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.
git clone --depth 1 https://github.com/masaomi/KairosChain_2026Wrote 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/rules/masaomi/kairoschain_2026/kairos)<a href="https://agentmods.dev/rules/masaomi/kairoschain_2026/kairos"><img src="https://agentmods.dev/badge/rules/masaomi/kairoschain_2026/kairos/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/rules/masaomi/kairoschain_2026/kairos"><img src="https://agentmods.dev/badge/rules/masaomi/kairoschain_2026/kairos.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 | $0.01124 | $0.01124 |
| Opus 5 | $0.00562 | $0.00562 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
kairos 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 10d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KairosChain — Core Philosophy for Development
Generative Principle: Structural Self-Referentiality
KairosChain's entire architecture flows from one principle:
Meta-level operations are expressed in the same structure as base-level operations.
This is why Ruby (DSL/AST) was chosen. "Defining a Skill" and "defining the evolution rules for a Skill" use the same language, syntax, and runtime. This structural correspondence is the foundation of self-referentiality, and all other properties of KairosChain germinate from it. Self-referentiality is not a design choice but an existential condition: without definitional closure at L0, the system would be "a program following configuration" rather than "an entity that defines its own conditions of existence."
Five Propositions (Summary)
-
Self-referentiality and metacognition as generative seed — Not an axiom deriving everything, but a pattern whose recursive application at different levels produces different properties. Intentionally asymmetric: strongest at L0 governance core, pragmatically open at infrastructure level ("sufficient self-referentiality"). Self-referentiality is structural (L0 defining itself); metacognition is cognitive (self_inspection evaluating the system's own state). Both dimensions are core.
-
Dual integrity guarantee — Prevention (approval_workflow's 5-layer validation) + structural impossibility (a contradictory self-referential system cannot operate). The latter holds within legitimate operation paths only.
-
Structure opens possibility space; design realizes it — Self-referential structure automatically enables recursive extension. Individual SkillSets (MMP, HestiaChain) are engineered, but the possibility of expressing meta-capabilities as SkillSets is a structural consequence, not a design decision.
-
Circular integration of process and result — Operation, evolution, and recording are functionally separated but ontologically unified through the same Skill structure. Time is Kairos (qualitative moment), not Chronos (quantitative flow).
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.
- 10d ago First seen · 79 lines · 1,124 tokens per session scan A 24683e57185d
kairos is a cursor rule published in the GitHub repository masaomi/KairosChain_2026 (7 stars, last pushed 4d ago), licensed MIT. It adds 1,124 tokens to every session, about $0.0056 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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.