Borrowing it
Nothing to install: this file belongs to liuyingxuvka/Khaos-Brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/liuyingxuvka/Khaos-Brain/main/AGENTS.mdgit clone --depth 1 https://github.com/liuyingxuvka/Khaos-BrainWrote 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/instructions/liuyingxuvka/khaos-brain/agents-md)<a href="https://agentmods.dev/instructions/liuyingxuvka/khaos-brain/agents-md"><img src="https://agentmods.dev/badge/instructions/liuyingxuvka/khaos-brain/agents-md/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/instructions/liuyingxuvka/khaos-brain/agents-md"><img src="https://agentmods.dev/badge/instructions/liuyingxuvka/khaos-brain/agents-md.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 | $0.04956 | $0.04956 |
| Opus 5 | $0.02478 | $0.02478 |
| Sonnet 5 | $0.00991 | $0.00991 |
| Haiku 4.5 | $0.00496 | $0.00496 |
Grade A, and why
Khaos-Brain AGENTS.md 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 9d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository expectations
Bootstrap
- If the user asks to install, enable, deploy, bootstrap, or set up this predictive KB system on any machine, your default first action is to run
python scripts/install_codex_kb.py --jsonfrom the repository root. - Immediately after installation, run
python scripts/install_codex_kb.py --check --jsonand confirm the install is healthy before doing anything else. - Treat the installer as idempotent. If the system may already be installed, rerun the installer anyway rather than asking the user to verify it manually.
- If this repository was moved to a new path or re-cloned, rerun the installer from the new clone so the Codex-side manifest points at the current KB root.
- The installed global preflight skill must enable implicit invocation, remind Codex to add phase-change KB checkpoints during long mixed tasks, and remind Codex to record KB postflight observations after meaningful work, including skill/plugin and subagent/delegation usage lessons when they materially affect task outcomes. Treat missing behavior as an installation defect and fix it.
- The installer must also refresh the repository-managed
kb-sleep-maintenance,kb-dream-pass,kb-organization-contribute,kb-organization-maintenance, andkhaos-brain-updateskills under$CODEX_HOME/skills; these skills are explicit maintenance, organization, or update entry points and should not enable broad implicit invocation.khaos-brain-updateis manual-only and has no automation binding. - The installer must refresh exactly two scheduled composite automations under
$CODEX_HOME/automations:KB Sleepowns the local Sleep-then-Dream cycle, and organization maintenance owns snapshot refresh, shared maintenance, and contribution.kb-dream-passandkb-organization-contributeremain callable child Skills, not scheduled owners. The installer must permanently retire the exact legacykb-architect-passSkill,kb-architectautomation,khaos-brain-system-updateautomation, and the former standalone Dream/contribution schedules on fresh installs and upgrades, without touching similarly named user assets. - Every install or upgrade must run the versioned Chaos Brain maintenance migration, settle old lifecycle debt, archive retention-required cold evidence, prune only receipt-covered derivations, rescan for late reintroduced and Windows extended-length managed files, settle observations admitted by concurrent AI work through bounded post-commit receipts, rebuild the active index, preserve every surviving automation's user pause state, and remain rollbackable until current aggregate validation passes.
- Chaos Brain has zero normal-runtime compatibility and zero normal-runtime fallback. Exact retired formats may be read only by their versioned upgrade owner, which must rewrite or replace them directly, remove their old authority, prove zero residuals, and otherwise roll back while both retained composite automations remain paused. An incompatible residual is an unfinished upgrade-AI work item: derive one evidence-bound direct-to-current disposition and retry inside the rollbackable upgrade instead of adding a product reader. Missing current authority must fail visibly; never add a dual reader/writer, alias, alternate launcher/model, or silent downgrade.
- The installer must also write or refresh a repository-managed global defaults block under
$CODEX_HOME/AGENTS.mdso other machines inherit the strongest available session-wide KB preflight and postflight rules, not only the implicit skill layer. - The install check must expose a structured machine-install checklist that explicitly verifies the global skill files, implicit invocation, phase-change KB checkpoint wording, postflight reminder wording, mistake-first highest-priority postflight wording, skill/plugin and subagent/delegation signal wording, managed global AGENTS block, repo-managed maintenance/organization/update skills, all repo-managed automations, and the final
strong_session_defaultsreadiness signal.
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.
- 9d ago First seen · 253 lines · 4,956 tokens per session scan A 31a8efc5faa5
Khaos-Brain AGENTS.md is an instructions file published in the GitHub repository liuyingxuvka/Khaos-Brain (37 stars, last pushed 1mo ago), licensed MIT. It adds 4,956 tokens to every session, about $0.0248 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.