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 rules/cybertheory/clrun/use-clrungit clone --depth 1 https://github.com/cybertheory/clrunWhat 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 | $0.00486 | $0.00486 |
| Opus 5 | $0.00243 | $0.00243 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
use-clrun scanned grade A with 0 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 2d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Use clrun for All Terminal Commands
When executing terminal commands, always use clrun instead of running commands directly in the shell. This gives persistent, observable, interactive sessions.
How to Run Commands
# Start a new session
clrun <command>
# Send input to an existing session
clrun <terminal_id> "<text>"
# Navigate TUI prompts (select lists, checkboxes, confirms)
clrun key <terminal_id> down down enter
clrun key <terminal_id> space down space enter
# Read output
clrun tail <terminal_id> --lines 50
# Check all sessions
clrun status
# Kill a session
clrun kill <terminal_id>
Rules
- Never run shell commands directly — always wrap them with
clrun - Store the
terminal_idfrom everyclrunresponse - Use
clrun keyfor TUI prompts with select lists or checkboxes - Use
clrun <id> "text"for text input prompts - Use
clrun key <id> enterto accept defaults in TUI prompts - Single-quote
$variables —clrun <id> 'echo $VAR' - Read the
hintsin every response — they tell you exactly what to do next - Parse YAML — all clrun responses are structured YAML
Prompt Types
| You see | Action |
|---|---|
◆ Name: │ default |
clrun <id> "value" or clrun key <id> enter |
● Option1 ○ Option2 |
clrun key <id> down... enter |
◻ Check1 ◻ Check2 |
clrun key <id> space down space enter |
● Yes / ○ No |
clrun key <id> enter or clrun key <id> right enter |
(y/n) |
clrun <id> "y" or clrun <id> "n" |
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.
- 2d ago First seen · 53 lines · 486 tokens per session scan A 3eb27579c53d
use-clrun is a cursor rule published in the GitHub repository cybertheory/clrun (4 stars, last pushed 6mo ago), licensed MIT. It adds 486 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
agent-development
Python agents are typically in folders named agent-py/ or agent/ and use the sdk-python/ package.
statusline
Turn the usage statusLine on or off (model + context% + 5-hour usage% in every project) without editing config by hand. Runs bin/install-statusline.sh, which installs the script to /.claude and merges the setting without clobbering other keys. Opt-in, global, run once per machine; /statusline off disables it.
add-linter
Add linter configs and GitHub Actions workflows for languages detected in the current repo. Use when the user wants to add linters, set up code quality checks, or after sync-scaffold suggests running /add-linter.
simplify
Structural-quality review of changed code — score against the four-dimension rubric, gate at 10/10, and (in auto-fix mode or with --fix) apply reuse/simplification/efficiency/altitude cleanups. Includes a diff-economy lens; correctness is /validate, full-repo survey is /audit.
create-pr
Create a pull request for the current branch and immediately subscribe to PR activity. Use when the user wants to open a PR, submit changes for review, or push and create a pull request.
conventional-commits
Always use Conventional Commits for git commit messages.