run

run is a command for Claude Code from airmcp-com/mcp-standards. It costs 0 tokens per session (357 once invoked), scanned A, a copy of run, MIT.

A command for running a chain of at least two prompts, where each step receives the complete output from the previous step as context.

In plain words
What is it for?
Use it for multi-step jobs such as analysing authentication, finding security vulnerabilities, proposing fixes, implementing them, and generating tests.
Why use it?
It preserves the work from one stage so later stages can build on it without you manually copying results between prompts.

Command for Claude Code

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/airmcp-com/mcp-standards/run
Clone the repo
git clone --depth 1 https://github.com/airmcp-com/mcp-standards

Made for: Claude Code.

Wrote 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.

agentmods badge for run

README.md
[![agentmods](https://agentmods.dev/badge/commands/airmcp-com/mcp-standards/run.svg)](https://agentmods.dev/commands/airmcp-com/mcp-standards/run)
Your own site
<a href="https://agentmods.dev/commands/airmcp-com/mcp-standards/run"><img src="https://agentmods.dev/badge/commands/airmcp-com/mcp-standards/run.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 357 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00000 $0.00357
Opus 5 $0.00000 $0.00179
Sonnet 5 $0.00000 $0.00071
Haiku 4.5 $0.00000 $0.00036

Measured 2d ago against content hash 554410e9afc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 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.

Origin

This is a copy

100% identical to run — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/stream-chain/run.md · 70 lines

What it actually says

stream-chain run

Execute a custom stream chain with your own prompts.

Usage

claude-flow stream-chain run <prompt1> <prompt2> [...] [options]

Minimum 2 prompts required for chaining.

Options

  • --verbose - Show detailed execution information
  • --timeout <seconds> - Timeout per step (default: 30)
  • --debug - Enable debug mode

How It Works

Each prompt in the chain receives the complete output from the previous step as context, enabling complex multi-step workflows.

Examples

Basic Chain

claude-flow stream-chain run \
  "Write a function" \
  "Add tests for it"

Complex Workflow

claude-flow stream-chain run \
  "Analyze the authentication system" \
  "Identify security vulnerabilities" \
  "Propose fixes with priority levels" \
  "Implement the critical fixes" \
  "Generate tests for the fixes"

With Options

claude-flow stream-chain run \
  "Complex analysis task" \
  "Detailed implementation" \
  --timeout 60 \
  --verbose

Context Preservation

The output from each step is injected into the next prompt:

Step 1: "Write a sorting function"
Output: [function code]

Step 2 receives: "Previous step output:
[function code]

Next step: Optimize for performance"

Best Practices

  1. Clear Instructions: Make each prompt specific
  2. Logical Flow: Order prompts in logical sequence
  3. Appropriate Timeouts: Increase for complex tasks
  4. Verification: Add verification steps in chain
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. 2d ago First seen · 70 lines · 0 tokens per session scan A 554410e9afc1

Subscribe to this mod's changes

run is a command published in the GitHub repository airmcp-com/mcp-standards (3 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 357 tokens. A static security scan graded it A with 0 findings. It is 100% identical to run, differing in 0 lines, and is treated as a copy.