Official agent skill

Argus Run

by microsoft in microsoft/ArgusAgent

A skill your agent uses when work needs persistent multi-step execution, independent review, resumable project state, or long-running research and engineering coordination through Argus.

OfficialMITAuto-check passedAgent Workflows

Install Argus Run

skills CLI
$ npx skills add microsoft/ArgusAgent --skill argus-run -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install microsoft/ArgusAgent argus-run --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/microsoft/ArgusAgent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/argus/skills/argus-run .claude/skills/argus-run && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
argus-run
GitHub stars
135
Token cost
~323 tokens
SKILL.md length
161 words
Files
2
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when work needs persistent multi-step execution, independent review, resumable project state, or long-running research and engineering coordination through Argus.

  • Works in 5 steps: Call argus_project_list with the exact… → Reuse the most recently active… → Call argus_message with the user's… → …
  • Work needs persistent multi-step execution
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Independent review

What it does

Argus Run is an agent skill from microsoft/ArgusAgent, published by the product's own GitHub organization. Use when work needs persistent multi-step execution, independent review, resumable project state, or long-running research and engineering coordination through Argus.

Its SKILL.md is about 320 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows. It works with Model Context Protocol. The repository describes itself as: A persistent, reviewed multi-agent runtime for long-horizon research and engineering. The licence is MIT.

When your agent uses it

  • Work needs persistent multi-step execution
  • Independent review
  • Resumable project state
  • Long-running research and engineering coordination through Argus

Example prompts

  • “/argus-run”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Call argus_project_list with the exact current work directory.
  2. Reuse the most recently active exact-workdir project when one exists;
  3. Call argus_message with the user's complete objective. Manager owns chat
  4. Report the project ID and whether the turn was handled inline or dispatched.
  5. For dispatched work, stop the current turn. Do not create an unchanged polling

What it can do on your machine

Read from SKILL.md and the folder at commit 746f76b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Argus Run loads about 323 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 161 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~323

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microsoft/ArgusAgent at commit 746f76b, republished under its MIT licence (© microsoft). 161 words, ~323 tokens.

Download SKILL.mdSave it as .claude/skills/argus-run/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
argus-run
description
Use when work needs persistent multi-step execution, independent review, resumable project state, or long-running research and engineering coordination through Argus.

Run With Argus

Use the installed Argus MCP tools. Do not imitate the Argus roles in the host session and do not write Argus state files directly.

  1. Call argus_project_list with the exact current work directory.
  2. Reuse the most recently active exact-workdir project when one exists; otherwise call argus_project_create with that directory and a concise name.
  3. Call argus_message with the user's complete objective. Manager owns chat versus task routing, lifetime, workflow, domain, and execution handoff.
  4. Report the project ID and whether the turn was handled inline or dispatched.
  5. For dispatched work, stop the current turn. Do not create an unchanged polling loop; use the argus-status Skill when status is requested.

If the MCP server is unavailable, run argus --doctor and report the exact installation or backend failure. Do not silently replace Argus with an ad hoc single-agent workflow.

Never claim completion from dispatch, daemon activity, loss, or intermediate artifacts. Argus completion comes from its persisted Reviewer/Manager state.

© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/argus/skills/argus-run of microsoft/ArgusAgent.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 746f76b

Compare with similar skills

Argus Run next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Argus Run compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Argus Run this skillmicrosoft/ArgusAgent135—~323Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
MemPalace Memory SearchMemPalace/mempalace59k—~1.4kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed
  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    59k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from microsoft/ArgusAgent

  • Research Workflow

    microsoft/ArgusAgent

    Official

    Plan and execute multi-step research, surveys, feasibility studies, and evidence-heavy analyses with adaptive planning, source verification, critic review, and cross-task learning.

    135 GitHub stars~2.7k tokensUpdated 5 days ago
    Auto-check passed
  • Argus Runtime Orchestration

    microsoft/ArgusAgent

    Official

    Portable outer-operator procedure for durable Argus missions across five hosts.

    135 GitHub stars~3.6k tokensUpdated 5 days ago
    Auto-check passed
  • Minimal Rigorous Work

    microsoft/ArgusAgent

    Official

    A skill your agent uses for Argus implementation, research, document, planning, review, and orchestration work that must stay evidence-driven and lean.

    135 GitHub stars~447 tokensUpdated 5 days ago
    Auto-check passed
  • Target Disease Research

    microsoft/ArgusAgent

    Official

    A skill your agent uses when researching a biomedical target and disease relationship, mechanism, human evidence, clinical translation, safety, failed programs, competitive trials, or an auditable…

    135 GitHub stars~477 tokensUpdated 5 days ago
    Auto-check passed
  • Argus Status

    microsoft/ArgusAgent

    Official

    A skill your agent uses when checking an Argus project's progress, pending questions, active role, diagnostics, selected artifacts, intervention state, recovery options, or graceful stop status.

    135 GitHub stars~295 tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Argus Run

What does Argus Run do?

A skill your agent uses when work needs persistent multi-step execution, independent review, resumable project state, or long-running research and engineering coordination through Argus. Argus Run is an agent skill from microsoft/ArgusAgent, published by the product's own GitHub organization. Use when work needs persistent multi-step execution, independent review, resumable project state, or long-running research and engineering coordination through Argus.

When should I use Argus Run?

Argus Run fits situations like: work needs persistent multi-step execution; independent review; resumable project state; long-running research and engineering coordination through Argus.

How do I install Argus Run in Claude Code?

Run `npx skills add microsoft/ArgusAgent --skill argus-run -a claude-code`. Or copy the skill folder (plugins/argus/skills/argus-run in microsoft/ArgusAgent) into .claude/skills/argus-run in your project. Claude Code loads it when a task matches its description.

How do I install Argus Run in Codex?

Run `npx skills add microsoft/ArgusAgent --skill argus-run -a codex`. Or copy the skill folder (plugins/argus/skills/argus-run in microsoft/ArgusAgent) into .agents/skills/argus-run in your project. Codex loads it when a task matches its description.

Can I use Argus Run in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/ArgusAgent --skill argus-run -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/argus-run, .gemini/skills/argus-run, .github/skills/argus-run and .opencode/skills/argus-run in your project.

What does Argus Run need to run?

SKILL.md names no scripts, command-line tools or credentials: Argus Run is instructions for the agent only.

Does Argus Run access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Argus Run safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Argus Run use?

Argus Run is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Argus Run use?

About 323 tokens (SKILL.md is roughly 1.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Argus Run?

Skills that share tags, products or a category with Argus Run: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Argus Run?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/ArgusAgent, which has 135 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 2, 2026.

Source: microsoft/ArgusAgent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.