A command for running a named .slang multi-agent workflow from start to finish. The workflow can require defined inputs and human approval before continuing.

Use it to resolve and run workflows by name or file path, provide key-value parameters, answer missing inputs, and complete workflows that require human review.

It organizes a multi-step agent process around a declared contract instead of making the user coordinate each step manually. It also pauses when required information or human decisions are needed.

slang-run — Command for Claude Code by shofer-dev

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.

Clone the repo

git clone --depth 1 https://github.com/shofer-dev/claude-code-slang-orchestrator

Made for: Claude Code.

Or install slang-workflows, the plugin that ships this one along with the rest of its 4 commands, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/shofer-dev/claude-code-slang-orchestrator/slang-run.svg)](https://agentmods.dev/commands/shofer-dev/claude-code-slang-orchestrator/slang-run)

Your own site

<a href="https://agentmods.dev/commands/shofer-dev/claude-code-slang-orchestrator/slang-run"><img src="https://agentmods.dev/badge/commands/shofer-dev/claude-code-slang-orchestrator/slang-run.svg" alt="Measured on agentmods" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 417 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.00417
Opus 5	$0.00010	$0.00209
Sonnet 5	$0.00004	$0.00083
Haiku 4.5	$0.00002	$0.00042

Measured 7d ago against content hash 4b33a4aef81e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

slang-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 7d 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.

commands/slang-run.md · 15 lines

What it actually says

Start the slang workflow the user asked for: $ARGUMENTS

The first token is the workflow identifier; any following key=value pairs are workflow params.

Resolve the workflow. If the identifier contains / or ends in .slang, you'll run it by path; otherwise it's a name. If none was given, or the name is ambiguous, call list_workflows and ask the user which one to run.
Gather required inputs. Call list_workflows to see the chosen flow's declared params. For every param that has no default and was not supplied as a key=value arg, ask the user for it now, in this conversation — smoother than a mid-run dialog, and it lets you discuss/validate the value. (If you don't, run_workflow will prompt for any still-missing required param via an elicitation dialog before it starts, so nothing runs with an unfilled ${param}.) Collect the answers plus the provided key=value pairs into the params object.
Run run_workflow with the name/path and params, synchronously (do NOT pass background:true) — so any escalate @Human step, including a workflow that collects input via an initial form:, can prompt the user through this conversation. Relay each escalation's reason/choices and continue the run with the user's answer.
When it finishes, summarize the terminal status and each agent's committed output, and offer to render the run diagram with get_trace.

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.

7d ago First seen · 15 lines · 19 tokens per session scan A 4b33a4aef81e

Subscribe to this mod's changes

slang-run is a command published in the GitHub repository shofer-dev/claude-code-slang-orchestrator (1 stars, last pushed 9d ago), licensed Apache-2.0. It adds 19 tokens to every session and 417 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.

Building agents Claude Code ai mcp

slang-run

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze