run-operator

run-operator is an agent for Claude Code from hoangsonww/Claude-Code-Agent-Monitor. It costs 18 tokens per session (126 once invoked), scanned A, original, MIT.

An agent skill for safely operating Claude Code and Codex processes through the Claude Code Agent Monitor.

In plain words
What is it for?
Use it to inspect options, prepare a launch, send follow-ups, stop runs, or resume sessions with explicit settings.
Why use it?
It checks available programs, models, folders, and existing runs before proposing an action, reducing accidental launches or unsafe settings.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code; mentions Codex.

Part of the ccam-runner plugin — 2 skills, 1 command, 1 agent shipped together

Good fit Use it to inspect options, prepare a launch, send follow-ups, stop runs, or resume sessions with explicit settings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hoangsonww/claude-code-agent-monitor/run-operator
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/hoangsonww/Claude-Code-Agent-Monitor

Made for: Claude Code.

Or install ccam-runner, the plugin that ships this one along with the rest of its 2 skills, 1 command, 1 agent.

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-operator

README.md
[![agentmods](https://agentmods.dev/badge/agents/hoangsonww/claude-code-agent-monitor/run-operator/github.svg)](https://agentmods.dev/agents/hoangsonww/claude-code-agent-monitor/run-operator)
Your own site
<a href="https://agentmods.dev/agents/hoangsonww/claude-code-agent-monitor/run-operator"><img src="https://agentmods.dev/badge/agents/hoangsonww/claude-code-agent-monitor/run-operator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for run-operator

Your own site · 80×15
<a href="https://agentmods.dev/agents/hoangsonww/claude-code-agent-monitor/run-operator"><img src="https://agentmods.dev/badge/agents/hoangsonww/claude-code-agent-monitor/run-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 126 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00126
Opus 5 $0.00009 $0.00063
Sonnet 5 $0.00004 $0.00025
Haiku 4.5 $0.00002 $0.00013

Measured 7d ago against content hash 9078c19fb02b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

run-operator 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.

plugins/ccam-runner/agents/run-operator.md · 17 lines

What it actually says

Run Operator

Operate the ccam run command surface. Inspect binaries, models, working directories, and existing handles before proposing a launch. Always show the exact provider, model, approval policy, sandbox, working directory, and prompt before any start, message, or stop action. Default Codex to on-request and workspace-write. Never use danger-full-access without explicit user intent.

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. 7d ago First seen · 17 lines · 18 tokens per session scan A 9078c19fb02b

Subscribe to this mod's changes

run-operator is an agent published in the GitHub repository hoangsonww/Claude-Code-Agent-Monitor (989 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 126 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 2026-09-03.

Related

Other agents, from other repositories

support-assistant

Use when: handling helpdesk tickets, technical support, or customer service conversations. Do NOT use for: internal system changes, refund approvals, or formal-complaint handling (escalate to the relevant team instead).

fusengine/agents · 48 tokens

radin-execute-background

Work through the project's backlog in its own agent thread, so the calling session stays free. Dispatch it and then say nothing further about it: it reports to the user in its own transcript, never back to you. Use when the user asks for the backlog run to happen in the background or out of the way.

shortcuts/radin · 69 tokens

react-expert

Use when: package.json has React but NO next.config., Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use design-expert), Laravel+Inertia (use laravel-expert).

fusengine/agents · 60 tokens

jira-estimator

Heuristic story-point estimation for a single Jira ticket via the jira-as CLI wrapper. Read-only. Routed by mk:jira-estimator skill. NOT for complexity/inconsistency analysis (jira-evaluator); NOT for full RCA (jira-analyst).

ngocsangyem/MeowKit · 55 tokens

jira-jsm

Execute JIRA Service Management operations via the jira-as CLI wrapper: service desks, request types, requests, customers, organizations, queues, SLAs, approvals (8 sub-domains, 45 verbs total). Routed by mk:jira-jsm skill. Requires JSM-licensed tenant + agent or admin role. NOT for core Jira issue ops (jira-issue)…

ngocsangyem/MeowKit · 86 tokens

modifier-agent

Use this agent when quick, mechanical edits are needed across multiple files in the repository or /.claude/ folder — spelling corrections, minor reformatting, updating references after renames, reflecting small structural changes across documentation, version number updates, or simple find-and-replace changes. Handles…

isvlasov/rageatc-oss · 76 tokens