adaptive-model-routing

adaptive-model-routing is a skill for Claude Code from jeet129/praxis. It costs 132 tokens per session (4,055 once invoked), scanned A, original, MIT.

A routing guide that chooses a high, medium, or low reasoning level for each agent task based on its complexity, novelty, risk, and dependencies.

In plain words
What is it for?
Use it before launching specialist agents or entering workflow phases to select reasoning effort, explain the choice, recommend escalation, and record routing decisions.
Why use it?
It avoids spending the most computation on routine work while recommending a higher level when a task is difficult or an earlier attempt failed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Part of the praxis plugin — 105 skills, 12 commands, 17 agents, 6 hooks shipped together

Good fit Use it before launching specialist agents or entering workflow phases to select reasoning effort, explain the choice, recommend escalation, and record routing decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeet129/praxis/adaptive-model-routing
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 jeet129/praxis --skill adaptive-model-routing
Clone the repo
git clone --depth 1 https://github.com/jeet129/praxis

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 105 skills, 12 commands, 17 agents, 6 hooks.

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 adaptive-model-routing

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeet129/praxis/adaptive-model-routing/github.svg)](https://agentmods.dev/skills/jeet129/praxis/adaptive-model-routing)
Your own site
<a href="https://agentmods.dev/skills/jeet129/praxis/adaptive-model-routing"><img src="https://agentmods.dev/badge/skills/jeet129/praxis/adaptive-model-routing/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 adaptive-model-routing

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeet129/praxis/adaptive-model-routing"><img src="https://agentmods.dev/badge/skills/jeet129/praxis/adaptive-model-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,055 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 301
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 303
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 310
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 311
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00132 $0.04055
Opus 5 $0.00066 $0.02027
Sonnet 5 $0.00026 $0.00811
Haiku 4.5 $0.00013 $0.00405

Measured 9d ago against content hash 87c65a8cffd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adaptive-model-routing 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.

codex-plugin-assets/skills/adaptive-model-routing/SKILL.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adaptive Model Routing (Codex variant)

capability: foundation
domain: cross-cutting
state: active
dependencies:
  - using-praxis
  - llm-cost-optimization
  - agentic-architecture
triggers:
  - "about to launch a specialist Codex session — which reasoning effort should it use?"
  - "starting a new session — which model_reasoning_effort should I launch on?"
  - "prior attempt failed — should I escalate the reasoning tier?"
  - "deciding whether this task needs high reasoning or medium is enough"
  - "API spend running high — can I safely use medium reasoning here?"
  - "complex architecture decision coming — what reasoning tier?"
  - "entering a new workflow phase — should the reasoning tier change?"
outputs:
  - reasoning-effort selection (per session or specialist launch)
  - complexity score + rationale
  - escalation recommendation (when prior attempt fails)
  - routing log entry at .project/telemetry/model-routing.jsonl
consumers:
  - delivery-lead (primary — runs this SKILL before every specialist launch)
  - using-praxis (consumes routing decision when selecting reasoning effort for orchestration)
  - agentic-architecture (session-as-agent configuration)
references:
  - llm-cost-optimization.md
  - routing-examples.md

The Codex variant of adaptive-model-routing. Same underlying routing rubric as the Claude Code version; adapted to Codex CLI's model_reasoning_effort parameter and session-as-agent spawn pattern.

What differs from the Claude Code variant

Codex resolves tiers via model_reasoning_effort in codex-agents/*.toml (high / medium / low) on typically one base model; agents run as launched CLI sessions (no mid-session model switch — relaunch with the new config), and cost is per-token API spend rather than plan quota. Everything else — the 5-signal rubric, fast-path rules, phase defaults, per-agent assignments, escalation protocol — is identical model-agnostic discipline shared with every harness.

Read the full file on GitHub · 314 lines

Files

What ships with it

1 file 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.

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. 9d ago First seen · 314 lines · 132 tokens per session scan A 87c65a8cffd4

Subscribe to this mod's changes

adaptive-model-routing is a skill published in the GitHub repository jeet129/praxis (7 stars, last pushed 5d ago), licensed MIT. It adds 132 tokens to every session and 4,055 once invoked, about $0.0007 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.

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

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…

vercel/next.js · 83 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