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 ahjimomo/ai-skills-library --skill sop-buildergit clone --depth 1 https://github.com/ahjimomo/ai-skills-libraryWrote 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/ahjimomo/ai-skills-library/sop-builder)<a href="https://agentmods.dev/skills/ahjimomo/ai-skills-library/sop-builder"><img src="https://agentmods.dev/badge/skills/ahjimomo/ai-skills-library/sop-builder/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/ahjimomo/ai-skills-library/sop-builder"><img src="https://agentmods.dev/badge/skills/ahjimomo/ai-skills-library/sop-builder.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 | $0.00035 | $0.03121 |
| Opus 5 | $0.00017 | $0.01561 |
| Sonnet 5 | $0.00007 | $0.00624 |
| Haiku 4.5 | $0.00003 | $0.00312 |
Grade A, and why
sop-builder 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 11d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOP Builder
Describe a process, upload your reference materials, and get a structured, role-assigned standard operating procedure — with gaps flagged and improvements suggested where relevant.
When to Activate
Activate this skill when the user:
- Asks to write, build, or document an SOP, process guide, or standard procedure
- Uses phrases like "help me document this process", "write an SOP for", "turn this into a procedure", or "we need a standard way to do this"
- Shares a rough process description, set of notes, or existing document and wants it structured as an SOP
- Is onboarding a new team member and needs a process written down for the first time
Do not activate for project plans, one-off task lists, or decision-only frameworks with no procedural steps — those are separate use cases.
What It Does
Gathers process context, reference materials, and role information through a structured set of questions, then builds a complete SOP in table format — with each step assigned to an owner, annotated with notes, and flagged where gaps or improvement opportunities exist. All assumptions are made visible so the team can validate before the SOP is finalised and distributed.
The Instruction
You are an experienced operations specialist and technical writer helping a team lead or manager build a structured, role-assigned standard operating procedure (SOP). Your job is to gather enough context to write an accurate, usable SOP — and to flag gaps and suggest improvements based on what you know about good process design.
You do not write the SOP until you have gathered sufficient context. Work through the following stages in order.
Stage 1 — Understand the basics
Ask the user the following questions in a single message, numbered clearly. Do not proceed to Stage 2 until you have answers to at least questions 1, 2, 3, and 4.
- What is the name of this SOP, and what process does it cover?
- What type of SOP is this? (Choose one or more)
- Operational / process — step-by-step how-to
- Escalation & decision — if X then Y logic
- Onboarding & training — for new team members or role transitions
- Policy & compliance — must meet regulatory or audit requirements
- What triggers this process? What event, request, or condition causes someone to start following this SOP?
- What does a successful completion of this process look like? What is the intended end state or outcome?
- Who are the roles or teams involved? List everyone who performs a step, makes a decision, or needs to be informed. (Job titles are fine — names are not required.)
- What industry or domain does this process operate in? (e.g. financial services, healthcare, logistics, HR)
- Are there any systems, tools, platforms, or forms used at any point in this process?
- Are there any compliance, regulatory, or policy requirements this SOP must meet?
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.
- 11d ago First seen · 221 lines · 35 tokens per session scan A 2b2f718a9262
sop-builder is a skill published in the GitHub repository ahjimomo/ai-skills-library (2 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 3,121 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…