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.
npx agentmods add instructions/chronoaiproject/consensus-rnd/claude-mdgit clone --depth 1 https://github.com/ChronoAIProject/consensus-rndWrote 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/chronoaiproject/consensus-rnd/claude-md)<a href="https://agentmods.dev/instructions/chronoaiproject/consensus-rnd/claude-md"><img src="https://agentmods.dev/badge/instructions/chronoaiproject/consensus-rnd/claude-md.svg" alt="Measured on agentmods" 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 | $0.04252 | $0.04252 |
| Opus 5 | $0.02126 | $0.02126 |
| Sonnet 5 | $0.00850 | $0.00850 |
| Haiku 4.5 | $0.00425 | $0.00425 |
Grade A, and why
consensus-rnd CLAUDE.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 4d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
consensus-rnd - Agent 工作指南
本文件给在本仓库内维护 skill、清单和文档的 agent 使用,不是下游 host 的运行时配置。仓库定位与共识引擎设计哲学见英文 canonical README.md,中文 companion 见 README.zh-CN.md。
旁路推理通道: nyxid oracle (ChatGPT Pro)
nyxid oracle 可作为 codex / Claude 之外的独立推理通道。命令、参数和输出字段以 nyxid oracle --help 为准;长 prompt 可用 --file -,多轮可用 --new-conversation / --conversation。异步请求只在完成后读取一次结果,不 busy-loop 轮询。oracle 能自行抓取公开可访问的 GitHub 链接,所以大段仓库内容可改为附 pin 到 commit SHA 的 permalink,而不是塞进 prompt;未公开的内容不得外链,也不得为了外链而推送或改仓库可见性。
仓库性质
这是一个跨平台 Agent Skills 发布仓库,不是应用代码仓库。唯一产物是 skills/<name>/ 下的 SKILL.md 及其配套文件,同一份 skills/ 由 Claude Code / Codex / Cursor / Gemini 共享。
目录约定
.
├── .claude-plugin/ # Claude Code: plugin.json + marketplace.json
├── .codex-plugin/ # Codex: plugin.json
├── .cursor-plugin/ # Cursor: plugin.json
├── gemini-extension.json + GEMINI.md
├── package.json # npm 风格元数据 / 版本锚点
├── AGENTS.md -> CLAUDE.md # 跨 agent 约定(符号链接)
├── README.md + README.zh-CN.md
├── LICENSE
├── skills/sshx/ # 发布的 worker-delegated inline consensus skill
└── .version-bump.json # 版本号同步映射
设计哲学(跨 skill 不动点)
- 单一主干、插件扩展:每个 skill 只有一条权威主链路,新能力挂载在明确的子模块或脚本上。
- 内核最小化:SKILL.md 承载触发条件、稳定不变量、行为合同和事实源索引;机械部分下沉到
scripts/,prompt 模板下沉到prompts/。 - 边界清晰、职责分层:本文件承载仓库级边界;skill 的工作流细则和术语归其自身事实源维护。
- 事实源唯一:版本号以
.version-bump.json为准,skill 行为以对应SKILL.md和测试为准,host 事实由 host 配置注入。 - 抽象优先、行为契约:跨 skill 只通过稳定文件 artifact、host 配置等边界协作,不耦合内部实现。
- 强类型边界、窄扩展点:扩展点必须有清楚职责、最小权限和可验证的授权来源,不引入通用生命周期权力。
- 抽象一旦能被滥用即设计未完成;删除优先,废弃路径直接移除,不保留兼容空壳或历史副本。
- 变更必须可验证:优先用 behavior test 或端到端可观察输入 / 输出 / 副作用断言;source-regression 只锁跨 artifact 一致性、事实源唯一性和授权边界。
- 治理前置:架构性或流程性规则必须和机械验证手段同时进入仓库。
- 正确架构优先:随着 skill 增长若边界自然变松,应重设计而非增加 escape hatch。
- 命名跟随职责:被脚本解析或跨 agent 传递的名字由所属事实源声明格式、canonical write policy 和迁移策略。
- 哲学文档不写 schema/identifier 版本后缀;Release semver 只作为
.version-bump.json的发布坐标。
共识引擎哲学
权威表述见英文 canonical README.md 的 Core 段;中文 companion 为 README.zh-CN.md。
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.
- 4d ago First seen · 178 lines · 4,252 tokens per session scan A fb192deec2dd
consensus-rnd CLAUDE.md is an instructions file published in the GitHub repository ChronoAIProject/consensus-rnd (24 stars, last pushed today), licensed MIT. It adds 4,252 tokens to every session, about $0.0213 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.