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 AnkitClassicVision/agent-automation-creator --skill agenttwingit clone --depth 1 https://github.com/AnkitClassicVision/agent-automation-creatorWrote 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/ankitclassicvision/agent-automation-creator/agenttwin)<a href="https://agentmods.dev/skills/ankitclassicvision/agent-automation-creator/agenttwin"><img src="https://agentmods.dev/badge/skills/ankitclassicvision/agent-automation-creator/agenttwin/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/ankitclassicvision/agent-automation-creator/agenttwin"><img src="https://agentmods.dev/badge/skills/ankitclassicvision/agent-automation-creator/agenttwin.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 | $0.00246 | $0.03379 |
| Opus 5 | $0.00123 | $0.01690 |
| Sonnet 5 | $0.00049 | $0.00676 |
| Haiku 4.5 | $0.00025 | $0.00338 |
Grade A, and why
agenttwin 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 9d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentTwin
A diagnostic instrument for AI agent workflows. Locked at v1, May 2026. Built on AAC 2.0 (Agent Automation Creator, MyBCAT operating package, released 2026-06-05) with the v1.1 core rubric retained as the readiness reference. Produces a standalone HTML report that works without any external dependencies.
When to fire this skill
Fire when the user is doing any of these on an AI agent, automation, or agentic workflow:
- Designing — drafting a new agent, planning an automation, scoping a workflow
- Evaluating — auditing an existing agent, reviewing a vendor pitch, scoring a build
- Modifying — changing prompts, models, gates, or any agent component
- Diagnosing — investigating drift, hallucination, cost spike, missed escalation
- Accepting — reviewing a builder/vendor/internal-team deliverable as ready
- Onboarding — giving a new AI engineer / fractional TPL day-one context
Do NOT fire for:
- Generic AI questions not tied to a workflow ("how does Claude work?")
- Personal AI use ("draft me an email")
- Strategy/business questions not involving workflow design
- Pure code bugs unrelated to AI workflow elements
When in doubt, fire. A redundant retrieval is one OB query; a missed AgentTwin run means a workflow ships without governance.
What you produce
A single HTML file named agenttwin-{slug}-{date}.html saved to /mnt/user-data/outputs/ and presented to the user via present_files. The HTML is fully self-contained — embedded CSS, embedded fonts via Google Fonts CDN, no build step, opens in any browser, screenshots cleanly for decks.
The report has two tabs:
- Summary — 5th-grader-readable wellness report
- Letter grade (A/B/C/D/F) in a colored circle
- 5 property cards (Stays in lane, Checks facts, Checks before doing, Nothing is hidden, Has a stop button) with status + plain-English description + (if broken) problem + fix
- Before/After toggle showing the "twin" (current state vs ideal state)
- 3-item Action Plan for non-technical readers
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 224 lines · 246 tokens per session scan A a0968fd7e25c
agenttwin is a skill published in the GitHub repository AnkitClassicVision/agent-automation-creator (21 stars, last pushed 2mo ago), licensed MIT. It adds 246 tokens to every session and 3,379 once invoked, about $0.0012 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 2026-08-30.
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…