Skip to main content
skill CX Codex

long-command-check — Claude Code skill: what it does, how to install

long-command-check is a Claude Code skill that audits shell command execution in agent harnesses. It checks dev server hangs, timeouts, backgrounding, and prompt cache expiration.

MIT ★ 741 updated 2026-11-11

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install ronny@mcode-stack
Open on GitHub

What long-command-check does

The skill audits agent harness code for shell commands and background tasks against a ten-point checklist. It inspects foreground blocking limits so they stay safely below the provider's prompt cache lifetime, preventing expensive cache misses on long runs. It also verifies whether backgrounding keeps the original process alive instead of restarting it.

Other audit points cover timeout resets, result delivery via notifications rather than blind polling, output truncation, process cleanup on exit, and unread task persistence across context compaction. The skill tests harness behavior directly with four checks: launching a dev server, running multi-minute commands, killing the agent during execution, and triggering compaction before results are read.

The final report generates a table with pass, fail, or unknown marks, backed by code references, test results, and three recommended fixes.

What it helps with

  • audit an agent shell harness for orphaned background tasks
  • move long commands to the background without killing and restarting processes
  • stop prompt cache expiration caused by long foreground waits
  • preserve unread task results across conversation compaction

Example prompts for the agent

  • Audit our agent shell tool against the checklist in checklists/long-command.md.
  • Test whether the agent hangs when starting a dev server or running background tests.
  • Run the long command audit and list the top three fixes for our harness.

How to install long-command-check

1Plugin marketplace

/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install ronny@mcode-stack

This installs the whole ronny plugin with all its skills

2Skills CLI (Vercel)

npx skills add MiniMax-AI/mcode-stack --skill long-command-check -a claude-code

3Manually: put the files in place

~/.claude/skills/long-command-check/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/long-command-check/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about long-command-check

How to install long-command-check in Claude Code?

Add the repository with /plugin marketplace add MiniMax-AI/mcode-stack, then run /plugin install ronny@mcode-stack.

What does the long-command-check skill do?

It reviews agent shell harnesses across 10 checklist criteria and runs behavioral tests for hangs, cleanup, and background tasks.

Why are long foreground shell waits problematic?

Foreground waits delay the next model request. If waiting exceeds the model provider's prompt cache lifetime, the next request re-processes the entire prompt prefix from scratch.

Source text

SKILL.md · MIT
---
name: long-command-check
description: Audit how an agent harness runs long shell commands, covering foreground wait limits, moving to background without re-running, timeouts, completion notification, polling, output size, cleanup and behaviour after compaction. Use when building or reviewing an agent's shell or background-task tool, or when an agent hangs on dev servers, long builds or test runs.
---

# Long Command Check

For people building agents. The question is simple: when the agent runs a
shell command, should it wait for it to finish? Following that question leads
to a chain of design decisions. Foreground is for fast commands, background is
for long ones, and ideally the same process connects the two.

Companion to MCode Engineering Notes 04, "How long should one bash command
wait". Plain-text checklist: `checklists/long-command.md`.

## Why waiting is expensive

Two costs while the agent blocks on a command:

- The visible one: the user waits and nothing else happens.
- The hidden one: the provider's **prompt cache can expire**. While a command
  runs in the foreground there are no new model requests. If the wait is
  longer than the cache lifetime of the model service you use, the next
  request re-processes the whole prefix: slower first token, higher cost.
  Look up the cache lifetime in your provider's documentation.

Moving work to the background does not keep the cache warm forever. It saves
the time the agent would otherwise spend idle when it had other work to do.

## How to run the audit

Read the shell tool and background-task code of the target agent. For each
item, record the answer with evidence (file and function, config, or a test
you ran). Do not guess; write "unknown" if the code does not show it.

| # | Item | Question |
| --- | --- | --- |
| 1 | Foreground limit | How long does the foreground wait at most? Is that comfortably below the cache lifetime of your model service, leaving room for generation time? |
| 2 | No re-run | When a command moves from foreground to background, is it the same process, or is it killed and started again? |
| 3 | Timeout accounting | After moving to background and reading output, is the deadline reset? (It should not be, or a stuck command can run forever.) |
| 4 | Result delivery | When a background task finishes, does the model learn it from a notification, or only by polling? |
| 5 | Notification position | Is the notification appended at the end, or does it modify an already cached prefix? |
| 6 | Anti-polling | Is blocking wait time capped, and does repeated reading with no change produce a hint to stop polling? |
| 7 | Output size | Is large output truncated or written to a file and read incrementally, rather than pasted whole into context? Is incomplete output labelled as incomplete? |
| 8 | Cleanup | Who stops background tasks when the user stops the agent, when a one-shot headless run exits, and when the process restarts? Are orphaned tasks marked instead of showing "running" forever? |
| 9 | After compaction | Is "a task finished and its result was not read" tracked outside the conversation history (for example a task table), so it survives compaction? |
| 10 | Precondition | If the current environment cannot read background results, is backgrounding disabled? |

## Quick behavioural tests

If you can run the agent, try these and record what actually happened:

1. Ask it to start a dev server and then do something else. Does it hang?
2. Run a command that takes several minutes. Does it move to the background
   without starting a second copy?
3. Start a background task, then stop the agent. Is the task stopped?
4. Let a background task finish, then trigger compaction before reading the
   result. Is the unread result still surfaced afterwards?

## Output

A table of the ten items with pass / fail / unknown and evidence, the results
of any behavioural tests, and the top three fixes.

© Ronny (MiniMax Code team) · MIT · MiniMax-AI/mcode-stack

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set27

The whole set →
pr-description pr-description is a Claude Code skill that drafts and verifies pull request descriptions for GitHub and GitLab. It runs when opening a PR or when MCode Review reports missing sections. CX Codex +1 ★ 741repo stars subagent-split-check subagent-split-check is a Claude Code skill that decides whether work belongs in a subagent or the main loop. It checks context boundaries before a split. CX Codex +1 ★ 741repo stars context-tax-audit The context-tax-audit skill for Claude Code inventories injected data in agent requests to reduce token usage. It identifies redundant prompt blocks and configurations that hinder prompt cache performance. CX Codex +1 ★ 741repo stars long-session-check long-session-check is a Claude Code skill that audits long-session context and memory handling. It starts when constraints get lost or compaction has happened several times. CX Codex +1 ★ 741repo stars tool-budget-audit tool-budget-audit is a Claude Code skill that measures context used by tool schemas and call results. It flags catalog bloat and mistaken tool choices. CX Codex +1 ★ 741repo stars pr-quiz pr-quiz is a Claude Code skill that drafts multiple-choice questions for PR authors. It triggers when the MCode Review pipeline requests an author quiz. CX Codex +1 ★ 741repo stars pr-review pr-review is a Claude Code skill that reviews pull requests and branches with MCode Review rules. It runs from CI or on a developer’s request before human review. CX Codex +1 ★ 741repo stars pr-review-tuning pr-review-tuning is a Claude Code skill that automates the weekly tuning loop for a code review bot. It evaluates recent pull requests and proposes rule updates based on performance metrics. CX Codex +1 ★ 741repo stars

Project sponsors

Companies that keep this analytics open