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 skills/aaaaqwq/agi-super-team/claude-code-runnernpx skills add aAAaqwq/AGI-Super-Team --skill claude-code-runnergit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aaaaqwq/agi-super-team/claude-code-runner)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/claude-code-runner"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/claude-code-runner.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.01312 |
| Opus 5 | $0.00018 | $0.00656 |
| Sonnet 5 | $0.00007 | $0.00262 |
| Haiku 4.5 | $0.00004 | $0.00131 |
Grade B, and why
claude-code-runner scanned grade B 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Root or sudo access (for user switching) How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Runner
Overview
A wrapper skill for running Claude Code programmatically in non-interactive environments. Uses PTY (pseudo-terminal) to handle TTY-required operations and automatically responds to confirmation prompts.
Features
- PTY-based execution: Works in non-TTY environments (containers, CI/CD, background processes)
- Auto-respond to prompts: Automatically answers "Do you want to..." confirmations
- User switching: Runs as specified non-root user
- File synchronization: Copies project to temp directory, executes, syncs changes back
- Timeout handling: Configurable timeout with proper cleanup
- Output capture: Captures and returns full stdout/stderr
Installation
# Clone the skill
git clone https://github.com/lhl09120/claude-code-runner-en.git
# Make script executable
chmod +x claude-code-runner-en/scripts/run_claude.py
Usage
Basic Usage
from claude_code_runner import run_claude_code
result = run_claude_code(
workdir='/path/to/project',
prompt='Refactor the authentication module to use JWT tokens',
user='lighthouse',
timeout=300
)
print(result)
Via Command Line
python3 scripts/run_claude.py /path/to/project "Your task description here"
Advanced Options
result = run_claude_code(
workdir='/root/repo/my-project',
prompt='''
1. Review the codebase
2. Identify security vulnerabilities
3. Fix any issues found
4. Add appropriate tests
''',
user='developer',
timeout=600 # 10 minutes
)
API Reference
run_claude_code(workdir, prompt, user='lighthouse', timeout=300)
Execute a Claude Code task in a PTY environment.
Parameters:
workdir(str): Working directory containing the projectprompt(str): Natural language task descriptionuser(str): User to run as (default: 'lighthouse')timeout(int): Timeout in seconds (default: 300)
Returns:
str: Combined stdout and stderr output
What ships with it
5 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.
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 · 223 lines · 36 tokens per session scan B 6fb465cf17f3
claude-code-runner is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,312 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
code-tour
Maintain docs/code-tour.md — the annotated guided reading of Aigon's core logic. Use when you have changed code the tour quotes, added a subsystem a new reader would need, or the user says "update the code tour", "the tour is stale", "add X to the code tour", or asks to review/refresh the code examples doc.
aigon-next
Suggest the most likely next workflow action based on current context.
aigon-research-do
Do research - agent writes findings.
review-deep
Drive the deep-review phase of an automated PR review. Consumes the walkthrough, runs the deterministic deep-review workflow (parallel lenses → adversarial validation → code-enforced threshold/caps), drafts the surviving findings, and completes the review run.