agenttwin

agenttwin is a skill for Claude Code, Codex from AnkitClassicVision/ankit_shared_skills. It costs 44 tokens per session (661 once invoked), scanned A, original, MIT.

A diagnostic and reporting tool for AI agents and automated workflows. It produces a plain-language readiness report and a map comparing the current process with an intended one.

In plain words
What is it for?
Use it when designing, reviewing, changing, or accepting an AI agent or automation, and when investigating hallucinations, cost increases, missed escalations, or silent failures.
Why use it?
It helps reveal weak checks, hidden steps, scope drift, unhandled failures, and missing ways to stop or escalate an automated process.

Skill for Claude CodeCodex

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

Good fit Use it when designing, reviewing, changing, or accepting an AI agent or automation, and when investigating hallucinations, cost increases, missed escalations, or silent failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ankitclassicvision/ankit_shared_skills/agenttwin
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 AnkitClassicVision/ankit_shared_skills --skill agenttwin
Clone the repo
git clone --depth 1 https://github.com/AnkitClassicVision/ankit_shared_skills

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 agenttwin

README.md
[![agentmods](https://agentmods.dev/badge/skills/ankitclassicvision/ankit_shared_skills/agenttwin.svg)](https://agentmods.dev/skills/ankitclassicvision/ankit_shared_skills/agenttwin)
Your own site
<a href="https://agentmods.dev/skills/ankitclassicvision/ankit_shared_skills/agenttwin"><img src="https://agentmods.dev/badge/skills/ankitclassicvision/ankit_shared_skills/agenttwin.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 661 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 $0.00044 $0.00661
Opus 5 $0.00022 $0.00331
Sonnet 5 $0.00009 $0.00132
Haiku 4.5 $0.00004 $0.00066

Measured 8d ago against content hash 2a17f9e76749, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 8d 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.

agenttwin/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentTwin, public version

AgentTwin is a lightweight diagnostic instrument for AI agent workflows. It produces a plain-English wellness report plus an operator-grade process map.

This public copy intentionally omits private rubrics, private examples, internal customer references, and organization-specific capture rules.

When to use

Use when the user is doing any of these on an AI agent, automation, or agentic workflow:

  • Designing a new agent or automation
  • Evaluating an existing agent or vendor proposal
  • Modifying prompts, models, gates, or workflow components
  • Diagnosing drift, hallucination, cost spike, missed escalation, or silent failure
  • Accepting a build as ready for broader use
  • Onboarding an engineer or operator to an agentic workflow

Do not use for generic AI questions, personal drafting, or pure code bugs unrelated to agent/workflow behavior.

Report shape

Produce a self-contained markdown or HTML report with two views:

  1. Summary view

    • Overall grade: A, B, C, D, or F
    • Five property cards in plain English:
      • Stays in lane
      • Checks facts
      • Checks before doing
      • Nothing is hidden
      • Has a stop button
    • Current vs ideal flow
    • Three-item action plan
  2. Process map view

    • Nodes with runtime type, owner, input, output, status, and failure mode
    • Edges with trigger, contract, latency expectation, retry behavior, and audit trail
    • Cross-cutting state, memory, observability, and override model
    • Ranked recommendations by severity

Five closed-loop properties

  • Bounded: the workflow has a clear box, allowed actions, refused actions, and stop condition.
  • Grounded: important claims and decisions cite source evidence that can be rechecked.
  • Gated: risky writes, sends, labels, money movement, compliance actions, and human-impacting outputs require approval or deterministic checks.
  • Observed: runs leave useful traces, metrics, alerts, and replayable proof.
  • Governed: an owner can pause, override, audit, improve, and retire the workflow.

Read the full file on GitHub · 74 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. 8d ago First seen · 74 lines · 44 tokens per session scan A 2a17f9e76749

Subscribe to this mod's changes

agenttwin is a skill published in the GitHub repository AnkitClassicVision/ankit_shared_skills (11 stars, last pushed 27d ago), licensed MIT. It adds 44 tokens to every session and 661 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens