run

A command that sends a task to a second Claude Code session and returns its response. It can wait for the response or run the task in the background.

In plain words
What is it for?
Use it to delegate coding, investigation, or other command-line tasks to Claude Code and receive the result.
Why use it?
It lets you get another Claude-based analysis without switching sessions or manually copying the task.

Command

Part of the claude plugin — 2 commands shipped together

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 commands/valpere/chorus/run
Clone the repo
git clone --depth 1 https://github.com/valpere/chorus

Or install claude, the plugin that ships this one along with the rest of its 2 commands.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 339 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00012 $0.00339
Opus 5 $0.00006 $0.00169
Sonnet 5 $0.00002 $0.00068
Haiku 4.5 $0.00001 $0.00034

Measured 3d ago against content hash ef72a35d59bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run 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 3d 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.

plugins/claude/commands/run.md · 43 lines

What it actually says

Delegate a task to a second Claude Code instance and return its output verbatim.

Raw slash-command arguments: $ARGUMENTS

Execution mode rules:

  • If the raw arguments include --background, run Claude in the background.
  • If the raw arguments include --wait, run Claude in the foreground.
  • If neither flag is present, ask the user with two options: Wait for results (Recommended) or Run in background.
  • Strip --background and --wait before passing the task to Claude.

Pre-flight check:

  • Run: node "$CLAUDE_PLUGIN_ROOT/scripts/companion.mjs" check
  • If it exits non-zero, stop and tell the user to run /claude:setup.

Execution:

Foreground mode:

  • Run:
node "$CLAUDE_PLUGIN_ROOT/scripts/companion.mjs" run "$ARGUMENTS"
  • Return the stdout verbatim, exactly as-is.
  • Do not paraphrase, summarize, or add commentary.

Background mode:

  • Launch with Bash in the background:
Bash({
  command: `node "$CLAUDE_PLUGIN_ROOT/scripts/companion.mjs" run "$ARGUMENTS"`,
  description: "Claude task",
  run_in_background: true
})
  • Tell the user: "Claude task started in the background."
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. 3d ago First seen · 43 lines · 12 tokens per session scan A ef72a35d59bb

Subscribe to this mod's changes

run is a command published in the GitHub repository valpere/chorus (10 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 339 once invoked, about $0.0001 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.

Related

Other commands, from other repositories

update-ai-versions

Look up the latest published versions of the AI coding assistants pinned in the Dockerfile and update the ARG lines in place.

sugarfreebytes/aidevtools · 24 tokens

yapper-help

The /yapper-help command displays full documentation for the Yapper plugin, including all modes, commands, behaviours, configuration options, and usage examples. This command is itself rendered in Professor mode by default, because a help document that is not thoroughly elaborated would be somewhat contrary to the…

dzan314/yapper · 0 tokens

yapper-review

The /yapper-review command performs a thorough, multi-line pull request review. Rather than posting terse inline comments like "this is wrong" or "use X instead," yapper-review produces fully-explained feedback that describes the issue, the reasoning behind the concern, the potential impact, and a concrete suggested…

dzan314/yapper · 0 tokens

yapper-commit

The /yapper-commit command generates a verbose, fully-explained Git commit message for the current change or a described change. The resulting commit message explains not just what changed, but why it changed, what problem it solves, and how the solution works — providing maximum context for future readers of the git…

dzan314/yapper · 0 tokens

yapper

The /yapper command activates the Yapper verbosity system. Once active, all subsequent responses in the session will be substantially expanded, elaborated, and enriched with definitions, transitions, and restatements.

dzan314/yapper · 0 tokens

mem-last

Prints latest memory cards for the current project.

djinn-soul/gemini-mem · 0 tokens