cisco-meraki

Use when the user asks about Cisco Meraki across one or many client organizations: what is offline or alerting right now, failed MX WAN uplinks, license, subscription and end-of-support renewals, who

SKILL.md

GitHub

Cisco Meraki - Claude Code Skill

Prerequisites: Install the CLI

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

The installer downloads the cisco-meraki-cli and cisco-meraki-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.

One API key reaches every organization you administer, so this CLI treats them as one fleet: fleet health and fleet down show what is broken across all clients, fleet renewals lists license and hardware deadlines, and fleet find resolves a MAC, IP or serial to the client that owns it. Fleet commands walk every Link-header page; when some orgs fail they still exit 0 with the rows they could read and name the failed orgs on stderr (fleet health also marks each unreachable org's row, and fleet fanout carries the error in each org's row under --json). Generated list commands read every page with --all, and every write supports --dry-run.

When to Use This CLI

Use this CLI when an agent needs to read or change Cisco Meraki Dashboard state, especially across many client organizations at once: fleet health, down devices, license and EoX deadlines, change forensics, admin audits, and locating a device or client by MAC, IP or serial. Most fleet commands read live; fleet changes and fleet find can answer from the local mirror after a sync. History is limited by the API: 31 days for fleet flaps and fleet blame, 365 days for fleet changes.

Anti-triggers

Do not use this CLI for:

  • Do not use this CLI for Meraki Go devices; they are managed by a separate consumer app and API
  • Do not use it for Catalyst Center, ISE or IOS XE device CLI configuration
  • Do not use it to watch for real-time events; configure Dashboard webhooks instead
  • Do not use it for UniFi, Fortinet or other vendors' gear

Unique Capabilities

Every client org at once

  • fleet health - One worst-first row per client org with online, alerting, offline and dormant device counts, failed WAN uplinks, active alerts, and whether the org is reachable at all.

    Reach for this first when asked which client is in the worst shape right now; it answers in one call instead of one call per org.

    cisco-meraki-cli fleet health --agent
    
  • fleet down - Every offline or alerting device and every failed MX WAN uplink across all orgs, with org and network names and, for offline devices, how long since the device last reported.

    Use this to build a dispatch list of individual down devices and sites running on backup WAN across every client.

    cisco-meraki-cli fleet down --agent
    
  • fleet find - Paste a MAC, IP, serial, network ID or name and get the org and network that own the matching device, inventory entry, MX uplink or, by MAC, client.

    Use this whenever a ticket or alert names a device or client without saying which client org it belongs to.

    cisco-meraki-cli fleet find Q2QN-9J8L-SLPD --agent
    
  • fleet fanout - Run any organization-scoped read against every org, fully paginated, with observed-at, item count, completeness and next-cursor metadata per org (use --json: --agent compacts away next_cursor, limit_reason and error).

    Use this for any cross-org read that has no dedicated command, when you need to know the answer is complete.

    cisco-meraki-cli fleet fanout organizations/{organizationId}/firmware/upgrades --json
    

Deadlines and access audits

  • fleet renewals - License expirations (co-term, per-device or subscription, whichever each org uses) and end-of-sale and end-of-support hardware dates in one date-sorted list.

    Use this for renewal and hardware-refresh pipelines across every client org.

    cisco-meraki-cli fleet renewals --within 90d --agent
    
  • fleet admins - Dashboard admins across every org grouped by email, flagging missing two-factor auth, API key holders and stale access, with an offboarding view per person.

    Use this for access reviews and technician offboarding across all client orgs.

    cisco-meraki-cli fleet admins --stale 90d --agent
    

Change and outage history

  • fleet changes - Configuration changes from every org in one list, filterable by admin, org, network and page, with old and new values.

    Use this to answer who changed what in which client org this week.

    cisco-meraki-cli fleet changes --since 7d --agent
    
  • fleet flaps - Devices ranked by minutes offline, then by number of status changes, over a window of up to 31 days, across every org.

    Use this for the weekly look back at unstable devices, not for what is down right now.

    cisco-meraki-cli fleet flaps --since 7d --agent
    
  • fleet blame - For one network ID or device serial: each time it went offline or started alerting within --since (default 7 days, up to 31), the configuration changes made on that network just before.

    Use this in outage postmortems to find the change that probably caused it.

    cisco-meraki-cli fleet blame L_646829496481105433 --window 2h --agent
    

Safe writes at fleet scale

  • fleet push - Apply one settings change to many networks across orgs through action batches: it previews a per-network current-versus-new diff by default and sends batches only with --apply.

    Use this for bulk configuration changes across many client networks; read the preview, then rerun with --apply.

    cisco-meraki-cli fleet push --path /networks/{networkId}/snmp --body snmp.json --network-tag managed
    

Command Reference

The list below is a summary. The full tree has 1035 typed operations under organizations, networks, devices and administered; before concluding a capability is missing, run cisco-meraki-cli which "offline devices" --json or a group's help, e.g. cisco-meraki-cli organizations --help.

administered - Manage administered

  • cisco-meraki-cli administered bind-licensing-subscription-subscription - Bind networks to a subscription
  • cisco-meraki-cli administered claim-licensing-subscription-subscriptions - Claim a subscription into an organization.
  • cisco-meraki-cli administered generate-identities-me-api-keys - Generates an API key for an identity.
  • cisco-meraki-cli administered get-identities-me - Returns the identity of the current user.
  • cisco-meraki-cli administered get-identities-me-api-keys - List the non-sensitive metadata associated with the API keys that belong to the user
  • cisco-meraki-cli administered get-licensing-subscription-entitlements - Retrieve the list of purchasable entitlements
  • cisco-meraki-cli administered get-licensing-subscription-subscriptions - List available subscriptions
  • cisco-meraki-cli administered get-licensing-subscription-subscriptions-compliance-statuses - Get compliance status for requested subscriptions
  • cisco-meraki-cli administered revoke-identities-me-api-keys - Revokes an identity's API key, using the last four characters of the key.
  • cisco-meraki-cli administered validate-licensing-subscription-subscriptions-claim-key - Find a subscription by claim key. Returns 400 if the key has already been claimed.

devices - Manage devices

  • cisco-meraki-cli devices get - Return a single device
  • cisco-meraki-cli devices update - Update the attributes of a device

networks - Manage networks

  • cisco-meraki-cli networks delete - Delete a network
  • cisco-meraki-cli networks get - Return a network
  • cisco-meraki-cli networks update - Update a network

organizations - Manage organizations

  • cisco-meraki-cli organizations create - Create a new organization
  • cisco-meraki-cli organizations delete - Delete an organization
  • cisco-meraki-cli organizations get - List the organizations that the user has privileges on
  • cisco-meraki-cli organizations get-organizationid - Return an organization
  • cisco-meraki-cli organizations update - Update an organization

fleet

  • cisco-meraki-cli fleet health - One worst-first row per client org with online, alerting, offline and dormant device counts, failed WAN uplinks, active alerts, and whether the org is reachable at all.

  • cisco-meraki-cli fleet down - Every offline or alerting device and every failed MX WAN uplink across all orgs, with org and network names and, for offline devices, how long since the device last reported.

  • cisco-meraki-cli fleet renewals - License expirations (co-term, per-device or subscription, whichever each org uses) and end-of-sale and end-of-support hardware dates in one date-sorted list.

  • cisco-meraki-cli fleet changes - Configuration changes from every org in one list, filterable by admin, org, network and page, with old and new values.

  • cisco-meraki-cli fleet find - Paste a MAC, IP, serial, network ID or name and get the org and network that own the matching device, inventory entry, MX uplink or, by MAC, client.

  • cisco-meraki-cli fleet fanout - Run any organization-scoped read against every org, fully paginated, with observed-at, item count, completeness and next-cursor metadata per org.

  • cisco-meraki-cli fleet push - Apply one settings change to many networks across orgs through action batches: it previews a per-network current-versus-new diff by default and sends batches only with --apply.

  • cisco-meraki-cli fleet admins - Dashboard admins across every org grouped by email, flagging missing two-factor auth, API key holders and stale access, with an offboarding view per person.

  • cisco-meraki-cli fleet flaps - Devices ranked by minutes offline, then by number of status changes, over a window of up to 31 days, across every org.

  • cisco-meraki-cli fleet blame - For one network ID or device serial: each time it went offline or started alerting within --since (default 7 days, up to 31), the configuration changes made on that network just before.

Finding the right command

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

cisco-meraki-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

Morning fleet triage

cisco-meraki-cli fleet down --agent --select organization_name,network_name,serial,kind,status,down_for

Narrow the cross-org down list to the fields a dispatcher needs.

Who touched which client this week

cisco-meraki-cli fleet changes --since 7d --group-by admin --agent

Group every org's configuration changes by admin for the weekly review.

Locate a MAC from a SOC alert

cisco-meraki-cli fleet find 00:18:0a:12:34:56 --agent

Resolve a client MAC to the org and network that owns it without guessing.

Renewal pipeline

cisco-meraki-cli fleet renewals --within 90d --csv

Export license and end-of-support deadlines due within 90 days, plus overdue ones, across all orgs for quoting; add --include-expired=false to hide overdue items (over MCP, pass "include-expired": false).

Preview a bulk SNMP change

cisco-meraki-cli fleet push --path /networks/{networkId}/snmp --body snmp.json --network-tag managed

Shows which networks would change and which already match (a credential such as the community string always shows as a change, so the preview cannot confirm it; --apply sends only real changes); nothing is sent until you rerun the same command with --apply.

Auth Setup

Meraki uses one Dashboard API key, sent as the X-Cisco-Meraki-API-Key header. Enable API access for each organization (Organization > Settings > Dashboard API access), then generate a key under My Profile > API access. The key reaches every organization that admin can see, which is what the fleet commands fan out across. Export it as MERAKI_DASHBOARD_API_KEY or store it with auth set-token. Dashboards in Canada, China, India or FedRAMP need CISCO_MERAKI_BASE_URL set to that region's host.

Run cisco-meraki-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)

  • --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:

    cisco-meraki-cli devices get Q2QN-9J8L-SLPD --agent --select serial,name,model,networkId,lanIp
    
  • 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 prompts - writes and deletes run as soon as they are invoked, with no confirmation prompt; preview with --dry-run (or run fleet push without --apply) before mutating. --yes is only read by profile delete and client-profile commands.

  • Explicit retries - use --idempotent only when an already-existing create should count as success, and use --ignore-missing only when a missing delete target should count as success

Response envelope

Generated commands that read from the local store or the API wrap output in a provenance envelope (fleet commands add it only under --agent; with --json they print a bare array):

{
  "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 CISCO_MERAKI_HOME=<dir> to relocate all four path kinds under one root.

  • Use per-kind env vars only when a specific kind must diverge: CISCO_MERAKI_CONFIG_DIR, CISCO_MERAKI_DATA_DIR, CISCO_MERAKI_STATE_DIR, CISCO_MERAKI_CACHE_DIR.

  • Resolution order is per-kind env var, --home, CISCO_MERAKI_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 local mirror (data-<hash>.db, one per API key), 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 cisco-meraki-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": {
        "cisco-meraki": {
          "command": "cisco-meraki-mcp",
          "env": {
            "CISCO_MERAKI_HOME": "/srv/cisco-meraki"
          }
        }
      }
    }
    

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use CISCO_MERAKI_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 CISCO_MERAKI_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, pass the question as an argv or MCP tool argument to recall --json (under --agent the envelope below arrives wrapped as {"meta": ..., "results": <envelope>}). 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=$(cat /path/to/question.txt)
cisco-meraki-cli recall "$QUERY" --json

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>", "cisco-meraki-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 `cisco-meraki-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; cisco-meraki-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 cisco-meraki-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=$(cat /path/to/question.txt)
cisco-meraki-cli teach --query "$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:

# Common case: record both the resource learning AND the playbook in one call.
QUERY=$(cat /path/to/question.txt)
cisco-meraki-cli teach \
  --query "$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=$(cat /path/to/question.txt)
cisco-meraki-cli teach-playbook \
  --query "$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)
cisco-meraki-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

cisco-meraki-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.
  • CISCO_MERAKI_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:

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

Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless CISCO_MERAKI_FEEDBACK_ENDPOINT is set AND either --send is passed or CISCO_MERAKI_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

Sink Effect
stdout Default; write to stdout only
file:<path> Atomically write output to <path> (tmp + rename). 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)

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled or recurring agent reuses the same saved flags while providing different input each run.

cisco-meraki-cli profile save briefing --json
cisco-meraki-cli --profile briefing devices get Q2QN-9J8L-SLPD
cisco-meraki-cli profile list --json
cisco-meraki-cli profile show briefing
cisco-meraki-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 Generic error
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:

  1. Empty, help, or --help → show cisco-meraki-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 for per-agent wire-up).
  2. Register with Claude Code:
    claude mcp add cisco-meraki-mcp --env MERAKI_DASHBOARD_API_KEY=<your-api-key> -- cisco-meraki-mcp
    
  3. Verify: claude mcp list

Direct Use

  1. Check if installed: which cisco-meraki-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:
    cisco-meraki-cli fleet down --agent
    
  4. If ambiguous, drill into subcommand help, e.g. cisco-meraki-cli organizations devices --help.