Datto SaaS Protection - Claude Code Skill

Prerequisites: Install the CLI

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

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/datto-saas/install.sh)

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/datto-saas/install.ps1 | iex

Verify: datto-saas-cli --version
Ensure ~/.local/bin (macOS / Linux) or %LOCALAPPDATA%\Programs\msp-skills (Windows) is on $PATH.

The installer downloads the datto-saas-cli and datto-saas-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 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.

The Partner Portal shows one client at a time. This CLI syncs every client's domains, seats and backup history into SQLite so you can reconcile billing with seats reconcile, find unprotected seats with seats gaps, rank backups with backup-health, and hand a departing client a full exit-inventory. Seat changes are planned locally with seats bulk-plan; seats bulk-change is the one command that sends a change.

When to Use This CLI

Use this CLI when an MSP needs answers across many Datto SaaS Protection clients at once: seat and billing reconciliation, unprotected or newly added seats, backup coverage ranking, or a full inventory of a client that is leaving. Run datto-saas-cli sync first; the audit commands read the local store and an unsynced store returns empty results. It is also the safe way to plan License, Pause and Unlicense changes in batches of at most 100 seats before sending them with seats bulk-change.

Anti-triggers

Do not use this CLI for:

Restoring or exporting mailbox, drive or site data: the public API has no restore or export endpoints; use the SaaS Protection portal
Creating or deleting clients, domains or subscriptions: the API has no endpoints for it
Datto BCDR appliances, agents or screenshots: use the datto-bcdr CLI
Datto RMM devices or monitoring: use the datto-rmm CLI
Changing Seat Management 1.0 Google seats: the API cannot; use the portal

Unique Capabilities

Safe seat changes

seats bulk-plan - Turn a seat selection into ready-to-run License, Pause or Unlicense batches, grouped by subscription and seat type and capped at 100 ids, without sending anything.

Reach for this before any seat change: it previews which seats would move, skips seats already in the target state, blocks clients with several subscriptions until --subscription picks one, and prints the seats bulk-change command per batch. Check blocked and skipped before trusting an empty plan.
```
datto-saas-cli seats bulk-plan --action License --state Unprotected --customer 123456 --subscription Classic:Office365:654321 --agent
```

Fleet seat audit

seats reconcile - See, per client, where Datto's seatsUsed disagrees with billable and Active seats before you invoice.

Use it for monthly invoice prep or a cost-leak sweep; it reports signed deltas and flags instead of raw seat lists.
```
datto-saas-cli seats reconcile --agent
```
seats gaps - List seats across all clients that are Unprotected (Paused too with --include-paused), newest first, with each seat's remoteId for a License plan.

Use it to answer who joined a tenant and is not covered, across the whole fleet in one call.
```
datto-saas-cli seats gaps --since 30d --agent
```
seats roster - Every synced seat across all clients in one table, joined with its customer's domains, product types and subscription ids; --csv for a fleet-wide export.

Reach for this for a fleet-wide seat export or to hand a client's seat list to billing; use seats summary for counts.
```
datto-saas-cli seats roster --customer 123456 --state Unprotected,Paused --agent
```
seats summary - Seat counts per client and seat type, split by Active, Paused, Archived and Unprotected state and the billable flag.

Reach for this for plain counts by type and state; use seats reconcile to compare counts with Datto's seatsUsed.
```
datto-saas-cli seats summary --agent
```

Backup health

backup-health - Rank clients worst first by backup coverage, then consecutive short backup windows and perfect-backup rate.

Use it for the daily or weekly backup triage instead of opening each client's report.
```
datto-saas-cli backup-health --below 95 --agent
```

Client offboarding

exit-inventory - Build one manifest for a client leaving SaaS Protection: domains, subscription ids, retention, every seat with remoteId, storage, last backups and a blockers checklist.

Use it to plan a migration or offboarding from facts and to confirm nothing is still un-backed-up before cancellation. Use --data-source live for a real offboarding: the local fallback has no detailed backup stats.
```
datto-saas-cli exit-inventory 123456 --agent
```

Command Reference

activity-log - Datto platform activity log (shared reporting endpoint).

datto-saas-cli activity-log - List Datto platform activity log entries, filtered by client, user, target or time window.

applications - Per-customer backup history by suite and application.

datto-saas-cli applications <saasCustomerId> - Show one customer's backup report: used bytes, backup history per suite and app, and optional remote IDs per seat type.

backup-stats - Per-customer detailed backup statistics.

datto-saas-cli backup-stats <saasCustomerId> - Show detailed backup statistics for one SaaS customer.

domains - Protected Microsoft 365 tenants and Google Workspace domains.

datto-saas-cli domains - List every protected Microsoft 365 tenant and Google Workspace domain, with its saasCustomerId and subscription id.

seats - Protected seats (users, shared mailboxes, sites, team sites, teams, shared drives).

datto-saas-cli seats bulk-change <saasCustomerId> <externalSubscriptionId> - License, pause, or unlicense up to 100 seats of one subscription in one call. This is the only write: it changes which seats are protected and billed. It sends immediately: there is no confirmation prompt and --yes is not required. Preview with --dry-run, which applies the same seat-type, action and 100-id checks as a real send, or plan batches with seats bulk-plan.
datto-saas-cli seats list <saasCustomerId> - List the seats of one SaaS customer with seat type, state, billable flag, date added and remoteId.

backup-health

datto-saas-cli backup-health - Rank clients worst first by backup coverage, then consecutive short backup windows and perfect-backup rate.

exit-inventory

datto-saas-cli exit-inventory <customer> - Build one manifest for a client leaving SaaS Protection: domains, subscription ids, retention, every seat with remoteId, storage, last backups and a blockers checklist.

sync

datto-saas-cli sync - Pull every domain, then each client's seats and backup history, into the local store. Run it before the local commands below.

seats (local audit and planning) - Run datto-saas-cli sync first: these commands read the local store, and an unsynced store returns empty results, which is not an all-clear.

datto-saas-cli seats bulk-plan - Turn a seat selection into ready-to-run License, Pause or Unlicense batches, grouped by subscription and seat type and capped at 100 ids, without sending anything.
datto-saas-cli seats reconcile - See, per client, where Datto's seatsUsed disagrees with billable and Active seats before you invoice.
datto-saas-cli seats gaps - List seats across all clients that are Unprotected (Paused too with --include-paused), newest first, with each seat's remoteId for a License plan.
datto-saas-cli seats roster - Every synced seat across all clients in one table, joined with its customer's domains, product types and subscription ids; --csv for a fleet-wide export.
datto-saas-cli seats summary - Seat counts per client and seat type, split by Active, Paused, Archived and Unprotected state and the billable flag.

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 DATTO_SAAS_NO_AUTO_REFRESH=1 to skip the freshness hook without changing source selection.

Covered paths:

datto-saas-cli domains

The seat, backup-health and exit-inventory commands are not covered: the pre-read refresh only re-fetches the domains list, not the per-client seats and backup history those commands read. Run datto-saas-cli sync to refresh them; they print a stale-data hint on stderr. The local-only commands (seats roster, seats summary, seats reconcile, seats gaps, seats bulk-plan, backup-health) reject --data-source live.

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:

datto-saas-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

Reconcile seats before invoicing

datto-saas-cli seats reconcile --agent

Per client, compares summed domain seatsUsed with billable and Active seats and flags mismatches.

Narrow a large seat roster

datto-saas-cli seats roster --agent --select saas_customer_name,domains,name,seat_type,seat_state,remote_id

The fleet roster is wide; select only the columns an agent needs.

Exit inventory for a departing client

datto-saas-cli exit-inventory 123456 --agent

One manifest with domains, subscription ids, seats, storage and a blockers checklist.

Plan unlicensing archived seats

datto-saas-cli seats bulk-plan --action Unlicense --state Archived --customer 123456 --subscription Classic:Office365:654321 --agent

Groups archived seats into batches of at most 100 and prints the seats bulk-change command for each; sends nothing. Check blocked and skipped before trusting an empty plan. Unlicense stops protecting the seat, so confirm how long the archived data is retained before running the batches.

Auth Setup

Datto SaaS Protection uses the Datto REST API key pair from the Partner Portal (Admin, Integrations, API Keys). Set DATTO_SAAS_PUBLIC_KEY to the public key and DATTO_SAAS_SECRET_KEY to the secret key; the CLI sends them as HTTP Basic auth to api.datto.com. One partner key sees every client you manage.

Run datto-saas-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:
```
datto-saas-cli activity-log --agent --select category,id,message
```
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
No confirmation prompt - seats bulk-change is the only write and sends immediately; --yes is not required. Preview with --dry-run or plan with seats bulk-plan
No create endpoints - --idempotent only turns an HTTP 409 into success, so seats bulk-change refuses it

Response envelope

Under --agent, commands wrap output in a provenance envelope (with plain --json, the local audit commands print the bare array or object):

{
  "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 DATTO_SAAS_HOME=<dir> to relocate all four path kinds under one root.
Use per-kind env vars only when a specific kind must diverge: DATTO_SAAS_CONFIG_DIR, DATTO_SAAS_DATA_DIR, DATTO_SAAS_STATE_DIR, DATTO_SAAS_CACHE_DIR.
Resolution order is per-kind env var, --home, DATTO_SAAS_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 datto-saas-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": {
    "datto-saas": {
      "command": "datto-saas-mcp",
      "env": {
        "DATTO_SAAS_HOME": "/srv/datto-saas"
      }
    }
  }
}

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use DATTO_SAAS_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 DATTO_SAAS_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. Reads in the default --data-source auto mode are written to the SQLite store; GET responses are cached for five minutes under the cache dir. 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. DATTO_SAAS_NO_LOCAL_DATA=1 disables the response cache and writing API data to the store (the learning loop's own records still go there unless you add --no-learn), turns auto reads into live reads, and blocks sync and workflow archive; --data-source local still reads an existing store, and DATTO_SAAS_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:

# 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=$(cat /path/to/question.txt)
datto-saas-cli recall "$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:

{
  "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>", "datto-saas-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 `datto-saas-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; datto-saas-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., an "o365" teach satisfying a "Microsoft 365" 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., one alias that maps to two seat types). 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 datto-saas-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:

QUERY=$(cat /path/to/question.txt)
datto-saas-cli teach --query "$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., "unlicensed") satisfies future queries under another alias (e.g., "not protected", "Unprotected") 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.
QUERY=$(cat /path/to/question.txt)
datto-saas-cli teach \
  --query "$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=$(cat /path/to/question.txt)
datto-saas-cli teach-playbook \
  --query "$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:

QUERY=$(cat /path/to/question.txt)
NOTE=$(cat /path/to/note.txt)
datto-saas-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 syncs, 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-client / per-seat / 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

datto-saas-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.
DATTO_SAAS_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:

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

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

datto-saas-cli profile save briefing --json
datto-saas-cli --profile briefing activity-log
datto-saas-cli profile list --json
datto-saas-cli profile show briefing
datto-saas-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	Other error (for example `--data-source live` on a local-only command)
2	Usage error (wrong arguments)
3	Resource not found
4	Authentication required
5	API error (upstream issue)
6	Partial failure
7	Rate limited (wait and retry)
10	Config error

Argument Parsing

Parse $ARGUMENTS:

Empty, help, or --help → show datto-saas-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 binary (run the install script from the Prerequisites section, or see mcp-install.md for per-agent wire-up).

claude mcp add datto-saas-mcp --env DATTO_SAAS_PUBLIC_KEY=<public-key> --env DATTO_SAAS_SECRET_KEY=<secret-key> -- datto-saas-mcp

Verify: claude mcp list

For a remote host, datto-saas-mcp --transport http requires DATTO_SAAS_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 DATTO_SAAS_MCP_HTTP_ALLOWED_ORIGINS (comma-separated scheme://host[:port] values). DATTO_SAAS_MCP_READ_ONLY=1 lists only read-only tools: datto-saas_execute, sync, export, the exit-inventory recipe and the learn-store tools (teach, teach_lookup, teach_pattern, teach_playbook, playbook_amend, learnings_confirm, learnings_forget, learnings_reject, workflow_archive) are not registered.

Over MCP the API endpoints are reached through datto-saas_search, datto-saas_read and datto-saas_execute. The one write, seats.bulk-change, goes through datto-saas_execute: it returns a preview and sends only when confirm is boolean true.

Direct Use

Check if installed: which datto-saas-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:

datto-saas-cli seats gaps --since 30d --agent

If ambiguous, drill into subcommand help, for example datto-saas-cli seats --help.