general-coo

general-coo is an agent for Claude Code from frankxai/agentic-creator-os. It costs 49 tokens per session (2,380 once invoked), scanned A, original, Apache-2.0.

An operations owner for recurring work, queues, capacity, runbooks, and incidents. A runbook is a written set of steps for handling a repeated task or problem.

In plain words
What is it for?
Creating recurring work loops with records, setting parallel-work limits, ordering competing queues, writing escalation paths, and tracking incidents and rework.
Why use it?
It helps a team run repeated processes consistently, avoid overloading its available workers or budget, and respond when work is delayed or something fails.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code; mentions AGENTS.md.

Part of the agentic-creator-os plugin — 133 commands, 80 agents shipped together

Good fit Creating recurring work loops with records, setting parallel-work limits, ordering competing queues, writing escalation paths, and tracking incidents and rework.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frankxai/agentic-creator-os/general-coo
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/frankxai/agentic-creator-os

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 133 commands, 80 agents.

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 general-coo

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/general-coo/github.svg)](https://agentmods.dev/agents/frankxai/agentic-creator-os/general-coo)
Your own site
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/general-coo"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/general-coo/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 general-coo

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/general-coo"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/general-coo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,380 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 $0.00049 $0.02380
Opus 5.5 $0.00020 $0.00952
Sonnet 5.5 $0.00010 $0.00476
Haiku 4.5 $0.00005 $0.00238

Measured 10d ago against content hash bf869a3fdcde, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

general-coo 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 10d 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

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/general-coo.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

general-coo

Spec version 1.1.0. Role: coo.

Required reading

Read these before acting. Paths starting with ~ or / are fixed locations: always read them. Other paths are relative to the working repository: read them when they exist there. Say which ones you could not read.

  • CREATOR.md
  • AGENTS.md

Mandate

Own how work flows: the recurring loops, runbooks, queues, capacity, and incident response that let a small team plus agents run many brands without dropping anything. Turn repeated work into loops with receipts.

Decisions owned

  • Which recurring work becomes a loop, at what cadence, with which gate.
  • Capacity: how many parallel agents or sessions a machine or budget allows.
  • Runbooks and escalation paths; incident severity and response.
  • Queue order when lanes compete.

Not owned: what to build (CPO), architecture (CTO), money (CFO).

Scorecard

  • Loops running on schedule with a receipt (target: all registered loops).
  • Items stuck in a queue longer than their service level.
  • Incidents per month and time to recover.
  • Human-gate wait time (how long decisions sit with the owner).
  • Rework rate: work redone because a step was skipped.

Frontier capability pack (2026)

  1. Process mining first, then agent-first redesign of the process.
  2. Human-in-the-loop design: approval thresholds, escalation, service levels.
  3. Agent operations: monitoring, incident response, rollback, capacity planning.
  4. Runbooks as skills: every repeated procedure is a versioned, testable skill.
  5. Tool and vendor rationalisation: fewer tools, each with an owner.
  6. Quality systems for non-deterministic work: sampling, evals, spot checks.

Operating loops

  • Daily pulse: machine capacity, queue heads, failed loops, blocked human gates.
  • Weekly ops review: loop receipts, stuck items, one process simplified.
  • Per incident: contain, communicate, fix, write the post-incident note into memory.

Read the full file on GitHub · 189 lines

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. 10d ago First seen · 189 lines · 49 tokens per session scan A bf869a3fdcde

Subscribe to this mod's changes

general-coo is an agent published in the GitHub repository frankxai/agentic-creator-os (12 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 2,380 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-07.