How do I install the Ki Tokenomics Codex skill?

Run npx skillmds@latest add knowledgeislands/ki-tokenomics-codex in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ki Tokenomics Codex safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ki Tokenomics Codex?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ki Tokenomics Codex free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ki Tokenomics Codex?

knowledgeislands (@knowledgeislands) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ki Tokenomics Codex by knowledgeislands

Name: Ki Tokenomics Codex
Author: knowledgeislands

Ki Tokenomics Codex

Audit direct, non-secret Codex filesystem observations in the selected repository: trusted project configuration, AGENTS.md, skill, and custom-agent source directories. Use when a Codex repository needs bounded runtime evidence for portable `ki-tokenomics` policy. Effective model, loaded instructions, active MCP, trust, memory use, transcripts, and compaction remain unavailable without authorised session evidence. For portable budgets use `ki-tokenomics`; for Claude Code use `ki-tokenomics-claude`.

knowledgeislands d6bd354 19 files · 35.2 KB Updated Sep 17, 2026

File contents

Codex tokenomics

ki-tokenomics-codex composes ki-tokenomics with direct Codex filesystem observations from the selected repository only. It does not inspect user-home state, Claude state, arbitrary local caches, or undocumented local state.

The audit reports paths and structural presence only. It parses the selected trusted project TOML only to verify its shape and never reports values, including environment variables, API keys, headers, or credential-bearing configuration. Effective model/profile, loaded instruction hierarchy, active MCP, trust, memory use, transcript, compaction, billing, and tool-schema metrics are unavailable.

For dated source-local family evidence and the no-live-call evaluation protocol, read the model-tier resolution standard.

It maps work roles to portable purposes without selecting an effective model; repository bindings remain advisory until separately authorised evaluation establishes a default.

CONFORM is report-only and emits no writes or commands.

Composition

Run ki-tokenomics for portable configuration, budget semantics, and model purpose. Route MCP-server design to ki-repo-mcp and skill-description quality to ki-skills.

Operating modes

Mode AUDIT

→ Read mode-audit.md

Mode CONFORM

→ Read mode-conform.md

Mode EDUCATE

Declare this adapter only for repositories that support Codex; it scaffolds no runtime state.

Mode REFRESH

→ Read mode-refresh.md

Refresh only in ki-agentic-harness; from an installed copy, stop and redirect to the canonical harness.

Mode HELP

Explain this Codex-only evidence boundary and stop without changing anything.

---name: ki-tokenomics-codexdescription: Audit direct, non-secret Codex filesystem observations in the selected repository: trusted project configuration, AGENTS.md, skill, and custom-agent source directories. Use when a Codex repository needs bounded runtime evidence for portable `ki-tokenomics` policy. Effective model, loaded instructions, active MCP, trust, memory use, transcripts, and compaction remain unavailable without authorised session evidence. For portable budgets use `ki-tokenomics`; for Claude Code use `ki-tokenomics-claude`.---# Codex tokenomics`ki-tokenomics-codex` composes `ki-tokenomics` with direct Codex filesystem observations from the selected repository only. It does not inspect user-home state, Claude state, arbitrary local caches, or undocumented local state.The audit reports paths and structural presence only. It parses the selected trusted project TOML only to verify its shape and never reports values, including environment variables, API keys, headers, or credential-bearing configuration. Effective model/profile, loaded instruction hierarchy, active MCP, trust, memory use, transcript, compaction, billing, and tool-schema metrics are unavailable.For dated source-local family evidence and the no-live-call evaluation protocol, read [the model-tier resolution standard](references/standards-model-tier-resolution.md).It maps work roles to portable purposes without selecting an effective model; repository bindings remain advisory until separately authorised evaluation establishes a default.CONFORM is report-only and emits no writes or commands.## CompositionRun `ki-tokenomics` for portable configuration, budget semantics, and model purpose. Route MCP-server design to `ki-repo-mcp` and skill-description quality to `ki-skills`.## Operating modes### Mode AUDIT→ Read [mode-audit.md](references/mode-audit.md)### Mode CONFORM→ Read [mode-conform.md](references/mode-conform.md)### Mode EDUCATEDeclare this adapter only for repositories that support Codex; it scaffolds no runtime state.### Mode REFRESH→ Read [mode-refresh.md](references/mode-refresh.md)Refresh only in `ki-agentic-harness`; from an installed copy, stop and redirect to the canonical harness.### Mode HELPExplain this Codex-only evidence boundary and stop without changing anything.

Frequently asked questions