Threatlocker

ThreatLocker - Claude Code Skill

Prerequisites: Install the CLI

This skill drives the threatlocker-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:

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

2. Windows (PowerShell):

   powershellCopy code
   iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/threatlocker/install.ps1 | iex
   

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

The installer downloads the threatlocker-cli and threatlocker-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.

A single CLI for MSPs running ThreatLocker across many customer tenants. It matches the full read surface of the incumbent MCP server, adds the writes nobody shipped (approve requests, toggle maintenance, push policy), and mirrors every entity into a local SQLite database so you can triage approvals, audit drift, and device health across ALL tenants at once - something the per-tenant API forces you to do one header-swap at a time.

When to Use This CLI

Use this CLI when you operate ThreatLocker across multiple customer organizations and need to act, not just read - clearing approval backlogs at scale, exporting audit evidence before it ages off, finding unhealthy agents, or pushing policy across tenants. It is the right tool when the portal's one-tenant-at-a-time UI or the read-only MCP server is the bottleneck.

Unique Capabilities

Cross-tenant intelligence

• approvals triage - One ranked queue of every pending application approval across all your managed customer tenants, grouped by file hash so duplicate requests collapse into one row.

  Reach for this to clear the morning approval backlog across an entire MSP book without swapping tenant context request-by-request.

  bashCopy code
  threatlocker-cli approvals triage --all-tenants --agent
  

• audit drift - One ranked table of security-relevant changes - protection disabled, policy changed, maintenance toggled - across every tenant in a time window.

  Use this for the weekly compliance sweep or right after a customer reports something changed unexpectedly.

  bashCopy code
  threatlocker-cli audit drift --since 7d --all-tenants --agent
  

• devices health - Joins computers, online-devices, and last-checkin data to classify every endpoint healthy / offline / stale / isolated, rolled up per tenant.

  Reach for this for the daily 'which agents are dark across all customers' sweep and post-patch verification.

  bashCopy code
  threatlocker-cli devices health --all-tenants --agent
  

• applications hunt - Find a file (by hash, certificate, or path) in every tenant's synced approval requests (tenant, endpoint, status) and application rules (which applications already trust it), in one offline query.

  Reach for this during incident response to see which tenants and endpoints asked to run a file, and which application rules already trust it, without swapping tenant context per search.

  bashCopy code
  threatlocker-cli applications hunt --hash 3a7bd3e2360a3d29eea436fcfb7e44c735d117c42d1c1835420b6b9942dd4f1b --agent
  

• maintenance open - Lists every endpoint whose maintenance-mode window is open right now across all tenants, longest-open first, flagging windows open past an age threshold.

  Reach for this to catch endpoints a technician left in a maintenance mode that relaxes protection, which keep running that way until someone notices.

  bashCopy code
  threatlocker-cli maintenance open --older-than 24h --agent
  

• organizations posture - One row per managed tenant from the local store: endpoint count, online and isolated endpoints, pending approvals, open maintenance windows and the age of the newest audit row.

  Reach for this before a customer review or a morning sweep to see which tenant needs attention first.

  bashCopy code
  threatlocker-cli organizations posture --agent
  

MSP write operations

• approvals approve-batch - Approve the same file (by SHA256) across every tenant where it is pending, in one command, with a dry-run plan first.

  Use this when one trusted updater is blocked everywhere - approve it once instead of clicking through 30 portals.

  bashCopy code
  threatlocker-cli approvals approve-batch --hash e3b0c44298fc1c149afbf4c8996fb924... --all-tenants --dry-run
  

Audit & compliance

• audit export - Export the Unified Audit log that audit pull saved, per tenant or across all tenants, to JSONL/CSV, keeping evidence past ThreatLocker's 31-day retention cliff.

  Run this on a schedule so compliance evidence and incident timelines survive the retention window.

  bashCopy code
  threatlocker-cli audit export --all-tenants --since 2026-04-01 --agent
  

• audit retention-check - Reports, per tenant, the oldest audit row you have versus the 31-day cliff and how stale your last complete audit pull is - flagging tenants about to lose evidence.

  Pick this to catch a broken export before the data it should have captured ages off the 31-day window forever.

  bashCopy code
  threatlocker-cli audit retention-check --agent
  

• audit pull - Pages the Unified Audit and portal system-audit searches for a time window into the local store, so audit export, drift, retention-check and posture have rows past the 31-day cliff.

  Run it on a schedule shorter than 31 days and the local archive keeps the evidence ThreatLocker deletes.

  bashCopy code
  threatlocker-cli audit pull --since 30d --agent
  

Auth resilience

• doctor - Diagnoses the #1 ThreatLocker integration pain: validates the raw 64-hex token format, the no-Bearer Authorization header, the ManagedOrganizationId header, New-vs-Old API mode, pings an authenticated endpoint, and maps a 401 to its exact likely cause.

  Run this first whenever a script starts returning 401 - it tells you whether the token expired, the org header is missing, or you're on the deprecated API mode.

  bashCopy code
  threatlocker-cli doctor --agent
  

Command Reference

application-files - File rules belonging to an application

• threatlocker-cli application-files - List the file rules within an application (paginated)

applications - Application definitions (custom + built-in) and policies' targets

• threatlocker-cli applications create - Create a custom application definition
• threatlocker-cli applications get - Get a single application by id
• threatlocker-cli applications match - Match a file (hash/path/cert) to existing applications - used in the approval flow
• threatlocker-cli applications research - ThreatLocker security research details (risk ratings, categories, remediation)
• threatlocker-cli applications search - Search applications (paginated). searchBy: app/full/process/hash/cert/created/categories/countries.
• threatlocker-cli applications update - Update an application's name/description

approvals - Application-control approval requests (list, inspect, approve)

• threatlocker-cli approvals approve - Approve (permit) an application approval request, creating/extending a permit policy. policyLevel: org/group/computer.
• threatlocker-cli approvals count - Count of pending approval requests
• threatlocker-cli approvals get - Get a single approval request
• threatlocker-cli approvals list - List approval requests. statusId 1=Pending,4=Approved,10=Ignored,13=Escalated. Use --child-orgs to span tenants.
• threatlocker-cli approvals permit-options - Get the permit options for an approval request (inputs to approve)
• threatlocker-cli approvals storage - Get storage-control approval request details

audit - Unified Audit (ActionLog) - permit/deny events. Default retention 31 days.

• threatlocker-cli audit file-history - All audit events for a given file path
• threatlocker-cli audit get - Get a single audit entry by id
• threatlocker-cli audit search - Search the Unified Audit log. actionId 1=Permit,2=Deny,99=AnyDeny. Requires startDate/endDate.

computer-groups - Computer groups

• threatlocker-cli computer-groups dropdown - Simple group dropdown (label/value)
• threatlocker-cli computer-groups list - List computer groups with nested computers

computers - Manage and inspect protected computers/devices

• threatlocker-cli computers baseline-rescan - Restart Baseline (learning) on computers
• threatlocker-cli computers checkins - Connection/check-in history for a computer (paginated)
• threatlocker-cli computers delete - Delete/remove computers by id
• threatlocker-cli computers enable-protection - Enable Secured Mode (re-enable protection) on computers
• threatlocker-cli computers get - Get a single computer's detail by id
• threatlocker-cli computers install-info - Deployment/install info for adding new computers
• threatlocker-cli computers list - List/search computers (paginated). searchBy 1-5; orderBy e.g. computername.
• threatlocker-cli computers maintenance - Enable maintenance mode (disable protection) on computers for a window
• threatlocker-cli computers maintenance-update - Set/extend maintenance mode on a single computer
• threatlocker-cli computers move-org - Move computers to another organization (tenant)
• threatlocker-cli computers restart-service - Restart the ThreatLocker service on computers

maintenance - Maintenance-mode history

• threatlocker-cli maintenance - Maintenance-mode history for a computer (paginated)

network-policies - Network Control (network access) policies

• threatlocker-cli network-policies get - Get a single network access policy by id
• threatlocker-cli network-policies list - List network access policies (paginated)

online-devices - Currently-online devices

• threatlocker-cli online-devices - List currently-online devices (paginated)

organizations - Managed (child) organizations - MSP tenants

• threatlocker-cli organizations auth-key - Get the installation auth key for the current organization
• threatlocker-cli organizations for-move - List organizations available as computer-move targets
• threatlocker-cli organizations list - List child/managed organizations (paginated)

policies - Application Control / Storage / Network policies

• threatlocker-cli policies copy - Copy policies from a source org/group to target org(s) - cross-tenant cloning
• threatlocker-cli policies create - Create a policy. policyActionId 1=Permit,2=Deny,6=Permit+Ringfence.
• threatlocker-cli policies delete - Delete policies by id
• threatlocker-cli policies deploy - Queue a policy deployment for an organization
• threatlocker-cli policies get - Get a single policy by id
• threatlocker-cli policies list-by-app - List policies that target an application (paginated)

reports - Reports

• threatlocker-cli reports data - Fetch dynamic data for a report
• threatlocker-cli reports list - List report categories and their reports

scheduled-actions - Scheduled agent actions

• threatlocker-cli scheduled-actions get - Get a single scheduled action by id
• threatlocker-cli scheduled-actions list - List scheduled agent actions
• threatlocker-cli scheduled-actions search - Search scheduled actions (paginated)

storage-policies - Storage Control policies

• threatlocker-cli storage-policies get - Get a single storage policy by id
• threatlocker-cli storage-policies list - List storage policies (paginated)

system-audit - Portal system audit (admin actions) + Health Center

• threatlocker-cli system-audit health-center - Health Center data for the last N days (1-365)
• threatlocker-cli system-audit search - Search portal admin/system audit entries. Requires startDate/endDate.

tags - Tags

• threatlocker-cli tags dropdown - Tag dropdown options (label/value)
• threatlocker-cli tags get - Get a single tag (with its values) by id

versions - ThreatLocker agent versions

• threatlocker-cli versions - List available agent versions (label/value/isEnabled/isDefault/osType)

applications

• threatlocker-cli applications hunt - Find a file (by hash, certificate, or path) in every tenant's synced approval requests (tenant, endpoint, status) and application rules (which applications already trust it), in one offline query.

approvals

• threatlocker-cli approvals triage - One ranked queue of every pending application approval across all your managed customer tenants, grouped by file hash so duplicate requests collapse into one row.

• threatlocker-cli approvals approve-batch - Approve the same file (by SHA256) across every tenant where it is pending, in one command, with a dry-run plan first.

audit

• threatlocker-cli audit export - Export the Unified Audit log that audit pull saved, per tenant or across all tenants, to JSONL/CSV, keeping evidence past ThreatLocker's 31-day retention cliff.

• threatlocker-cli audit retention-check - Reports, per tenant, the oldest audit row you have versus the 31-day cliff and how stale your last complete audit pull is - flagging tenants about to lose evidence.

• threatlocker-cli audit drift - One ranked table of security-relevant changes - protection disabled, policy changed, maintenance toggled - across every tenant in a time window.

• threatlocker-cli audit pull - Pages the Unified Audit and portal system-audit searches for a time window into the local store, so audit export, drift, retention-check and posture have rows past the 31-day cliff.

devices

• threatlocker-cli devices health - Joins computers, online-devices, and last-checkin data to classify every endpoint healthy / offline / stale / isolated, rolled up per tenant.

maintenance

• threatlocker-cli maintenance open - Lists every endpoint whose maintenance-mode window is open right now across all tenants (learning, installation or disabled protection), longest-open first, flagging windows past an age threshold.

organizations

• threatlocker-cli organizations posture - One row per managed tenant from the local store: endpoint count, online and isolated endpoints, pending approvals, open maintenance windows and the age of the newest audit row.

Finding the right command

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

bashCopy code
threatlocker-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 cross-tenant approval sweep

bashCopy code
threatlocker-cli approvals triage --all-tenants --agent --select organizationName,fileName,hash,ageHours,duplicateCount

Drain the overnight backlog ranked by age with duplicate hashes collapsed, then batch-approve the trusted ones. Requires a recent sync --resources approvals.

Nightly audit archive before the 31-day cliff

bashCopy code
threatlocker-cli audit export --all-tenants --since 2026-04-01 --csv > audit-archive.csv

Persist Unified Audit beyond ThreatLocker's retention window for SIEM and compliance. Run threatlocker-cli audit pull --since 30d first: the export materializes from the local archive that pull fills.

Who disabled protection this week

bashCopy code
threatlocker-cli audit drift --since 7d --all-tenants --agent

One ranked table of protection-off / policy-change / maintenance events across every customer. Run threatlocker-cli audit pull --since 30d first.

Dark-agent health sweep

bashCopy code
threatlocker-cli devices health --all-tenants --agent --select organizationName,computerName,healthClass,lastCheckin

Classify every endpoint healthy/offline/stale/isolated across all tenants in one pass. Requires a recent sync --resources computers,online-devices.

Diagnose a broken automation

bashCopy code
threatlocker-cli doctor --agent

Pinpoint whether a 401 is an expired token, a missing org header, or Old-API mode.

Auth Setup

Auth is a raw API token in the Authorization header (NO 'Bearer' prefix) - a 64-character lowercase hex string created in the portal under Administrators > API Users > Generate API Token. Most calls also need a ManagedOrganizationId header (your tenant GUID); set THREATLOCKER_ORG_ID or pass --org. Tokens renew on each use and silently expire when idle, so run doctor if you hit a 401.

Run threatlocker-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:

  bashCopy code
  threatlocker-cli application-files --application-id 550e8400-e29b-41d4-a716-446655440000 --agent --select applicationFileId,applicationId,fullPath
  

• 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

• Explicit confirmation - --agent does not imply --yes; pass --yes separately only after the target, arguments, and side effects are clear

• Explicit retries - use --idempotent only when an already-existing create should count as success

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

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

• Use per-kind env vars only when a specific kind must diverge: THREATLOCKER_CONFIG_DIR, THREATLOCKER_DATA_DIR, THREATLOCKER_STATE_DIR, THREATLOCKER_CACHE_DIR.

• Resolution order is per-kind env var, --home, THREATLOCKER_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 threatlocker-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:

  jsonCopy code
  {
    "mcpServers": {
      "threatlocker": {
        "command": "threatlocker-mcp",
        "env": {
          "THREATLOCKER_HOME": "/srv/threatlocker"
        }
      }
    }
  }
  

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use THREATLOCKER_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 THREATLOCKER_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. THREATLOCKER_NO_LOCAL_DATA=1 disables the response cache and store writes, turns auto reads into live reads, and blocks sync and workflow archive; --data-source local still reads an existing store, and THREATLOCKER_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:

bashCopy code
# 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=$(cat /path/to/question.txt)
threatlocker-cli recall "$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:

jsonCopy code
{
  "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>", "threatlocker-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:

Copy code
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 `threatlocker-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; threatlocker-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 threatlocker-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:

bashCopy code
QUERY=$(cat /path/to/question.txt)
threatlocker-cli teach --query "$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:

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

bashCopy code
QUERY=$(cat /path/to/question.txt)
NOTE=$(cat /path/to/note.txt)
threatlocker-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

threatlocker-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.
• THREATLOCKER_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:

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

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

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.

Copy code
threatlocker-cli profile save briefing --json
threatlocker-cli --profile briefing application-files --application-id 550e8400-e29b-41d4-a716-446655440000
threatlocker-cli profile list --json
threatlocker-cli profile show briefing
threatlocker-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

Argument Parsing

Parse $ARGUMENTS:

1. Empty, help, or --help → show threatlocker-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:

   bashCopy code
   claude mcp add threatlocker-mcp -- threatlocker-mcp
   

3. Verify: claude mcp list

For a remote host, threatlocker-mcp --transport http requires THREATLOCKER_MCP_HTTP_TOKEN (callers send Authorization: Bearer <token>), serves http://127.0.0.1:7777/mcp by default, and needs --tls-cert/--tls-key for any non-loopback --addr. THREATLOCKER_MCP_READ_ONLY=1 (exactly 1) lists only read-only tools: it removes threatlocker_execute, approvals_approve_batch, audit_pull, sync, workflow_archive, import, export and the learn-store tools (teach, teach_lookup, teach_pattern, teach_playbook, playbook_amend, playbook_list, recall, learnings_confirm, learnings_reject, learnings_forget), 17 of the 38 tools, and threatlocker_read still refuses every state-changing endpoint.

Direct Use

1. Check if installed: which threatlocker-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:

   bashCopy code
   threatlocker-cli <command> [subcommand] [args] --agent
   

4. If ambiguous, drill into subcommand help: threatlocker-cli <command> --help.