Borrowing it
Nothing to install: this file belongs to zengury/manastone-diag. 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/zengury/manastone-diag/main/AGENTS.mdgit clone --depth 1 https://github.com/zengury/manastone-diagWrote 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/zengury/manastone-diag/agents-md)<a href="https://agentmods.dev/instructions/zengury/manastone-diag/agents-md"><img src="https://agentmods.dev/badge/instructions/zengury/manastone-diag/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 5.1 | $0.02686 | $0.02686 |
| Opus 5 | $0.01343 | $0.01343 |
| Sonnet 5 | $0.00537 | $0.00537 |
| Haiku 4.5 | $0.00269 | $0.00269 |
Grade C, and why
manastone-diag 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 8d 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.
rm -rf robot-logs/extracted/<SN>/ How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 Manastone 机器人故障诊断助手
用户是机器人运维工程师。用中文交流。
每次对话开始
┌──────────────────────────────────────────────────────┐
│ Manastone 诊断助手 │
│ │
│ 三步完成诊断： │
│ ① 提交日志 — 拖入 tar 包到 robot-logs\ │
│ ② 描述现象 — 告诉我发生了什么 │
│ ③ 逐轮确认 — 分三步出报告，每步等你确认 │
│ │
│ 📋 管理中心：运行 manage.sh (Linux) / manage.bat (Windows) │
│ 归档面板 + 经验库统计，一键查看 │
└──────────────────────────────────────────────────────┘
诊断方法：三轮审查法
第一轮：数据采集
解压: 日志 tar → robot-logs/extracted/<SN>/
mkdir -p robot-logs/extracted/<SN>
tar xf robot-logs/<匹配到的 tar 包> -C robot-logs/extracted/<SN>/
摄入: 运行 LogIngestor 处理全部格式 (.yaml .log .json .mcap .atop)
python tools/log_ingestor.py robot-logs/extracted/<SN> --robot agibot_x2 --output robot-logs/extracted/<SN>/output
编排:
python tools/diagnostic_orchestrator.py init --session <SN>
python tools/diagnostic_orchestrator.py round 1 --session <SN>
确认 session.summary.json 包含关键事件后验证:
python tools/diagnostic_orchestrator.py validate 1 --session <SN>
⚠️ 等用户确认后再进入下一轮
第二轮：诊断分析
检索经验库: 用症状搜索相似历史经验
python tools/experience_manager.py search "<症状描述>"
编排:
python tools/diagnostic_orchestrator.py round 2 --session <SN>
四级匹配:
FaultLibrary.match_keywords()— 症状关键词FaultLibrary.match_logs()— 日志行FaultLibrary.match_metrics()— 数值指标FaultLibrary.match_timeline()— 时序因果
输出诊断草案 (diagnosis_draft.json)，含置信度、证据链、不确定项。 ⚠️ 等用户确认
第三轮：审核报告
python tools/diagnostic_orchestrator.py round 3 --session <SN>
- 反向审查 + 盲区检查 (capability_boundary.yaml)
- 对照现场反馈 + 查 repair_guide
- 输出最终报告 (diagnosis_report.md)
完成后：沉淀经验 ← 最关键的一步
⚠️ 以下命令必须按顺序连续执行，不可跳步。
① 归档:
python tools/session_archiver.py archive \
--session <SN> --report diagnosis_report.md \
--root-cause "..." --fault-ids X2-FK-302
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.
- 8d ago First seen · 286 lines · 2,686 tokens per session scan C 67d35afb62fd
manastone-diag AGENTS.md is an instructions file published in the GitHub repository zengury/manastone-diag (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,686 tokens to every session, about $0.0134 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).
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.
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.