adaptive-quality

adaptive-quality is a skill for Claude Code, Codex from Insajin/autopus-adk. It costs 15 tokens per session (4,326 once invoked), scanned A, original, MIT.

A task-routing skill that chooses an execution profile based on task complexity when the workspace uses Balanced quality mode.

In plain words
What is it for?
Use it for per-task model or worker selection in Balanced mode, including setups where different providers have separate quality settings.
Why use it?
It keeps complex tasks on a stronger reasoning path while routine tasks use the standard path, without changing how Ultra or Solo mode works.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Codex.

Good fit Use it for per-task model or worker selection in Balanced mode, including setups where different providers have separate quality settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/insajin/autopus-adk/adaptive-quality
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 Insajin/autopus-adk --skill adaptive-quality
Clone the repo
git clone --depth 1 https://github.com/Insajin/autopus-adk

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 adaptive-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/insajin/autopus-adk/adaptive-quality/github.svg)](https://agentmods.dev/skills/insajin/autopus-adk/adaptive-quality)
Your own site
<a href="https://agentmods.dev/skills/insajin/autopus-adk/adaptive-quality"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/adaptive-quality/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-quality

Your own site · 80×15
<a href="https://agentmods.dev/skills/insajin/autopus-adk/adaptive-quality"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/adaptive-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,326 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 pass 7 Sept 2026
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 $0.00015 $0.04326
Opus 5 $0.00008 $0.02163
Sonnet 5 $0.00003 $0.00865
Haiku 4.5 $0.00002 $0.00433

Measured 11d ago against content hash d0051b7e4dd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

adaptive-quality 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.

.omp/skills/adaptive-quality/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adaptive Quality Skill

Overview

Adaptive Quality is a sub-extension of Quality Mode. In Balanced mode only, task complexity determines the execution profile used for each task batch call. High-complexity tasks still receive the strongest reasoning path, while routine tasks stay on the standard path. In this workspace, OMP no longer falls back to haiku; OMP maps managed workers to Sol/Terra/Luna, while new projects leave the primary session on the user's model unless supervisor_model_policy: quality is selected; OMP keeps its configured default model.

Relationship to Quality Mode

Mode Behavior
Ultra ALL tasks use the premium execution path. Complexity is IGNORED.
Balanced Complexity determines the execution profile. Adaptive Quality applies.
Solo No task batch items. Not applicable.

Adaptive Quality is not a replacement for Quality Mode — it is a refinement that operates exclusively within Balanced mode.

Provider-specific mode selection

Mixed OMP and OMP projects can select Ultra or Balanced independently while retaining the existing global fallback:

quality:
  default: balanced
  providers:
    claude: ultra
    codex: balanced

Resolve the effective mode in this order: explicit per-run global --quality, persisted quality.providers.<claude|codex>, persisted quality.default, then balanced. The global per-run flag intentionally overrides both providers without rewriting YAML.

auto quality provider claude ultra --apply
auto quality provider codex balanced --apply
auto quality provider claude inherit --apply

claude-code is accepted as a CLI alias for canonical provider key claude. Provider-specific --apply refreshes only that configured platform; auto quality <mode> --apply continues to refresh every configured platform.

Complexity Assessment Criteria

The planner assesses each task before spawning an agent. The assessment considers:

Factor Weight
file_count Number of files to be modified
estimated_lines Expected lines of new/changed code
requirement_count Number of distinct requirements
dependency_count Number of packages/modules involved

Read the full file on GitHub · 387 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. 11d ago First seen · 387 lines · 15 tokens per session scan A d0051b7e4dd6

Subscribe to this mod's changes

adaptive-quality is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 4,326 once invoked, about $0.0001 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.