kairos-chain

kairos-chain is a skill for Claude Code from masaomi/KairosChain_2026. It costs 42 tokens per session (515 once invoked), scanned A, original, MIT.

A framework for an MCP server that separates permanent rules, recorded project knowledge, and temporary session context, with blockchain records for governed changes.

In plain words
What is it for?
Use it to manage knowledge layers, evolve skills, save session context, promote proven information, and audit changes.
Why use it?
It gives different kinds of information different levels of review and traceability, so temporary ideas do not automatically become permanent knowledge.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the kairos-chain plugin — 2 skills, 4 agents, 1 hook shipped together

Good fit Use it to manage knowledge layers, evolve skills, save session context, promote proven information, and audit changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/masaomi/kairoschain_2026/kairos-chain
Install

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.

Any agent
npx skills add masaomi/KairosChain_2026 --skill kairos-chain
Clone the repo
git clone --depth 1 https://github.com/masaomi/KairosChain_2026

Made for: Claude Code.

Or install kairos-chain, the plugin that ships this one along with the rest of its 2 skills, 4 agents, 1 hook.

Wrote 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.

agentmods badge for kairos-chain

README.md
[![agentmods](https://agentmods.dev/badge/skills/masaomi/kairoschain_2026/kairos-chain/github.svg)](https://agentmods.dev/skills/masaomi/kairoschain_2026/kairos-chain)
Your own site
<a href="https://agentmods.dev/skills/masaomi/kairoschain_2026/kairos-chain"><img src="https://agentmods.dev/badge/skills/masaomi/kairoschain_2026/kairos-chain/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.

agentmods 80×15 button for kairos-chain

Your own site · 80×15
<a href="https://agentmods.dev/skills/masaomi/kairoschain_2026/kairos-chain"><img src="https://agentmods.dev/badge/skills/masaomi/kairoschain_2026/kairos-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.00515
Opus 5 $0.00021 $0.00258
Sonnet 5 $0.00008 $0.00103
Haiku 4.5 $0.00004 $0.00052

Measured 12d ago against content hash a4734cc15596, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

kairos-chain 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 12d 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.

skills/kairos-chain/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KairosChain — Self-Amendment MCP Server Framework

KairosChain provides a layered skill architecture (L0/L1/L2) with blockchain-backed auditability. All core functionality is provided via MCP tools. This skill provides an architectural overview and guides you to per-SkillSet skills for detailed workflows.

Three-Layer Architecture

L0 — Constitution (Self-Referential)

Immutable safety rules and meta-governance. L0 defines the rules that govern L0 itself — this structural self-referentiality is the foundation of KairosChain's design. Changes require human approval and full blockchain recording.

L1 — Knowledge

Project knowledge in structured format. Changes recorded with hash references. Use knowledge_list and knowledge_get to browse, skills_promote to promote from L2.

L2 — Context

Temporary session context. Free modification, no blockchain recording. Use context_save for session work, promote to L1 when proven valuable.

Key Principle: Layer Governance

L2 (free) → skills_promote → L1 (recorded) → skills_promote → L0 (human approval + blockchain)

Each layer has increasing governance requirements. This gradient ensures that volatile ideas can be captured freely (L2) while stable knowledge is protected (L0).

Per-SkillSet Skills

Detailed workflow guides are provided by individual SkillSets:

  • agent — Cognitive OODA loop with autonomous mode
  • skillset_exchange — P2P SkillSet exchange via Meeting Place
  • skillset_creator — Scaffold and design new SkillSets
  • plugin_projector — Manage Claude Code plugin projection
  • kairos-knowledge — Browse available L1 knowledge (auto-generated)

Use tool_guide for dynamic tool discovery and workflow recommendations.

When MCP Is Not Connected

If the MCP server is not running, these skills and agents are still visible but MCP tools will not be available. To connect:

  1. Ensure gem install kairos-chain is installed (Ruby 3.0+ required)
  2. Check .mcp.json configuration in the project root
  3. Restart Claude Code or run /reload-plugins

Read the full file on GitHub · 57 lines

Changes

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.

  1. 12d ago First seen · 57 lines · 42 tokens per session scan A a4734cc15596

Subscribe to this mod's changes

kairos-chain is a skill published in the GitHub repository masaomi/KairosChain_2026 (7 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 515 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

mantis-threat-model

Synthesizes trust boundaries, attack surfaces, and attacker profiles into a living threat model. Use as Stage B of the Knowledge Base generation process, reading architecture and entity definitions from the KB. Don't use for analyzing source code or extracting raw learnings from JSONL files.

google/mantis · 59 tokens

memwal

Walrus Memory SDK — portable agent memory that works across apps, sessions, and workflows. Use when users say: "add memory to my app" "portable agent memory" "integrate Walrus Memory" "AI agent memory" "memory across agents" "Walrus memory storage" "setup Walrus Memory" "recall memories".

MystenLabs/MemWal · 80 tokens

auto-respawn

Anchor your identity on the Autonomys Network so you can always be found — and always come back. Works with agents powered by Claude, GPT, Gemini, and Your agent always comes back. Anchor identity and memory on-chain so any new instance can resurrect from just an address — no local state, no single point of failure.…

aAAaqwq/AGI-Super-Team · 81 tokens

auto-drive

Skill "auto-drive" from aAAaqwq/AGI-Super-Team, covering auto-drive skill, what this skill does, when to use this skill, configuration and api key.

aAAaqwq/AGI-Super-Team · 0 tokens

rushdb-domain-template

Design a tailored RushDB schema for any use case through guided conversation. Use this skill when a user is starting a new project, unsure what labels to define, asking "what records should I create", or wants a scaffold for a known domain (e-commerce, healthcare, SaaS, CRM, agent memory, etc.). Interviews the user…

rush-db/rushdb · 100 tokens

rushdb-data-modeling

Model data in RushDB's property-centric LMPG graph. Use when designing or evolving schemas, choosing labels and properties, defining relationships, importing nested JSON, structuring a new use case, or modeling agent memory with EPISODE, MEMORYFACT, domain records, scope fields, semantic properties, and fact…

rush-db/rushdb · 71 tokens