Agent skill · product strategy · borghei
extended-thinking-architect
This skill should be used when the user asks to "decide reasoning effort", "set a thinking budget", "when to use extended thinking", "tune reasoning vs cost", or "should this task use a reasoning model".
Why this skill is useful
Adds two executable scripts for optimizing reasoning budgets and allocating effort across agent loops, which are not commonly found in public documentation.
What it needs
Requires python installed locally. About 3k tokens when loaded. Last updated 2026-07-21. 462 stars on the source repository.
What this skill does
Extended Thinking Architect Category: Engineering Domain: AI Engineering Overview The Extended Thinking Architect skill helps you decide when an LLM task should spend a reasoning/thinking budget, how much (no-thinking / low / medium / high), and when the better move is a cheaper model with a sharper prompt instead. It turns task signals — error cost, ambiguity, step count, latency budget — into a deterministic recommendation with a rough cost multiplier, and allocates effort across the phases of an agent loop so you front-load reasoning where it pays and avoid runaway budgets. Clarify First Before recommending an effort level, confirm these inputs. If any is unknown or vague, ASK — do not assume: [ ] Task type & verifiability — what the model is actually doing (extraction, classification, planning, code-debug, math…) and whether the output is checkable (sets --task-type and --verifiable) [ ] Cost of a wrong answer — how expensive a bad output is, plus the latency budget the task must fit (sets --error-cost and --latency-budget) [ ] Shape of the work — how many reasoning/tool steps are expected and how ambiguous the request is (sets --steps and --ambiguity) Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact. Quick Start Tools Overview Tool Purpose Key Flags ------ --------- ----------- reasoningbudgetadvisor.py Recommend an effort level (none/low/medium/high) or "prompt-first / cheaper-model" for one task, with rationale + cost multiplier --task-type, --error-cost, --steps, --ambiguity, --latency-budget, --verifiable, --json reasoningloopallocator.py Allocate reasoning effort across agent-loop phases (plan/act/observe/recover/finalize) under a total budget cap --difficulty, --steps, --max-budget-multiplier, --realtime, --json Workflows Choosing Effort for a New Task 1. Identify the task type and whether the output is verifiable (ground truth or a checker exists). 2. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills borghei/extended-thinking-architect