agentmods.dev

run-agents

run-agents is a skill for Claude Code, Codex from Jerry0022/dotclaude. It costs 111 tokens per session (2,255 once invoked), scanned B, original, MIT.

An orchestration skill that evaluates a task and coordinates several coding agents, either at the same time or in sequence. Orchestration means dividing work between agents and managing how their results fit together.

In plain words
What is it for?
Use it to analyze task scope, dependencies, complexity, and risk, then choose and coordinate suitable agents.
Why use it?
It helps with tasks that span multiple areas or benefit from separate implementation, testing, and review work.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the devops plugin — 23 skills, 12 agents, 5 hooks, 3 MCP servers shipped together

not rated 5 +1 today B scan 111 tokens original MIT
View the source file Jerry0022/dotclaude
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 skills/jerry0022/dotclaude/run-agents
Any agent
npx skills add Jerry0022/dotclaude --skill run-agents
Clone the repo
git clone --depth 1 https://github.com/Jerry0022/dotclaude

Made for: Claude Code, Codex.

Or install devops, the plugin that ships this one along with the rest of its 23 skills, 12 agents, 5 hooks, 3 MCP servers.

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-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerry0022/dotclaude/run-agents.svg)](https://agentmods.dev/skills/jerry0022/dotclaude/run-agents)
Your own site
<a href="https://agentmods.dev/skills/jerry0022/dotclaude/run-agents"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/run-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,255 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00111 $0.02255
Opus 5 $0.00056 $0.01128
Sonnet 5 $0.00022 $0.00451
Haiku 4.5 $0.00011 $0.00226

Measured 5d ago against content hash d6267491844b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

run-agents scanned grade B with 1 finding 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

are NOT covered by the current `~/.claude/settings.json` allow-list. Prevents
plugins/devops/skills/run-agents/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Agents

Evaluate which agents add value for $ARGUMENTS, then orchestrate their execution.

Step 0 — Load Extensions

Check for optional overrides. Use Glob to verify each path exists before reading. Do NOT call Read on files that may not exist — skip missing files silently (no output).

  1. Global: ~/.claude/skills/run-agents/SKILL.md + reference.md
  2. Project: {project}/.claude/skills/run-agents/SKILL.md + reference.md
  3. Merge: project > global > plugin defaults

Step 1 — Task Analysis

Analyze $ARGUMENTS to understand:

  1. Domains touched — which areas of the codebase are affected?
  2. Complexity — single-domain vs. cross-cutting?
  3. Dependencies — what must happen before what?
  4. Risk level — does this need QA/PO review?

If $ARGUMENTS is empty or vague, ask ONE focused question via AskUserQuestion. Use the wording matching the active [ui-locale: ...] (defaults to en):

  • en: "What exactly should be orchestrated? (Feature, refactoring, bugfix, research...)"
  • de: "Was genau soll orchestriert werden? (Feature, Refactoring, Bugfix, Research...)"

Step 1.5 — Permission Audit

Before spawning agents, scan recent sessions for MCP tools that were used but are NOT covered by the current ~/.claude/settings.json allow-list. Prevents permission prompts from interrupting wave execution — especially painful with parallel agents.

node "$CLAUDE_PLUGIN_ROOT/scripts/permission-audit.js" --days=7 --quiet

Parse the JSON suggestions array:

  • Empty → skip silently, continue to Step 2.

  • Non-empty → present ALL suggestions in one AskUserQuestion multi-select. Never auto-apply — every rule needs user confirmation, to prevent log-forgery from seeding the allow-list. Each option = one suggested rule, labeled with its risk marker:

    • 🟢 low: user-installed plugin/runtime MCPs (mcp__plugin_*, mcp__ccd_*)
    • 🟡 medium: third-party / unknown MCPs — include the rationale text

    Pre-recommend the 🟢 ones in the description. Header: "Permissions", question: "Diese MCP-Tools wurden zuletzt genutzt aber sind nicht erlaubt. Welche zur Allow-Liste hinzufügen?"

Read the full file on GitHub · 210 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 210 lines · 111 tokens per session scan B d6267491844b

Subscribe to this mod's changes

run-agents is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 2,255 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens