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/tile-ai/tilelang-ascend/agents-mdgit clone --depth 1 https://github.com/tile-ai/tilelang-ascendWrote 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/tile-ai/tilelang-ascend/agents-md)<a href="https://agentmods.dev/instructions/tile-ai/tilelang-ascend/agents-md"><img src="https://agentmods.dev/badge/instructions/tile-ai/tilelang-ascend/agents-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 | $0.02141 | $0.02141 |
| Opus 5 | $0.01071 | $0.01071 |
| Sonnet 5 | $0.00428 | $0.00428 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade A, and why
tilelang-ascend 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 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
项目概述
本项目是 TileLang-Ascend 算子开发项目，基于 TVM 编译器基础设施，提供 Python DSL 用于开发华为昇腾 NPU 上的高性能 AI 计算 kernel。
核心功能
- 使用 Python DSL +
@tilelang.jit编写昇腾 NPU 自定义 kernel - 支持 Developer 模式（自动化）和 Expert 模式（手动控制）两种编程范式
- 提供完整的编译、测试、调试及性能调优工作流
Skills 索引
算子开发与编排
tilelang-op-design：生成算子设计方案（design.md），含三维 Kernel / threads / 动态边界 / L0C 容量 / GEMM 非整除等技术约束检测tilelang-op-develop：基于 design.md 生成算子实现代码、内嵌 golden 与测试用例tilelang-ascend-tile-api：新增或封装T.tile.xxx小 API 时端到端打通前端、lowering / codegen、helper、测试与文档tilelang-programming-model-guide：Developer / Expert / 混合模式选择、pass_configs 配置与转换指南tilelang-api-best-practices：TileLang API 速查与最佳实践（Kernel 定义、内存分配、计算原语、调度同步）
Pass 分析与设计
tilelang-pass-analyzer：Pass 功能分析、对比、分类查询tilelang-pass-workflow-analyzer：Pass 工作流分析、执行顺序、依赖关系、新 Pass 定位tilelang-pass-design：Pass 设计方案与实现模式
调试与错误处理
tilelang-debug-helper：为算子添加 GDB 调试代码，配置 CMakeLists.txt 与 VSCode 联合调试tilelang-error-fixer：编译 / 运行时错误诊断与修复
性能调优
tilelang-perf-optimization：性能优化方案、最佳实践（Flash Attention / GEMM intrinsic / RoPE）与反模式排查
环境与工具
tilelang-env-check：环境检查与配置验证（CANN、torch_npu、子模块、编译产物、环境变量）tilelang-submodule-pull：自动拉取代码和子模块tilelang-github-operations：GitHub PR 创建与操作
Skill 管理
skill-creator：创建新 skillskill-journal：算子开发反馈记录 schematilelang-skill-review：聚合 skill-journal 反馈，按命令式 apply / reject 落到对应 SKILL.mdtilelang-review：通用 skill 质量评审
算子开发编排体系（OpenCode 多代理）
由 @tilelang-op-orchestrator 作为 Primary 驱动 3 阶段状态机，调度 3 个 Subagent：
@tilelang-op-analyst(Stage 1)：调用tilelang-op-design完成需求理解与设计@tilelang-op-developer(Stage 2)：调用tilelang-op-develop完成代码实现、测试、精度调试（一站式，attempt 上限 5 次）@tilelang-op-perf-tuner(Stage 3，可选)：调用tilelang-perf-optimization完成性能调优
DESIGN.md 非硬性约束——Subagent 在实施中发现设计错误时返回 [DESIGN_ERROR]，Orchestrator 回退到 Stage 1 重做（不设次数上限）。新建算子直接对 @tilelang-op-orchestrator 描述需求；单独使用某个 skill 可走 /tilelang-op-design、/tilelang-op-develop、/tilelang-perf-optimization、/tilelang-env-check 跳过编排层。
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 · 129 lines · 2,141 tokens per session scan A c2f376b32df8
tilelang-ascend AGENTS.md is an instructions file published in the GitHub repository tile-ai/tilelang-ascend (358 stars, last pushed 7d ago), licensed MIT. It adds 2,141 tokens to every session, about $0.0107 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
firmware CLAUDE.md
Claude Code instructions for OpenIPC/firmware, covering claude.md, what this is, before you start: is this the right repository?, build and common tasks.
Tutorial_AwesomeModernCPP AGENTS.md
AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.
ext-apps CLAUDE.md
Claude Code instructions for modelcontextprotocol/ext-apps, a project described as: Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers.