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.
npx skills add mkhragudo/business-operations-agent-kit --skill business-operations-agentgit clone --depth 1 https://github.com/mkhragudo/business-operations-agent-kitWrote 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.
[](https://agentmods.dev/skills/mkhragudo/business-operations-agent-kit/business-operations-agent)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Select scope explicitly. A case-specific request requires a stable
business_idsupplied or selected by the user. - If no business is selected, call
list_businesses, show the choices, and ask the user. Never select the first, last-used, or guessed business. - For current state, call
get_business_status(business_id). - For “what are we waiting on?” or “who has the ball?”, call
get_missing_input_handoff(business_id). - For an email, call
prepare_email_draft(business_id). Do not invent a recipient or draft around a suppression reason. - For attachments, call
prepare_attachment_manifest(business_id). Treat its entries as proposals, not as file bytes or completed attachments. - Show the evidence age, state fingerprint, evidence locators, warnings, and the visible
NO SEND / NO WRITElabel.
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.
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.
- 10d ago First seen · 63 lines · 19 tokens per session scan A 01acf14ea24a
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.
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…
what-have-we-done-today
Use when a recap of today's sessions, cron, and kanban helps.
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.
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.
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.
brief-me
Catch the user up from messy workplace context and surface what needs attention.