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/walker152/navi_minco_bit/agents-mdgit clone --depth 1 https://github.com/Walker152/navi_minco_bitWrote 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/walker152/navi_minco_bit/agents-md)<a href="https://agentmods.dev/instructions/walker152/navi_minco_bit/agents-md"><img src="https://agentmods.dev/badge/instructions/walker152/navi_minco_bit/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 | $0.05879 | $0.05879 |
| Opus 5 | $0.02939 | $0.02939 |
| Sonnet 5 | $0.01176 | $0.01176 |
| Haiku 4.5 | $0.00588 | $0.00588 |
Grade A, and why
navi_minco_bit 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 — 703 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
项目 Agent 行为准则
本文件是本仓库中 AI Agent、Codex、Claude、superpower skill、多 agent 工作流的统一行为规范。
所有代码修改、审计、重构、调参、文档化任务都必须优先阅读并遵守本文件。
本仓库是 RoboMaster 哨兵机器人比赛代码仓库,包含行为树、自主决策、planner、controller、地图、里程计、点云、裁判系统通信、launch、参数文件等模块。仓库中存在已经经过比赛验证的逻辑,任何修改都必须以“保持可复现、最小改动、可审计”为第一原则。
0. 最高优先级限制:编译构建限制
禁止在未经用户明确允许的情况下执行任何编译或构建操作,包括但不限于:
colcon buildcatkin build/catkin_makecmake构建make/ninjacargo build/cargo checknpm run build/yarn build- 任何其他会触发代码编译、链接的命令
在执行任何编译构建命令之前,必须先向用户确认并获得明确许可。
允许在未确认前执行的低风险检查包括:
grep/rgfindlssed/catpython3静态解析脚本- XML 语法解析
- YAML 语法解析
- git diff / git status
- 不触发编译、链接、生成代码的静态检查
如果不确定某条命令是否会触发构建,必须先询问用户。
0.1 最高优先级限制:禁止版本控制提交操作
禁止执行任何会改变 Git 历史、Git 索引、远端仓库、分支或标签状态的提交类操作,无论用户是否要求修改代码,均不得由 Agent 主动提交。
禁止命令包括但不限于:
git addgit commitgit commit --amendgit pushgit taggit mergegit rebasegit cherry-pickgit revertgit reset --hardgit checkout -- <file>/git restore <file>等会覆盖工作区修改的命令gh pr merge、gh release create等任何会产生提交、合并、发布或远端变更的命令
允许的只读 Git 检查包括:
git statusgit diffgit loggit show
Agent 只负责修改工作区文件和说明变更,不负责暂存、提交、推送、打标签或合并。
即使任务已经完成,也只能提醒用户自行检查和提交,不能代替用户执行任何提交操作。
0.2 最高优先级限制:禁止 writingplans / 计划说明工具
禁止使用 writingplans、Superpower writing plan、计划说明 skill 或类似工具来生成计划、改造计划、测试计划或阶段说明。
执行方式要求:
- 用户与 Agent 已经商讨清楚需求和边界后,直接修改代码或文件。
- 不要在正式修改前额外输出长篇“计划说明”“改造计划说明”“测试计划说明”。
- 不要新建
writingplans相关文件。 - 不要把计划说明作为修改前的阻塞步骤。
- 必要的任务边界、风险、检查项可以写入最终改造记录或最终回复,但不能调用 writingplans 工作流。
- 多 Agent 流程只有在用户明确要求时使用,且不得用 writingplans 替代 Explorer / Modifier / Auditor 的实际检查。
允许保留简短的执行摘要和最终检查结果,但不得以 writingplans 形式展开。
核心原则是:商讨完毕后直接按约束修改代码,修改完成后再给出摘要、检查结果和剩余风险。
1. 项目背景
本仓库包含但不限于以下模块:
- 行为树与自主决策:
bt_manager、行为树 XML、blackboard、裁判系统通信。 - 规划器:MINCO planner、路径搜索、轨迹优化、重规划逻辑。
- 控制器:MPC controller、controller_server、速度输出、参数切换。
- 地图与感知:ROGMap、ProjectionLayer、ESDF、地形投影、动态障碍处理。
- 里程计与点云:Point-LIO / Batch-LIWO、Livox 驱动、完整点云输出、去畸变、odom。
- ROS 2 通信:component container、intra-process、QoS、topic、launch、参数文件。
- 比赛策略:前哨站、冲家、补给、复活、姿态、小陀螺、隧道、台阶、资源兑换。
- 文档与实验材料:论文、申请材料、性能记录、CSV、图片、演讲稿等。
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 · 703 lines · 5,879 tokens per session scan A 235d0fa1e4f1
navi_minco_bit AGENTS.md is an instructions file published in the GitHub repository Walker152/navi_minco_bit (24 stars, last pushed 4d ago), licensed Apache-2.0. It adds 5,879 tokens to every session, about $0.0294 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.