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.
npx skills add roedyrustam/vibes-plug --skill test-time-compute-optimizergit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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.
[](https://agentmods.dev/skills/roedyrustam/vibes-plug/test-time-compute-optimizer)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/test-time-compute-optimizer"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/test-time-compute-optimizer/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.
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/test-time-compute-optimizer"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/test-time-compute-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.02854 |
| Opus 5.5 | $0.00034 | $0.01142 |
| Sonnet 5.5 | $0.00017 | $0.00571 |
| Haiku 4.5 | $0.00008 | $0.00285 |
Grade A, and why
test-time-compute-optimizer 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
test-time-compute-optimizer — vibes-plug Skill
English
Orchestration & Integration
- Upstream & Orchestration:
zero-to-prod-orchestrator(Phase 4 AI agent integration),brainstorming,session-memory-manager. - Reasoning Budget & Cascading:
thinking-budget-orchestrator(dynamic token budget allocation),adaptive-model-cascade(complexity threshold escalation),llm-finops-router(token expenditure tracking). - Frontier LLMs & Sandboxes:
frontier-ai-models-expert(Gemini 4 Pro, Claude 5.5, GPT Astra 6 reasoning parameters),ephemeral-wasm-sandbox-executor(deterministic code candidate execution). - Consensus & Multi-Drafting:
speculative-multi-draft-synthesizer(multi-candidate arbiter),formal-spec-z3-verifier(mathematical invariant proving).
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). - Implementing inference-time search algorithms (Monte Carlo Tree Search, Best-of-N with verification).
- Optimizing cost-vs-accuracy trade-offs to prevent over-spending on trivial tasks while maximizing reasoning on critical bottlenecks.
Core Concepts & Patterns
1. Dynamic Reasoning Budget Matrix
Inference-time compute scaling operates across three distinct operational tiers based on prompt entropy and execution risk:
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.
- 3d ago Changed · -22 lines 33605ba98a29
- 4d ago Changed · +1 lines 157b217fed9f
- 7d ago Changed 731240e1b02e
- 16d ago Changed 6aad03f34c48
- 18d ago Changed 22f3c4befb9a
- 21d ago First seen · 232 lines · 84 tokens per session scan A ca9c7a83a59b
test-time-compute-optimizer is a skill published in the GitHub repository roedyrustam/vibes-plug (113 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 2,854 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
prompt-modeler
Generate structured strategic prompts with diagnostic and multiple options. Triggers on: /modelar-prompt.
few-shot-architect
Professional Few Shot Architect skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
llm-prompt-master
Professional LLM Prompt Master skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
responsible-ai
Professional Responsible Ai Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.