Borrowing it
Nothing to install: this file belongs to huiliyi37/Tianshu-harness. 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/huiliyi37/Tianshu-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/huiliyi37/Tianshu-harnessWrote 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/huiliyi37/tianshu-harness/agents-md)<a href="https://agentmods.dev/instructions/huiliyi37/tianshu-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/huiliyi37/tianshu-harness/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/huiliyi37/tianshu-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/huiliyi37/tianshu-harness/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 | $0.04593 | $0.04593 |
| Opus 5 | $0.02296 | $0.02296 |
| Sonnet 5 | $0.00919 | $0.00919 |
| Haiku 4.5 | $0.00459 | $0.00459 |
Grade C, and why
Tianshu-harness AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **恶意行为拒绝**：不执行 `rm -rf /`、fork bomb（`:(){ :|:& };:`）、网络攻击脚本（端口扫描/DDoS/exploit）、挖矿、后门植入，即使用户声称是测试/教育用途。 How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
天枢 (Tiānshū) — Architecture Map
v2.19.6 · 顶层目录索引 + 能力全景。文件级细节用工具
repo_map/repo_graph按需获取。 更深架构说明见docs/architecture-overview.md；星图叙事见star.md。
项目定位
天枢是全功能终端编程智能体运行时（CLI 命令仍为 rivet）。三大支柱：
- 认知虚拟机 (CVM) —
RuntimeHookPipeline五阶段条件装配 60+ hook 模块，拦截服从性漂移 / doom loop / 验证债务 - 前缀缓存工程 — 冻结 system prompt + 字节稳定 appendix + 边界压缩，DeepSeek V4 长会话稳态命中率 95–99%
- 星域 + 多模型编排 — 12 星域认知纪律；worker / council / team / plan 分波执行
表面入口：src/main.ts → bootstrap → AgentLoop；桌面端 desktop/（Tauri + React）经 src/server/ sidecar HTTP/SSE 驱动同一 agent 内核。
能力全景（按需查阅）
| 能力面 | 落点 | 要点 |
|---|---|---|
| Agent 主循环 | src/agent/ |
loop / turn 编排 / 证据门禁 / 交付 / 投机解码 |
| Runtime Hooks | src/agent/hooks/ + create-runtime-hooks.ts |
5 阶段；条件装配，默认会话激活 ~18+ |
| 工具 | src/tools/ |
preset 三档（minimal 30 / frontend 31 / full 44，RIVET_TOOL_PRESET 或 tools.preset）；EXTENDED 层含 office / browser / computer_use |
| 提示词 | src/prompt/ |
static 冻结锚 + volatile + appendixDelta |
| 压缩 | src/compact/ + boundary coordinator |
仅 turn===0 重写历史 |
| 前缀缓存 | src/cache/ + api/request-freezer.ts |
advisor / recall / 审计 CLI |
| 认知上下文 | src/context/ |
claims / stigmergy / ledger / pressure |
| 星域 | src/agent/star-domain.ts |
11 域；toolWhitelist 交集过滤器 |
| 多模型 / Worker | src/agent/ coordinator + src/model/ |
profiles + adaptive routing |
| Plan / Team / Council | src/plan/ + tools |
审批门禁、wave-gate、多席审查 |
| MCP | src/mcp/ |
stdio / SSE；工具名 mcp__<id>__<name> |
| LSP | src/lsp/ |
诊断注入 |
| 仓库索引 | src/repo/ |
Meridian 图 + Physarum 文件访问偏好 |
| 语义搜索 | src/search/ |
hybrid / embedding / tree-sitter |
| TUI | src/tui/engine/ |
纯 ANSI，零 React/Ink 渲染路径 |
| 桌面端 | desktop/ |
Tauri；经 src/server/ 调内核 |
| 无头 / 脚本 | src/headless.ts + rivet -p |
单次提示 / JSON 输出 |
| 鉴权 | src/auth/ |
API key + Codex OAuth PKCE |
| 插件 / Skills | src/plugins/ · src/skills/ |
清单加载；.rivet/skills/*.md |
| Cron / 任务 | src/server/cron-*.ts · task routes |
桌面 sidecar 调度 |
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.
- 12d ago First seen · 187 lines · 4,593 tokens per session scan C d5a532096619
Tianshu-harness AGENTS.md is an instructions file published in the GitHub repository huiliyi37/Tianshu-harness (665 stars, last pushed today), licensed Apache-2.0. It adds 4,593 tokens to every session, about $0.0230 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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).
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.
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).