mkonstan

4 mods across 1 repository, 2 stars between them.

llm-tools AGENTS.md

01

mkonstan/llm-tools

Instructions file CodexOpenCode

Instructions for mkonstan/llm-tools, covering project runtime governor, 1. behavioral override, 2. stamp (mandatory runtime header), rules and 3. tier classification.

2 5mo ago A 972 tokens original Apache-2.0

context-transfer

02

mkonstan/llm-tools

Skill Claude CodeCodex

Generate a state document (context transfer) that allows any fresh AI instance to resume work without conversation history. Use this skill whenever the user asks to checkpoint, create a state transfer, save state, generate a handoff document, create compaction insurance, or says anything like 'snapshot this', 'create…

2 5mo ago A 156 tokens original Apache-2.0

interview

03

mkonstan/llm-tools

Skill Claude CodeCodex

Adversarial knowledge extraction through structured interviewing. Use this skill when the user wants to extract tacit knowledge, scope a new domain, gather requirements, document decisions, do knowledge transfer, or bootstrap a context dump from a cold start. Triggers include: "interview me", "extract what I know"…

2 5mo ago A 189 tokens original Apache-2.0

pipeline-builder

04

mkonstan/llm-tools

Skill Claude CodeCodex

Convert workflow documents, CLAUDE.md rules, or process descriptions into agentic pipeline skills that Claude Code or Cowork can execute as enforced task lists. Use this skill whenever a user says 'build a pipeline', 'convert my workflow to a skill', 'make this agentic', 'enforce my CLAUDE.md', 'turn my rules into a…

2 5mo ago A 182 tokens original Apache-2.0