coverage 1HGCV1F34LA000001 --agent

Decode the VIN and list model-level campaigns while linking to the official lookup for unverified VIN repair status.

Auth Setup

No authentication required.

Run vehicle-safety-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:

  vehicle-safety-pp-cli safety-ratings get mock-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 VEHICLE_SAFETY_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: VEHICLE_SAFETY_CONFIG_DIR, VEHICLE_SAFETY_DATA_DIR, VEHICLE_SAFETY_STATE_DIR, VEHICLE_SAFETY_CACHE_DIR.

• Resolution order is per-kind env var, --home, VEHICLE_SAFETY_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 vehicle-safety-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": {
      "vehicle-safety": {
        "command": "vehicle-safety-pp-mcp",
        "env": {
          "VEHICLE_SAFETY_HOME": "/srv/vehicle-safety"
        }
      }
    }
  }

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

vehicle-safety-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>", "vehicle-safety-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 `vehicle-safety-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; vehicle-safety-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 vehicle-safety-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.