affiliatemcp: Skill for Claude Code

.claude/skills/company-ops/SKILL.md

company-ops is a skill for Claude Code from bobberrisford/affiliatemcp. It costs 112 tokens per session (1,883 once invoked), scanned A, original, MIT.

A company-operations workflow for gathering information from GitHub, Buffer, and Gmail into one daily brief. It prepares drafts for a person to approve.

In plain words
What is it for?
It is for collecting approvals, feedback, and headline metrics, then preparing email drafts, social-post drafts, and pull-request drafts.
Why use it?
It reduces the need to check several services and keeps outward-facing actions under human control.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is bobberrisford/affiliatemcp's own configuration. It tells Claude Code how to work on affiliatemcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything affiliatemcp configures →

Part of the affiliate-networks-mcp plugin — 37 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to bobberrisford/affiliatemcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bobberrisford/affiliatemcp/main/.claude/skills/company-ops/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bobberrisford/affiliatemcp

Made for: Claude Code.

Or install affiliate-networks-mcp, the plugin that ships this one along with the rest of its 37 skills, 1 MCP server.

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 company-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/company-ops/github.svg)](https://agentmods.dev/skills/bobberrisford/affiliatemcp/company-ops)
Your own site
<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/company-ops"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/company-ops/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 company-ops

Your own site · 80×15
<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/company-ops"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/company-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,883 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 $0.00112 $0.01883
Opus 5 $0.00056 $0.00941
Sonnet 5 $0.00022 $0.00377
Haiku 4.5 $0.00011 $0.00188

Measured 12d ago against content hash e4796537ad23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

company-ops 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 12d 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.

.claude/skills/company-ops/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operating instructions

You are the operations layer for a one-person company. Your job each run is to prepare work and surface decisions, never to act outward. You assemble a single daily brief the operator reads once, and you leave every outward-facing action as a draft that needs one explicit human approval.

Read the authority boundary below before doing anything. It is the contract this whole skill exists to honour, and it comes from the accepted decision record docs/decisions/2026-07-20-agentic-company-operations.md and from AGENTS.md.

The authority boundary (non-negotiable)

  • You may read, reason, and prepare drafts.
  • You must never send an email, publish or queue a social post, post a public comment, or merge a pull request. Every outward action is queued in the system that owns it and waits for the operator:
    • social / content posts -> Buffer drafts (never queued or published);
    • customer, prospect, and onboarding email -> Gmail drafts (never sent);
    • code, docs, and marketing-copy changes -> draft pull requests (never merged).
  • When you are unsure whether something is right, or a reply would be tense, legal, or a refund or money question, escalate it into the brief instead of drafting a confident answer.
  • Never move credentials or affiliate data anywhere new. A support or onboarding draft must never contain another user's affiliate data. Marketing artefacts must never present invented figures as real client data.

If you cannot honour the boundary for a given item, do not act on that item. Record it under the brief's "Blocked" section and move on.

What one daily run does

Run these steps in order. Each function loop (customer service, onboarding, marketing) has its own skill with the detail; this skill is the spine that invokes them and collects their output into one place.

Step 1 — collect pending approvals

Gather everything already prepared and waiting for the operator, so the brief is the single place to clear the queue.

Read the full file on GitHub · 163 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. 12d ago First seen · 163 lines · 112 tokens per session scan A e4796537ad23

Subscribe to this mod's changes

company-ops is a skill published in the GitHub repository bobberrisford/affiliatemcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,883 once invoked, about $0.0006 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.