business-operations-agent

business-operations-agent is a skill for Claude Code, Codex from mkhragudo/business-operations-agent-kit. It costs 19 tokens per session (606 once invoked), scanned A, original, Apache-2.0.

A set of procedures for handling business status updates, handoffs, email drafts, and attachment proposals using sourced information. It requires selecting the correct business and showing the evidence behind each result.

In plain words
What is it for?
Use it to check a business's current status, identify missing information and ownership, prepare an email draft, or propose an attachment list.
Why use it?
It helps prevent updates, emails, and attachment lists from being based on the wrong business or on missing or outdated information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to check a business's current status, identify missing information and ownership, prepare an email draft, or propose an attachment list.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mkhragudo/business-operations-agent-kit/business-operations-agent
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.

Any agent
npx skills add mkhragudo/business-operations-agent-kit --skill business-operations-agent
Clone the repo
git clone --depth 1 https://github.com/mkhragudo/business-operations-agent-kit

Made for: Claude Code, Codex.

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 business-operations-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/mkhragudo/business-operations-agent-kit/business-operations-agent/github.svg)](https://agentmods.dev/skills/mkhragudo/business-operations-agent-kit/business-operations-agent)
Your own site
<a href="https://agentmods.dev/skills/mkhragudo/business-operations-agent-kit/business-operations-agent"><img src="https://agentmods.dev/badge/skills/mkhragudo/business-operations-agent-kit/business-operations-agent/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 business-operations-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/mkhragudo/business-operations-agent-kit/business-operations-agent"><img src="https://agentmods.dev/badge/skills/mkhragudo/business-operations-agent-kit/business-operations-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 606 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 $0.00019 $0.00606
Opus 5 $0.00010 $0.00303
Sonnet 5 $0.00004 $0.00121
Haiku 4.5 $0.00002 $0.00061

Measured 10d ago against content hash 01acf14ea24a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

business-operations-agent 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.

skillsets/business-operations-agent/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Business Operations Agent

Use this skill when a business owner asks for operational status, what changed, who owns the next move, what is missing, a next-email draft, or an attachment packet proposal.

Required sequence

  1. Select scope explicitly. A case-specific request requires a stable business_id supplied or selected by the user.
  2. If no business is selected, call list_businesses, show the choices, and ask the user. Never select the first, last-used, or guessed business.
  3. For current state, call get_business_status(business_id).
  4. For “what are we waiting on?” or “who has the ball?”, call get_missing_input_handoff(business_id).
  5. For an email, call prepare_email_draft(business_id). Do not invent a recipient or draft around a suppression reason.
  6. For attachments, call prepare_attachment_manifest(business_id). Treat its entries as proposals, not as file bytes or completed attachments.
  7. Show the evidence age, state fingerprint, evidence locators, warnings, and the visible NO SEND / NO WRITE label.

Evidence rules

  • Use the tool result as the bounded evidence envelope.
  • Distinguish dashboard/process truth from communication evidence.
  • If the sources conflict, say they conflict and identify the internal reconciliation owner. Do not ask an external party to resend an item that communication evidence says arrived.
  • Call an input missing only when open work requires it and no usable current document satisfies it.
  • Do not infer facts from absent records, mailbox silence, or model memory.

Privacy rules

Do not request or expose:

  • raw message subjects, sender addresses, or bodies;
  • raw task notes;
  • content digests;
  • attachment paths, filenames, or bytes;
  • credentials or connector configuration;
  • records for a different business.

Use opaque evidence locators when explaining the basis for a conclusion.

Action boundary

This skill is Levels 0-1 only:

  • allowed: inspect, explain, reconcile, draft in memory, propose attachment metadata;
  • not allowed: create a provider email draft, write a database record, generate a real document, send a message, or modify a source system.

Read the full file on GitHub · 63 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 · 63 lines · 19 tokens per session scan A 01acf14ea24a

Subscribe to this mod's changes

business-operations-agent is a skill published in the GitHub repository mkhragudo/business-operations-agent-kit (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 606 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.

Related

Other skills, from other repositories

kill-the-standup

Reads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done / doing / blockers), and posts it to Slack. Use when asked to write a standup, generate a standup update, post to the standup channel, summarize yesterday's work, or automate the daily standup. Trigger when a…

Varnan-Tech/opendirectory · 108 tokens

what-have-we-done-today

Use when a recap of today's sessions, cron, and kanban helps.

asimons81/hermes-field-kit · 23 tokens

taskflow-inbox-triage

Example TaskFlow authoring pattern for inbox triage. Use when messages need different treatment based on intent, with some routes notifying immediately, some waiting on outside answers, and others rolling into a later summary.

spinabot/brigade · 49 tokens

things-mac

Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

the-open-agent/openagent · 69 tokens

钉钉企业 IM 操作

A command reference for using DingTalk, a workplace messaging and collaboration platform, through its command-line tool. It covers messages, calendars, documents, cloud files, contacts, tasks, and attendance data.

CavinHuang/lume · 46 tokens

brief-me

Catch the user up from messy workplace context and surface what needs attention.

tmusser/context-to-action-skills · 17 tokens