warranty git:20261105.d3c9cd7B

Immutable. This exact content never changes and is served at /api/v1/blob/ec04660bb8a6bf61.

---
name: warranty
description: "Dell, Lenovo and Apple warranty end dates for every client's devices, in one local mirror. Trigger phrases: `is this laptop still under warranty`, `warranty end date for serial`, `which devices go out of warranty this quarter`, `dell warranty lookup`, `lenovo warranty lookup`, `use warranty`, `run warranty-cli`."
author: "Damien Stevens"
license: "Apache-2.0"
vendor: "Dell, Lenovo and Apple"
argument-hint: "<command> [args] | install cli|mcp"
allowed-tools: "Read Bash"
metadata:
  openclaw:
    requires:
      bins:
        - warranty-cli
    install:
      - kind: script
        bins: [warranty-cli]
        sh: https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/warranty/install.sh
        ps1: https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/warranty/install.ps1
---

# Device Warranty - Claude Code Skill

## Prerequisites: Install the CLI

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

1. macOS / Linux:
   ```bash
   bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/warranty/install.sh)
   ```
2. Windows (PowerShell):
   ```powershell
   iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/warranty/install.ps1 | iex
   ```
3. Verify: `warranty-cli --version`
4. Ensure `~/.local/bin` (macOS / Linux) or `%LOCALAPPDATA%\Programs\msp-skills` (Windows) is on `$PATH`.

The installer downloads the `warranty-cli` and `warranty-mcp` binaries into `~/.local/bin`
(macOS / Linux) or `%LOCALAPPDATA%\Programs\msp-skills` (Windows). It does not
register the skill with your agent and writes no MCP client config - see
[mcp-install.md](./mcp-install.md) for that wire-up.

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.

Look up any serial against Dell TechDirect, Lenovo eSupport or Apple Business with whichever vendor credentials you have, keep every result in a local per-client warranty mirror (data-warranty.db), and answer fleet questions offline: report lists what expires soon, lifecycle counts coverage endings by quarter for refresh planning, unresolved shows what was never verified, and events list feeds coverage changes to your PSA.

## When to Use This CLI

Use this CLI when an agent or technician needs hardware warranty end dates for Dell, Lenovo or Apple devices, one serial or a whole client fleet, or a per-client view of what expires soon. It keeps a local mirror so expiry reports, lifecycle forecasts and coverage-change events work offline after a lookup.

## Anti-triggers

Do not use this CLI for:
- HP warranty: HP's public warranty API is discontinued, so this CLI cannot look up HP serials
- Pulling device lists from an RMM: use the datto-rmm, ninjaone or n-central connector and import its export here
- Buying or renewing coverage: the vendor portals handle quotes and purchases

## Unique Capabilities

### Fleet-wide answers from the local mirror
- **`lifecycle`**  -  Per client: devices covered now, expired, unverified (no coverage data yet), coverage ending in each of the next quarters, and devices past an age threshold.

  _Reach for this to count coverage endings by quarter for a refresh plan or a QBR hardware-lifecycle slide, for one or every client._

  ```bash
  warranty-cli lifecycle --quarters 4 --age 4y --agent
  ```
- **`apple-pull`**  -  Load one client's Apple devices from its Apple Business organization (needs that organization's WARRANTY_APPLE_* account; exits 10 without it) and see what is new, gone, or missing from the RMM import.

  _Use this to catch Macs and iPads the RMM export never listed._

  ```bash
  warranty-cli apple-pull --customer "Acme Dental" --agent
  ```
- **`report`**  -  Devices out of warranty or expiring within N days, per client, from the mirror.

  _Use this to list the individual devices that need a renewal quote or replacement._

  ```bash
  warranty-cli report --within 90d --customer "Acme Dental" --agent
  ```

### Keeping the mirror honest
- **`recheck`**  -  Re-check serials already in the mirror: never-checked first, then coverage ending soon, then stale; each vendor's batch size and pace respected, vendors without credentials skipped.

  _Use this on a schedule so reports and coverage events stay current without re-importing files._

  ```bash
  warranty-cli recheck --older-than 30d --expiring 120d --max-calls 50 --dry-run
  ```
- **`unresolved`**  -  Every device whose coverage the report cannot speak for, each with one reason: vendor unknown, vendor not configured, ambiguous, invalid, not found, not in the Apple organization, lookup error, never checked, stale or duplicated.

  _Check this before trusting an empty expiry report: it shows what was never verified._

  ```bash
  warranty-cli unresolved --customer "Acme Dental" --agent
  ```
- **`events list`**  -  Coverage expiring, expired and changed events after a cursor, once each.

  _Poll this to open tickets or quotes for coverage that is ending or changed._

  ```bash
  warranty-cli events list --since 0 --agent
  ```

### Serial lookups
- **`lookup`**  -  Warranty for one or more serials, vendor detected from the serial or named, normalized to one coverage-line shape and saved to the mirror; vendors without credentials are reported as vendor_unconfigured, not called.

  _Use this to answer 'is this device still covered, and until when' for Dell, Lenovo or Apple serials whose vendor credentials are set._

  ```bash
  warranty-cli lookup 1ABC234 PF1ABCDE --agent
  ```
- **`import`**  -  Load a CSV or JSON device export (serial, optional manufacturer, model, hostname) into the mirror under a client name; CLI only, not available over MCP.

  _Start here so report, lifecycle and recheck know which client owns each serial._

  ```bash
  warranty-cli import devices.csv --customer "Acme Dental"
  ```

## Command Reference

**apple**  -  Apple Business AppleCare coverage and organization devices by serial

- `warranty-cli apple coverage`  -  Returns every coverage line for the device: limited warranty, AppleCare+ or AppleCare+ for Business, with status
- `warranty-cli apple get`  -  Returns the device's model, product family, part and order numbers
- `warranty-cli apple list`  -  Lists every device the organization enrolls through Automated Device Enrollment, with serial number, model

**dell**  -  Dell TechDirect warranty entitlements by service tag

- `warranty-cli dell entitlements`  -  Returns one record per service tag with ship date, product line and every entitlement line (start, end, service level).
- `warranty-cli dell summary`  -  Returns the asset header, entitlements and shipped components for a single service tag.

**lenovo**  -  Lenovo eSupport warranty, warranty offerings and contracts by serial

- `warranty-cli lenovo contract`  -  Returns the contract description and dates and every covered product with its serial, machine type, SLA
- `warranty-cli lenovo offering`  -  Returns the localized name, description, type, delivery
- `warranty-cli lenovo warranty`  -  Returns the product, ship and purchase dates, in-warranty flag, warranty lines and contract lines for the serial.


**apple-pull**


- `warranty-cli apple-pull`  -  Load one client's Apple devices from its Apple Business organization (needs that organization's WARRANTY_APPLE_* account; exits 10 without it) and see what is new, gone, or missing from the RMM import.


**events**


- `warranty-cli events list`  -  Coverage expiring, expired and changed events after a cursor, once each.


**import**


- `warranty-cli import`  -  Load a CSV or JSON device export (serial, optional manufacturer, model, hostname) into the mirror under a client name; CLI only, not available over MCP.


**lifecycle**


- `warranty-cli lifecycle`  -  Per client: devices covered now, expired, unverified (no coverage data yet), coverage ending in each of the next quarters, and devices past an age threshold.


**lookup**


- `warranty-cli lookup`  -  Warranty for one or more serials, vendor detected from the serial or named, normalized to one coverage-line shape and saved to the mirror; vendors without credentials are reported as vendor_unconfigured, not called.


**recheck**


- `warranty-cli recheck`  -  Re-check serials already in the mirror: never-checked first, then coverage ending soon, then stale; each vendor's batch size and pace respected, vendors without credentials skipped.


**report**


- `warranty-cli report`  -  Devices out of warranty or expiring within N days, per client, from the mirror.


**unresolved**


- `warranty-cli unresolved`  -  Every device whose coverage the report cannot speak for, each with one reason: vendor unknown, vendor not configured, ambiguous, invalid, not found, not in the Apple organization, lookup error, never checked, stale or duplicated.




### Finding the right command

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

```bash
warranty-cli which "<capability in your own words>"
```

`which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match  -  fall back to `--help` or use a narrower query. `--json` (and other machine formats) keep that exit-2 contract and write `{"matches":[]}` on stdout so agents can inspect the envelope without treating a miss as success.

## Recipes

### QBR lifecycle slide for one client

```bash
warranty-cli lifecycle --customer "Acme Dental" --quarters 4 --csv
```

Coverage ending per quarter and devices past the age threshold, ready for a spreadsheet.

### What expires in the next 90 days, trimmed for an agent

```bash
warranty-cli report --within 90d --agent --select devices.serial,devices.customer,devices.coverage_end,unverified,note
```

Keeps serial, customer and end date, plus unverified and note so an empty list cannot be mistaken for a verified fleet.

### Recheck never-checked, soon-expiring and stale serials within a call budget

```bash
warranty-cli recheck --older-than 30d --max-calls 20
```

Never-checked devices go first, then coverage ending within 120 days, then devices last checked over 30 days ago, up to 20 vendor calls.

### Feed coverage changes to a PSA

```bash
warranty-cli events list --since 0 --agent
```

Returns coverage events and a cursor to pass as --since next time.

## Auth Setup

Each vendor is optional and needs its own enrollment; a missing vendor never blocks the configured ones (its serials report vendor_unconfigured). Dell TechDirect: request Warranty API access (APIs, API Key Management; approval can take several days), then set WARRANTY_DELL_CLIENT_ID and WARRANTY_DELL_CLIENT_SECRET, or store them with the auth login command (the auth commands cover Dell only). Lenovo eSupport: a ClientID token from your Lenovo account manager or partner representative, environment only: WARRANTY_LENOVO_CLIENT_KEY. Apple Business: an API account (Settings, API) in each customer's organization, environment only: WARRANTY_APPLE_CLIENT_ID, WARRANTY_APPLE_KEY_ID and WARRANTY_APPLE_PRIVATE_KEY (PEM text or a path to the .pem file). One Apple account covers one customer organization, so set that customer's variables and pass --customer. warranty-cli doctor --json shows a vendors block with what each vendor still needs.

Run `warranty-cli doctor` to verify setup.

## Agent Mode

Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color`.

Global format flags share one contract on promoted, novel, sync, and `--deliver` paths:

- `--json`  -  one JSON document on stdout (sync progress events go to stderr)
- `--compact`  -  keep identity/status/timestamp fields; does not change the document vs stream shape
- `--csv` / `--plain`  -  tabular rows (collection envelopes unwrap to the row array). `--csv` prefixes `'` on a cell or header key that starts with `=`, `+`, `-`, `@`, tab, CR, or LF (fullwidth `＝＋－＠` too) so a spreadsheet does not run it as a formula; a plain signed number such as `-5` or `+2.5e3` is unchanged.
- `--quiet`  -  one identity value per row, no envelope

- **Pipeable**  -  JSON on stdout, errors on stderr
- **Filterable**  -  `--select` keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

  ```bash
  warranty-cli apple list --agent --select id,attributes.serialNumber,attributes.deviceModel
  ```
- **Previewable**  -  `--dry-run` shows the request without sending
- **Offline-friendly**  -  `report`, `lifecycle`, `unresolved` and `events list` answer from the local warranty mirror
- **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": <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 `WARRANTY_HOME=<dir>` to relocate all four path kinds under one root.
- Use per-kind env vars only when a specific kind must diverge: `WARRANTY_CONFIG_DIR`, `WARRANTY_DATA_DIR`, `WARRANTY_STATE_DIR`, `WARRANTY_CACHE_DIR`.
- Resolution order is per-kind env var, `--home`, `WARRANTY_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`, the warranty mirror `data-warranty.db`, and the generated store `data.db`. `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 `warranty-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": {
      "warranty": {
        "command": "warranty-mcp",
        "env": {
          "WARRANTY_HOME": "/srv/warranty"
        }
      }
    }
  }
  ```

Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `WARRANTY_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 `WARRANTY_HOME`, or `doctor` will not find credentials left under the former root.

Local data is unencrypted and relies on OS account permissions plus disk encryption. The warranty mirror (`data-warranty.db`) holds every client's devices, coverage lines and events; generated endpoint reads in `--data-source auto` mode are written to the SQLite store; vendor responses are not cached on disk. `local-data purge` previews what it would erase (store files, response cache, learn journal) and deletes only with `--yes`; it is not exposed over MCP. `WARRANTY_NO_LOCAL_DATA=1` disables the response cache and store writes, turns `auto` reads into live reads, and blocks `sync`, `workflow archive`, `import`, `recheck` and `apple-pull` (`lookup` still answers without saving); `--data-source local` still reads an existing store, and `WARRANTY_DATA_SOURCE` sets the `--data-source` default.

## 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, pass the question as an argv or MCP tool argument to `recall --agent`. Do not interpolate user-controlled text into a shell command line.

Quoted `recall "<question>"` breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data:

```bash
# Write the question verbatim with your file-writing tool (no shell involved).
# Command substitution on a file only ever yields data  -  the shell never
# parses the file's bytes as syntax.
QUERY=$(cat /path/to/question.txt)
warranty-cli recall "$QUERY" --agent
```

Prefer MCP: pass the question as the tool's query argument. `"$QUERY"` after a file read is argv-safe; putting the question itself in the command text is not.

The response envelope:

```json
{
  "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>", "warranty-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 `warranty-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; `warranty-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 `warranty-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. Pass the query the same way as recall  -  argv/MCP, or file-then-`$QUERY`. Do not splice the question into the command text:

```bash
QUERY=$(cat /path/to/question.txt)
warranty-cli teach --query "$QUERY" --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:

```bash
# Common case: record both the resource learning AND the playbook in one call.
QUERY=$(cat /path/to/question.txt)
warranty-cli teach \
  --query "$QUERY" \
  --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).
QUERY=$(cat /path/to/question.txt)
warranty-cli teach-playbook \
  --query "$QUERY" \
  --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`. Pass the query and note as argv/MCP arguments, or write each with a non-shell file tool and read them back (`QUERY=$(cat ...)`, `NOTE=$(cat ...)`). Do not interpolate either string into the command text:

```bash
QUERY=$(cat /path/to/question.txt)
NOTE=$(cat /path/to/note.txt)
warranty-cli playbook amend \
  --query "$QUERY" \
  --add-note "$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]: <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

`warranty-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.
- `WARRANTY_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:

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

Entries are stored locally as `feedback.jsonl` under the resolved data dir. They are never POSTed unless `WARRANTY_FEEDBACK_ENDPOINT` is set AND either `--send` is passed or `WARRANTY_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>` as a private 0600 file (exclusive randomly named temp in the destination directory, then rename; a planted symlink is not followed). Binary-response commands write decoded payload bytes (not the base64 JSON envelope) and print a small JSON receipt on stdout; `--json`/`--csv` do not refuse when this sink is set. |
| `webhook:<url>` | POST the output body to the URL (`application/json`). Redirects are not followed; a 3xx response fails the delivery and the body is not sent to the `Location`. |

Unknown schemes are refused with a structured error naming the supported set. Webhook failures, including redirects, return non-zero and log the URL and 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.

```
warranty-cli profile save briefing --json
warranty-cli --profile briefing apple list
warranty-cli profile list --json
warranty-cli profile show briefing
warranty-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 |
| 1 | Error (for example refused while `WARRANTY_NO_LOCAL_DATA=1`) |
| 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 `warranty-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 binary (run the install script from the Prerequisites section, or see [mcp-install.md](./mcp-install.md) for per-agent wire-up).
2. Register with Claude Code:
   ```bash
   claude mcp add warranty-mcp --env WARRANTY_DELL_CLIENT_ID="$WARRANTY_DELL_CLIENT_ID" --env WARRANTY_DELL_CLIENT_SECRET="$WARRANTY_DELL_CLIENT_SECRET" --env WARRANTY_LENOVO_CLIENT_KEY="$WARRANTY_LENOVO_CLIENT_KEY" --env WARRANTY_APPLE_CLIENT_ID="$WARRANTY_APPLE_CLIENT_ID" --env WARRANTY_APPLE_KEY_ID="$WARRANTY_APPLE_KEY_ID" --env WARRANTY_APPLE_PRIVATE_KEY="$WARRANTY_APPLE_PRIVATE_KEY" -- warranty-mcp
   ```
   Pass only the vendors you have; Lenovo and Apple credentials are read from the environment only.
3. Verify: `claude mcp list`

Over MCP, `import` is hidden and `lookup --file` is refused (both read a file on the host); `recheck` stops after 10 vendor calls and `apple-pull` after one page per call.

For a remote host, `warranty-mcp --transport http` requires `WARRANTY_MCP_HTTP_TOKEN` set to at least 32 characters (callers send `Authorization: Bearer <token>`; `openssl rand -hex 32` prints 64 hex characters and meets that minimum), serves `http://127.0.0.1:7777/mcp` by default, and needs `--tls-cert`/`--tls-key` for any non-loopback `--addr`. Requests with no `Origin` header are accepted. Loopback origins are accepted; any other `Origin` is refused unless listed in `WARRANTY_MCP_HTTP_ALLOWED_ORIGINS` (comma-separated `scheme://host[:port]` values). `WARRANTY_MCP_READ_ONLY=1` drops mirrored write commands (local-write commands that only touch the CLI's own learn store stay) and makes the raw execute tool refuse state-changing calls. Read-only here means no vendor-side writes: every vendor command is a read, and `lookup`, `recheck` and `apple-pull` stay available because they write only this CLI's local mirror (`data-warranty.db`).

## Direct Use

1. Check if installed: `which warranty-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
   warranty-cli report --within 90d --agent
   ```
4. If ambiguous, drill into subcommand help, for example `warranty-cli recheck --help`.