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/parallel-web/parallel-cursor-plugin/parallel-setupgit clone --depth 1 https://github.com/parallel-web/parallel-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 | $0.00015 | $0.00350 |
| Opus 5 | $0.00008 | $0.00175 |
| Sonnet 5 | $0.00003 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade C, and why
parallel-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.
curl -fsSL https://parallel.ai/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://parallel.ai/install.sh | bash What it actually says
Parallel Plugin Setup
Step 1: Check if CLI is already installed
parallel-cli --version
If this prints a version, skip to Step 2: Authenticate.
Step 1b: Attempt installation
Try installing with the install script:
curl -fsSL https://parallel.ai/install.sh | bash
If that fails, try pipx:
pipx install "parallel-web-tools[cli]"
pipx ensurepath
After either install method, verify it worked:
parallel-cli --version
If installation fails
Tell the user to re-run /parallel-setup with sandbox mode disabled. Installation requires network and filesystem access that Cursor's sandbox may block.
Alternatively, they can install manually in their own terminal:
curl -fsSL https://parallel.ai/install.sh | bash
or:
pipx install "parallel-web-tools[cli]"
pipx ensurepath
They may need to add ~/.local/bin to PATH in their shell config (e.g. ~/.zshrc). Ask them to re-run /parallel-setup once installed.
Step 2: Authenticate
Check if already authenticated:
parallel-cli auth
If not authenticated, tell the user to run parallel-cli login in their terminal, or set PARALLEL_API_KEY in their environment.
Step 3: Verify
parallel-cli auth
Confirm the CLI is installed, authenticated, and ready to use.
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 · 73 lines · 15 tokens per session scan C 3dad86c0f6fe
parallel-setup is a command published in the GitHub repository parallel-web/parallel-cursor-plugin (3 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 350 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.