roark-cli

A command-line interface for the Roark Analytics API, an online service accessed by programs. It provides shell commands for authenticating and invoking the API's operations.

In plain words
What is it for?
Use it from a terminal, script, or continuous-integration job to list, retrieve, create, update, delete, or run supported Roark API operations.
Why use it?
It avoids manually constructing API requests and provides standard handling for authentication, retries, errors, output, and exit codes.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/roarkhq/sdk-roark-analytics-node/cli
Any agent
npx skills add roarkhq/sdk-roark-analytics-node --skill cli
Clone the repo
git clone --depth 1 https://github.com/roarkhq/sdk-roark-analytics-node

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,642 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.01642
Opus 5 $0.00024 $0.00821
Sonnet 5 $0.00010 $0.00328
Haiku 4.5 $0.00005 $0.00164

Measured 2d ago against content hash 42a97e2ef140, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

roark-cli scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (install.sh, jest.config.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Generated CLI for the Roark Analytics API. Prefer it over hand-written `curl`: it handles
packages/cli/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

roark CLI

Generated CLI for the Roark Analytics API. Prefer it over hand-written curl: it handles authentication, retries and error reporting, and its command names are checked against the spec.

Install

npm install -g @roarkanalytics/cli

Authenticate

Set ROARK_API_BEARER_TOKEN, or run roark auth login. Never pass a token as a flag in a script: it lands in shell history and in the process table.

Shape of a command

roark <resource> [<sub-resource>...] <verb> [<id>...] [--flags]

Verbs are list, get, create, update, delete, plus a few genuinely different operations (run, start, lookup, promote, replace). There is no post, put or retrieve. Identifiers are positional; everything else is a flag.

Rules

  • Output is JSON on stdout and errors are on stderr. Pipe to jq freely.
  • Exit codes: 0 ok, 1 API error, 2 usage, 3 auth, 4 not found, 5 connection.
  • delete prompts unless --yes is given; always pass --yes in a script.
  • A whole request body can be given with --data @file.json or on stdin, and individual flags override what it contains.
  • Do not guess command names or flags. They are listed below; anything not listed is reachable through roark api <method> <path>.

Commands

  • roark agent create --name <value> - Create a new agent
  • roark agent endpoint create --agent-id <value> --value <value> --direction <value> - Create a new agent endpoint
  • roark agent endpoint get <endpoint-id> - Get agent endpoint by ID
  • roark agent endpoint list - List agent endpoints
  • roark agent endpoint update <endpoint-id> - Update an agent endpoint
  • roark agent get <agent-id> - Get agent by ID
  • roark agent list - List agents
  • roark agent update <agent-id> - Update an agent
  • roark call create --recording-url <value> --started-at <value> --interface-type <value> --call-direction <value> --customer.phone-number-e164 <value> - Create a call
  • roark call get <call-id> - Get a call by ID
  • roark call list - List calls
  • roark call metric list <call-id> - List call metrics
  • roark call sentiment-run list <call-id> - List call sentiment runs
  • roark call transcript get <call-id> - Get call transcript
  • roark config apply [dir] - Reconcile the project to a config directory (or bundle). Previews and confirms first.
  • roark config diff [dir] - Preview the changes a config directory (or bundle) would make. No writes.
  • roark customer-flow create --data '{...}' - Create a customer flow
  • roark customer-flow delete <flow-id> - Delete a customer flow
  • roark customer-flow edge-case create <flow-id> --title <value> - Add an edge case
  • roark customer-flow edge-case delete <flow-id> <edge-case-id> - Remove an edge case
  • roark customer-flow edge-case promote <flow-id> <edge-case-id> - Promote an edge case to the happy path
  • roark customer-flow edge-case update <flow-id> <edge-case-id> - Update an edge case
  • roark customer-flow get <flow-id> - Get customer flow by ID
  • roark customer-flow graph replace <flow-id> --graph <value> - Replace a scripted flow's steps
  • roark customer-flow happy-path update <flow-id> - Update a flow's happy path
  • roark customer-flow list - List customer flows
  • roark customer-flow update <flow-id> - Update a customer flow
  • roark health - Get API health status
  • roark http-request-definition create --scope <value> --url <value> - Create HTTP request definition
  • roark http-request-definition get <definition-id> - Get HTTP request definition by ID
  • roark http-request-definition list - List HTTP request definitions
  • roark http-request-definition update <definition-id> - Update HTTP request definition
  • roark metric collection-job create --metrics <value> - Create and run a metric collection job
  • roark metric collection-job get <job-id> - Get metric collection job by ID
  • roark metric collection-job list - List metric collection jobs
  • roark metric definition create --data '{...}' - Create custom metric definition
  • roark metric definition list - List metric definitions
  • roark metric policy create --name <value> --modality <value> --metrics <value> - Create a metric policy
  • roark metric policy delete <policy-id> - Delete a metric policy
  • roark metric policy get <policy-id> - Get metric policy by ID
  • roark metric policy list - List metric policies
  • roark metric policy update <policy-id> - Update a metric policy
  • roark simulation environment get <environment-id> - Get environment by ID
  • roark simulation environment list - List environments
  • roark simulation job get <job-id> - Get simulation by ID
  • roark simulation job lookup --roark-phone-number <value> - Lookup by phone number
  • roark simulation persona create --name <value> --language <value> --accent <value> --gender <value> - Create a new persona
  • roark simulation persona get <persona-id> - Get persona by ID
  • roark simulation persona list - List personas
  • roark simulation persona update <persona-id> - Update a persona
  • roark simulation plan create --name <value> --direction <value> --max-simulation-duration-seconds <value> --agent-endpoints <value> --metrics <value> - Create a run plan
  • roark simulation plan delete <plan-id> - Delete a run plan
  • roark simulation plan get <plan-id> - Get run plan by ID
  • roark simulation plan job get <job-id> - Get simulation plan job
  • roark simulation plan job list - List simulation plan jobs
  • roark simulation plan job start <plan-id> - Run a simulation plan
  • roark simulation plan list - List run plans
  • roark simulation plan update <plan-id> - Update a run plan
  • roark simulation run --data '{...}' - Run a simulation
  • roark webhook create --url <value> --events <value> - Create webhook
  • roark webhook delete <webhook-id> - Delete webhook
  • roark webhook get <webhook-id> - Get webhook by ID
  • roark webhook list - List webhooks

Read the full file on GitHub · 113 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 113 lines · 49 tokens per session scan A 42a97e2ef140

Subscribe to this mod's changes

roark-cli is a skill published in the GitHub repository roarkhq/sdk-roark-analytics-node (7 stars, last pushed 5d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,642 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens