regular_task

A service-monitoring workflow that runs important commands in tmux, a terminal session that can keep a process running after the visible shell changes. It checks progress at increasing time intervals, detects errors, and suggests fixes.

In plain words
What is it for?
Use it to monitor training or other services, inspect logs when something goes wrong, and manage monitored tmux sessions with the required naming and waiting scripts.
Why use it?
It helps catch failed or abnormal long-running jobs without repeatedly watching the terminal manually.

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/binary-husky/alphaautoresearch/regular_task
Any agent
npx skills add binary-husky/AlphaAutoResearch --skill regular_task
Clone the repo
git clone --depth 1 https://github.com/binary-husky/AlphaAutoResearch

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,989 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 $0.00000 $0.01989
Opus 5 $0.00000 $0.00994
Sonnet 5 $0.00000 $0.00398
Haiku 4.5 $0.00000 $0.00199

Measured yesterday against content hash 3313234b4d74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

regular_task 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 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

r = subprocess.run(
alpha_auto_research/skills/regular_task/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  1. Do Not Terminate Without Careful Consideration
  2. Run important commands in tmux sessions, and monitor them with tmux_wait.py to detect errors early and save time.
  3. Always use python ./tmux_wait.py instead of sleep to wait before checking tmux content, so that you can detect errors early and avoid wasting time.
  4. tmux session names must use prefix ajet_worker_*

Service Monitoring Skill

    ---
    name: monitor-with-tmux
    description: Monitor training progress by reading tmux content at exponential backoff intervals (30s, 1min, 2min, 4min, 8min, 16min), analyze logs when anomalies occur, and provide fix suggestions
    license: Complete terms in LICENSE.txt
    ---

    # Monitor with Tmux

    Monitor in tmux, detect anomalies, analyze errors, provide fix suggestions.

    ## Step Zero

    Create a sleep script for tmux monitoring:

    1. Create `./tmux_wait.py`

    ```python
    import argparse
    import subprocess
    import time

    SHELLS = {"bash", "zsh", "sh", "fish", "csh", "tcsh", "ksh", "dash", "ash"}

    def smart_sleep(session: str, seconds: float, check_every: float = 2.0) -> bool:
        end_time = time.time() + seconds
        while time.time() < end_time:
            try:
                r = subprocess.run(
                    ["tmux", "list-panes", "-F", "#{pane_current_command}", "-t", session],
                    capture_output=True, text=True, timeout=5
                )
                if r.returncode != 0:
                    return False
                cmds = [l.strip().lower() for l in r.stdout.splitlines() if l.strip()]
                if not any(c not in SHELLS for c in cmds):
                    return False
            except Exception:
                return False
            time.sleep(min(check_every, end_time - time.time()))
        return True

    def print_tmux_window(session: str, lines: int = 100):
        try:
            r = subprocess.run(
                ["tmux", "capture-pane", "-p", "-t", session],
                capture_output=True, text=True, timeout=5
            )
            if r.returncode == 0:
                output_lines = r.stdout.splitlines()
                print("\n\n--- tmux pane output (last {} lines) ---".format(lines))
                print("\n".join(output_lines[-lines:]))
                print("--- tmux pane output ends ---\n\n")
        except Exception as e:
            print(f"Failed to capture tmux pane: {e}")

    def main():
        parser = argparse.ArgumentParser(description="Wait for a tmux session with smart early-exit.")
        parser.add_argument("session", help="tmux session name")
        parser.add_argument("seconds", type=float, help="total seconds to wait")
        args = parser.parse_args()
        timed_out = smart_sleep(args.session, args.seconds, 2)
        print_tmux_window(args.session, 100)
        raise SystemExit(0 if timed_out else 1)

    if __name__ == "__main__":
        main()
    ```

    ## Begin Monitoring

    When you need to monitor a tmux window, run:

    ```bash
    python ./tmux_wait.py my_ajet_session_name 30
    ```

    This means:
    1. Monitor the tmux session named my_ajet_session_name
    2. Wait for 30 seconds

    - Exit code 0: Normal timeout (command is still running)
    - Exit code 1: Command finished early or session disappeared

    ## Using SSH

    When using SSH, always use a local tmux window to establish the SSH connection.

    ## When You Want to Delay Before Reading tmux Again

    You must have early-return-on-error capability. Do not use `sleep xxx`; instead use `python ./tmux_wait.py my_ajet_session_name xxx`

    DO NOT USE: `sleep 60 && tmux capture-pane -t my_ajet_session_name -p | tail -80`

    YOU SHOULD USE: `python ./tmux_wait.py my_ajet_session_name 30 && tmux capture-pane -t my_ajet_session_name -p | tail -80`

    - 60 seconds is too long
    - Always use `python ./tmux_wait.py` to wait



    ## Examples:


    ### Without SSH

    0 examples available


    ### With SSH

    1 example available

    ```agent

Read the full file on GitHub · 209 lines

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. yesterday First seen · 209 lines · 0 tokens per session scan A 3313234b4d74

Subscribe to this mod's changes

regular_task is a skill published in the GitHub repository binary-husky/AlphaAutoResearch (11 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,989 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens