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.
npx agentmods add commands/armert-labs/cursor-plugin/setupgit clone --depth 1 https://github.com/Armert-Labs/cursor-pluginWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.00207 |
| Opus 5 | $0.00008 | $0.00103 |
| Sonnet 5 | $0.00003 | $0.00041 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade C, and why
setup scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- If the result says `cursorAgent.available` is false, tell the user to install the Cursor CLI manually, for example `curl https://cursor.com/install -fsS | bash` (macOS/Linux), then rerun `/cursor:setup`. Do not auto-ru Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- If the result says `cursorAgent.available` is false, tell the user to install the Cursor CLI manually, for example `curl https://cursor.com/install -fsS | bash` (macOS/Linux), then rerun `/cursor:setup`. Do not auto-ru What it actually says
Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/cursor-companion.mjs" setup --json $ARGUMENTS
Output rules:
- Present the final setup output to the user.
- If the result says
cursorAgent.availableis false, tell the user to install the Cursor CLI manually, for examplecurl https://cursor.com/install -fsS | bash(macOS/Linux), then rerun/cursor:setup. Do not auto-run a network installer for them. - If
cursorAgent.availableis true butauth.loggedInis false, preserve the guidance to run!cursor-agent login, or to setCURSOR_API_KEYfor headless use. - Do not attempt to fix anything else.
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.
- yesterday First seen · 18 lines · 16 tokens per session scan C cdeb7aa7b91f
setup is a command published in the GitHub repository Armert-Labs/cursor-plugin (3 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 207 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.