test-time-compute-optimizer SKILL.md skillA

test-time-compute-optimizer from roedyrustam/vibes-plug is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add roedyrustam/vibes-plug/test-time-compute-optimizer@v4.2.0

Pins v4.2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
roedyrustam/vibes-plug
Path
skills/test-time-compute-optimizer/SKILL.md
Versions recorded
2
Latest version
v4.2.0, committed Oct 3, 2026
First version recorded
Oct 3, 2026
Size
12,100 bytes
Repository stars
122
License
MIT

Expert guide for scaling test-time compute, dynamic reasoning token allocation (Gemini 4 Pro, Claude 5.5, GPT Astra 6), Monte Carlo Tree Search (MCTS), and Process Reward Models / Panduan ahli penskalaan komputasi waktu uji (test-time compute), alokasi dinamis budget penalaran, MCTS, dan Process Reward Models.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# test-time-compute-optimizer — vibes-plug Skill

[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)

---

<a name="english"></a>
## English

### Orchestration & Integration
Connects and orchestrates with `brainstorming`, `zero-to-prod-orchestrator`, `ai-llm-integration-expert`, `frontier-ai-models-expert`, `llm-finops-router`, and `speculative-multi-draft-synthesizer` to dynamically balance reasoning depth, inference latency, and token expenditures across frontier models.

### Description
Production guide for scaling test-time compute (inference-time reasoning) across frontier AI models including Google Gemini 4 Pro, Anthropic Claude 5.5 (Opus/Sonnet), and OpenAI GPT Astra 6 (`o6`). Provides concrete architectures for dynamic thinking budget allocation, tree-search exploration (MCTS, beam search), step-level Process Reward Model (PRM) verification, and self-consistency consensus loops.

### Trigger Conditions
Activate this skill when:
- Designing systems that tackle hard algorithmic, formal verification, or multi-step architectural problems.
- Configuring model reasoning parameters (`thinkingBudget`, `budget_tokens`, `reasoning_effort`).
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add roedyrustam/vibes-plug/test-time-compute-optimizer@sha256:ca9c7a83a59b3cc1

The line at the top of this page pins the label v4.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_n2y7kohtjbtgu4gs.svg)](https://markdownregistry.com/a/art_n2y7kohtjbtgu4gs)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, all committed on Oct 3, 2026.

versioncommittedcommitsizeaudit
v4.2.0 latest2026-10-03 d8cca2a 12,100 BA view · diff
v4.1.02026-10-03 47606ed 12,100 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12100 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

roedyrustam/vibes-plug · 122 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_n2y7kohtjbtgu4gs
GET https://markdownregistry.com/api/v1/resolve?ref=roedyrustam/vibes-plug/test-time-compute-optimizer
GET https://markdownregistry.com/api/v1/blob/ca9c7a83a59b3cc10ba89bfe3a2af3b9e1a6fbb7c732d3e33c2a3348eaa0e561

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from roedyrustam/vibes-plug

vibes-plug-anti-slop Cursor rule
roedyrustam/vibes-plug · .cursor/rules/vibes-plug-anti-slop.mdc · Sovereign Anti-Slop Directive for Cursor AI — Absolute zero-tolerance for lazy placeholders, truncated code, syntax…
git:20261020.73c5751 · audit A · 122 stars
vibes-plug-core Cursor rule
roedyrustam/vibes-plug · .cursor/rules/vibes-plug-core.mdc · Vibes-Plug 147-Skill AI Agent Swarm Architecture — Universal AI plugin for modern 2026 development
git:20261008.97b4c97 · audit A · 122 stars
vibes-plug-mcp Cursor rule
roedyrustam/vibes-plug · .cursor/rules/vibes-plug-mcp.mdc · Vibes-Plug & XERJ MCP Tools Guide — How Cursor AI leverages local MCP servers for AST analysis, SQL evaluation, code…
git:20261020.73c5751 · audit A · 122 stars
vibes-plug-skills Cursor rule
roedyrustam/vibes-plug · .cursor/rules/vibes-plug-skills.mdc · Vibes-Plug 161-Skill Domain Registry — Use this rule whenever identifying specialized domain guidance, design patterns…
git:20261020.756149d · audit A · 122 stars
accessibility-testing-expert SKILL.md skill
roedyrustam/vibes-plug · .cursor/skills/accessibility-testing-expert/SKILL.md · Expert guide for automated and manual Web Accessibility (a11y) testing — axe-core, Pa11y, Playwright a11y, screen…
v4.4.2 · audit A · 122 stars
adaptive-model-cascade SKILL.md skill
roedyrustam/vibes-plug · .cursor/skills/adaptive-model-cascade/SKILL.md · Expert guide for intelligent model cascading and routing — complexity-scored task routing from Flash/Haiku to…
v4.4.2 · audit A · 122 stars
affective-computing-emotion-ai SKILL.md skill
roedyrustam/vibes-plug · .cursor/skills/affective-computing-emotion-ai/SKILL.md · Expert guide for Affective Computing, emotional AI, and real-time sentiment analysis through native multimodal tokens…
v4.4.2 · audit A · 122 stars
agentic-coding-workflow-expert SKILL.md skill
roedyrustam/vibes-plug · .cursor/skills/agentic-coding-workflow-expert/SKILL.md · Expert guide for AI-assisted coding workflows — agentic code generation, multi-agent code swarms, self-healing CI/CD…
v4.4.2 · audit A · 122 stars
agentic-m2m-settlement SKILL.md skill
roedyrustam/vibes-plug · .cursor/skills/agentic-m2m-settlement/SKILL.md · Expert guide for autonomous Machine-to-Machine (M2M) agent settlement, dual-rail fiat & stablecoin micro-clearing…
v4.4.2 · audit A · 122 stars
agentic-memory-architect SKILL.md skill
roedyrustam/vibes-plug · .cursor/skills/agentic-memory-architect/SKILL.md · Expert guide for long-term episodic memory integration (Mem0 v2, Letta/MemGPT, Zep v2), memory tier architecture…
v4.4.2 · audit A · 122 stars
agentic-micro-economy-architect SKILL.md skill
roedyrustam/vibes-plug · .cursor/skills/agentic-micro-economy-architect/SKILL.md · Expert guide for designing Machine-to-Machine (M2M) micro-economies, autonomous agent wallets, and swarm budget…
v4.4.2 · audit A · 122 stars
ai-code-review-autonomous SKILL.md skill
roedyrustam/vibes-plug · .cursor/skills/ai-code-review-autonomous/SKILL.md · Expert guide for multi-pass autonomous AI code self-review — syntax validation, logic correctness, architectural…
v4.4.2 · audit A · 122 stars

Every file in roedyrustam/vibes-plug

Other files named test-time-compute-optimizer

test-time-compute-optimizer SKILL.md skill
roedyrustam/vibes-plug · .cursor/skills/test-time-compute-optimizer/SKILL.md · Dynamic test-time compute allocation and reasoning token optimization / Alokasi komputasi test-time dinamis dan…
v4.7.0 · audit A · 122 stars

Browse by kind, by grade A, or by owner.