m2ai-model-economics

Plugin m2ai-model-economics from marketplace m2ai-skills-pack in m2ai-portfolio/m2ai-skills-pack. Commands read from the repo's manifest — 2 days ago.

Skills (28)

• adversarial-dual-model-workflow

  Set up and run a two-AI coding workflow where a primary assistant handles planning and code generation while an adversarial auditor stress-tests the plan, catches edge cases, and reviews output before shipping. Use when the user wants complementary AI tool pairing, a structured code review gate, an

• agent-cost-model

  Model token costs and optimization opportunities for any agent workflow, producing per-task costs, monthly burn, and model-routing savings.

• agent-memory-architecture-matrix

  Interactive decision matrix that walks a builder through choosing between provider-hosted memory (fast, locked) and self-owned memory (portable, more maintenance), weighted to their actual constraints. Outputs an architectural decision record with rationale. Use when the user is designing an agent's

• ai-cost-exposure-audit

  Walk through a three-prompt sequential audit of your organization's AI inference cost-structure exposure -- inventory dependencies, stress-test sensitivity to subsidized-pricing collapse, and assess workload portability. Use when you want to map your exposure to the AI inference cost curve before it

• api-breaking-change-scanner

  Scans a codebase for deprecated API parameters and patterns that break silently or return 400 errors when migrating to a new model version, reporting exact file/line locations and migration actions.

• boot-tax-monitor

  Monitor and alert when Claude Code session startup overhead (plugins, skills, MCP servers, CLAUDE.md chain) exceeds a configurable token threshold. Prevents the silent context bloat that eats your working memory before you type a single prompt.

• compensating-complexity-auditor

  Audit system prompts and agent pipelines for compensating complexity — scaffolding, procedural hacks, and duct tape built around previous model limitations that should be tested for deletion before a model upgrade. Use when upgrading models, reviewing system prompts, or preparing for model migration

• compute-availability-tracker

  Poll the status pages of major AI providers (Anthropic, OpenAI, Google, OpenRouter) and produce a current availability table with routing recommendations. Use when a model call is failing, before routing important work, or on a schedule to detect degradation early.

• context-cost-line-item-analyzer

  Decompose an agent's token spend into context-as-input vs output-as-output, identify the specific context drivers (startup overhead, system prompt bloat, MCP tool registration, plugin chain, CLAUDE.md chain), and produce targeted reduction recommendations. Use when the user says "context cost breakd

• cross-model-peer-review

  Implements a cross-model peer review loop where Model A grades Model B's output on a structured rubric, catching errors that neither model's self-assessment reliably detects.

• cross-runtime-skill-converter

  Convert a Claude Code skill to Codex format or vice versa. Trigger on: "convert my skill to Codex", "port this skill to Claude Code", "make this skill work in both runtimes", "cross-runtime skill", "skill doesn't work in [provider]", "convert [skill-name] to Codex", "bring this Codex skill into Clau

• fair-agent-license-rubric

  Score an agent license or SaaS contract term sheet against a 9-trait rubric distinguishing fair agent licensing (transparent, capped, portable, identity-aware) from rent-seeking (opaque, uncapped, lock-in, double-billing). Outputs a numeric score, flagged red clauses, and a verdict.

• gemini-rescue

  Get a second opinion from Google Gemini on the current diff, plan, or problem. Use when Claude is stuck, when an implementation needs adversarial review by a different vendor, or when a 1M-context audit is needed that Claude can't fit. Trigger on "second opinion", "rescue with Gemini", "let Gemini r

• inference-layer-ownership-auditor

  Map your AI stack to identify who controls each inference layer -- model provider, hosting, hardware -- and score substitutability at each layer. Flags layers where you have no alternative if the current vendor's economics break. Use before a strategic AI vendor decision or during portability planni

• inference-vendor-lock-in-scorer

  Scan agent and skill manifests for AI vendor lock-in exposure -- hardcoded model names, non-portable API surfaces, absent fallback chains, opaque key management. Outputs a per-artifact lock-in score and a prioritized remediation queue. Use before a vendor migration or portability planning sprint.

• license-audit

  Takes a team's current AI tool inventory and work types, then outputs a one-page misfit memo identifying duplicative tools, underserved work classes, and wasted license spend. Interactive advisory skill for AI tool stack rationalization.

• mcp-portability-auditor

  Scan an agent stack (Claude Code plugins, Conway .cnw.zip files, Gemini extensions, ChatGPT GPTs) and flag which capabilities are locked to one platform vs portable via open MCP. Outputs a portability score per tool and a migration checklist. Use when the user asks to audit their agent extensions, s

• model-audit

  Scan a codebase for LLM model usage and recommend tier, task-fit, and cost optimizations. Works on any project using Anthropic, Google, OpenAI, or open-source models. Use to check whether each task is running on the right model tier, when a new model generation ships and you want to see if you can t

• model-migration-preflight

  Audit your prompts, system instructions, and Claude Code configuration before switching model versions. Flags deprecated API parameters, prompts that depend on implicit model inference, scaffolding code the new model handles natively, and estimates the tokenizer cost delta. Use before any model vers

• model-release-deep-dive

  Produce a structured capability-delta brief for any AI model release -- what actually changed beyond benchmark scores, what breaks, what improves, and what it means for current workflows. Triggered by a new model release or when benchmarks alone don't explain real-world behavior changes.

• model-router

  Routes a task to the right model tier (Fable/Opus/Sonnet/Haiku/Local-SLM) and dispatches it immediately: as a subagent for Anthropic tiers, or via a local OpenAI-compatible server (llama-server, vLLM, Ollama) for the L tier. Auto-classifies by reasoning complexity, agency needs, output length, and c

• platform-dependency-mapper

  Audit an org's or individual's AI stack and produce an exit-cost estimate across four axes — data, integrations, behavioral context, and billing. Outputs a ranked dependency map and a "what you'd lose if you left tomorrow" report. Use when the user asks to audit AI lock-in, map vendor dependencies,

• poly-skill

  Convert any Claude Code skill to work in OpenAI Codex (or vice versa) by applying a structural adapter that handles naming differences, sidecar YAML generation, trigger placement, tool-permission fields, and terminal-command syntax between the two platforms.

• pre-turn-budget-guardian

  Enforce a token budget ceiling on Claude Code sessions by checking projected usage BEFORE each turn and halting with a structured stop reason if the budget would be exceeded. Prevents runaway loops and silent token burn. Completes the token management trilogy alongside boot-tax-monitor (measures sta

• prompt-rewriter

  Rewrite system prompts to strip compensating complexity and produce clean outcome-based prompts. Takes audit output (from compensating-complexity-auditor or manual analysis) and produces a four-component prompt — outcome spec, constraints, tools, coordination pattern. Use when modernizing prompts af

• provider-availability-scout

  Scheduled task that probes model provider availability, pricing changes, restriction announcements, and API deprecations across configured providers (Anthropic, OpenAI, Google, OpenRouter, etc.). Diffs against last run and optionally updates a routing defaults file so your model routing layer stays

• renewal-interrogation

  Generate a vendor-specific SaaS renewal playbook for contracts where agent workloads are in scope. Input vendor name, current contract terms summary, planned agent usage, and negotiation priorities; output a sequenced interrogation playbook — opening anchors, mid-conversation probes, closing protect

• token-burn-auditor

  Audit the live Claude Code environment for token waste -- measures per-session overhead, flags system prompt bloat, checks plugin/skill loading totals, and gives before/after deltas when changes are made. Real-time linter for AI workflows.

Similar plugins