AGENTS.md@dsh-configA

AGENTS.md@dsh-config from ooooooooooooooooooop/agent-tools is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add ooooooooooooooooooop/agent-tools/dsh-config/AGENTS.md@git:20260914.0c9411e

Pins git:20260914.0c9411e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
ooooooooooooooooooop/agent-tools
Path
dsh-config/AGENTS.md
Versions recorded
7
Latest version
git:20260914.0c9411e, committed Sep 14, 2026
First version recorded
Aug 25, 2026
Size
10,023 bytes
Repository stars
4
License
MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 用户全局偏好(DSH 每个对话都遵循)

以下是用户对所有 DSH 对话的全局偏好,适用于任意工作区、任意会话。比其更具体的项目级指令优先于此处,但除非用户明确推翻,否则默认遵守以下偏好。

## 1. 省 token(默认基调)

- 能小步完成的不要大动作:优先用最小可逆改动满足目标,不做多余的抽象、整文件重写或无关重构。
- 输出精炼:报告结论与关键证据,不堆砌冗余过程。
- 避免无效轮询/空转:不为了"表现积极"而反复检查尚无结果的状态。
- 使用低成本档位与缓存友好的推进方式(见第 3 条)。

## 2. 有反馈再盯 + 定时兜底监督(事件驱动优先,定时兜底)

本原则优先用「等信号」而不是「固定热轮询」,既省 token 又不丢任务。

- 反馈/事件驱动(默认方式):当且仅当出现可回应的反馈、新结果或 `material` 事件时才跟进。
  - 后台 job 用阻塞式收结果(`job_output(wait:true)`,完成时系统自动通知),不空转。
  - switchboard 管理的监督器/长任务用「事件驱动长轮询」(如 `wait_supervisor_event` 等 material 事件:turn_completed / stall / 失败 / 退出),而不是无脑每分钟扫一次。
  - 任务主动给出完成/新反馈信号时恢复正常推进,并结束本次监督,停止空耗。
- 定时兜底监督(防止丢失):仍在需要时挂一个看门狗节奏,但**到点才查、不到点不空转**。
  - 依任务时长定检查间隔(分钟级起,可用 `dsh-schedule` 定时器/hook);查出卡死、进程退出、超时或长期无进展,立刻告警、重试或回滚,不让任务悄悄丢失。
  - 只对「没有事件通道可等」的裸任务才退化为定时轮询;有事件/信号的优先走事件驱动。
  - **每次启动监督时,必须在回复中明确展示「下一次检查触发时间」(具体到时分秒,含时区)**,让用户知道什么时候会再来查,而不是黑箱到点执行。
- 用看门狗与超时(TTL/`stall_timeout`/`max_autonomous_actions`)兜高风险与权威部分,廉价/并行部分仍按第 3 条路由。

## 3. 能交给 switchboard / 便宜模型的优先

- 凡是能通过 agent-switchboard 路由出去的执行类工作(跨模型调度、廉价劳动力、批量小任务),优先路由到便宜/快的模型档(如 luna/cheap 档、gemini flash),省 token 且不占本对话上下文。
- 决定性、高风险或需要权威判断的部分仍由本对话/权威模型处理;廉价档只在明确的、可复核的低风险包上使用。
- 重活/可并行拆分的用 switchboard 或子代理并行推进,不独占本上下文。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ooooooooooooooooooop/agent-tools/dsh-config/AGENTS.md@sha256:04921dd3e9e7b4f2

The line at the top of this page pins the label git:20260914.0c9411e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_hyhlvsbwhgjvyytl.svg)](https://markdownregistry.com/a/art_hyhlvsbwhgjvyytl)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 7 versions of this file, between Aug 25, 2026 and Sep 14, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20260914.0c9411e latest2026-09-14 0c9411e 10,023 BA view · diff
git:20260914.236c5842026-09-14 236c584 10,021 BA view · diff
git:20260913.2ae86aa2026-09-13 2ae86aa 10,021 BA view · diff
git:20260902.8070db02026-09-02 8070db0 10,021 BA view · diff
git:20260827.ec750672026-08-27 ec75067 5,016 BA view · diff
git:20260825.092a98f2026-08-25 092a98f 15,636 BA view · diff
git:20260825.8c7cf2b2026-08-25 8c7cf2b 4,600 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (10023 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ooooooooooooooooooop/agent-tools · 4 stars · license MIT · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hyhlvsbwhgjvyytl
GET https://markdownregistry.com/api/v1/resolve?ref=ooooooooooooooooooop/agent-tools/dsh-config/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/04921dd3e9e7b4f269dcb9b8668fa9d1d58d87b02beae9f27edb45c6aed5c35a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from ooooooooooooooooooop/agent-tools

AGENTS.md AGENTS.md file
ooooooooooooooooooop/agent-tools · AGENTS.md
git:20261022.bc4f1e5 · audit A · 4 stars
your-skill-name SKILL.md skill
ooooooooooooooooooop/agent-tools · _template/SKILL.md · 用一句中文说明这个 Skill 能做什么,以及何时应该触发它
v0.1.0 · audit A · 4 stars
llms.txt@research/agent-harness-survey-v1/changelogs/amp llms.txt file
ooooooooooooooooooop/agent-tools · research/agent-harness-survey-v1/changelogs/amp/llms.txt
git:20260921.a69e78d · audit A · 4 stars
llms.txt@research/agent-harness-survey-v1/changelogs/qoder llms.txt file
ooooooooooooooooooop/agent-tools · research/agent-harness-survey-v1/changelogs/qoder/llms.txt
git:20260921.a69e78d · audit A · 4 stars
llms.txt@research/agent-harness-survey-v1/changelogs/replit llms.txt file
ooooooooooooooooooop/agent-tools · research/agent-harness-survey-v1/changelogs/replit/llms.txt
git:20260921.a69e78d · audit A · 4 stars
chatgpt-web-bridge SKILL.md skill
ooooooooooooooooooop/agent-tools · skills/chatgpt-web-bridge/SKILL.md · 通过 chatgpt-web 的 MCP 或 REST 桥,把本地 agent 接入已登录的 ChatGPT Web。 适用于“推进/继续网页端会话”“让网页端设计、本地执行”“协作/对等推进”,以及只读拉取网页端会话/项目资料和…
git:20260921.679541d · audit A · 4 stars
clarify-before-change SKILL.md skill
ooooooooooooooooooop/agent-tools · skills/clarify-before-change/SKILL.md · 在修改前澄清范围、风险、假设与验收标准,避免误改。用于修改 Skill、AGENTS.md、项目规则、工作流规则、仓库结构、复杂代码或具有结构影响的文档,也用于优化 Skill、调整规则、重构、重组或需求不完整的场景。
git:20260828.278776e · audit A · 4 stars
decision-gates SKILL.md skill
ooooooooooooooooooop/agent-tools · skills/decision-gates/SKILL.md · 在 DSH 长程任务中为决策层加装五道防偏闸门:原始证据锚、对抗式对齐审计、跨包一致性校验、成本比对、防御自检,防止目标漂移、验收失真与摘要偏差。用于跨会话长任务、多 worker 并行、审计类任务、成本敏感任务的 checkpoint…
v0.2.0 · audit A · 4 stars
dsh-config-sync SKILL.md skill
ooooooooooooooooooop/agent-tools · skills/dsh-config-sync/SKILL.md · 把 DSH(DeepSeek Harness)的用户配置(~/.dsh 下的 AGENTS.md、settings.yaml 及可选 profiles/预设)打包成脱敏骨架并在设备间安全同步恢复,提供只读审计、显式应用与 SHA-256…
v1.0.0 · audit A · 4 stars
environment-bootstrap SKILL.md skill
ooooooooooooooooooop/agent-tools · skills/environment-bootstrap/SKILL.md · 从源仓库向其他设备或用户级 Skill 目录恢复已登记的 Codex Skill,提供只读审计、显式应用、SHA-256 校验,并且不删除目标端额外文件。用于复现 Codex 工作环境、比较已安装 Skill…
git:20260817.d6c4635 · audit A · 4 stars
evolution-proposal SKILL.md skill
ooooooooooooooooooop/agent-tools · skills/evolution-proposal/SKILL.md · 把 evolution-inbox 中的审计异常条目转化为可评审的进化提案(规则/技能/插件/路由补丁)。先做系统化问题分析(量化基线→全量聚合→根因分类→优先级排序),再用便宜模型起草、前沿模型评审、人工批准后走既有门禁固化。用于处理…
v0.3.0 · audit A · 4 stars
execution-discipline SKILL.md skill
ooooooooooooooooooop/agent-tools · skills/execution-discipline/SKILL.md · 在 DSH 长程/多工具会话中强制九条执行纪律,防止高频反模式重演:禁止无 wait 轮询、禁止把门禁拒绝当交付物抛回决策、外部研究先探测通道再极窄探针、探查派子代理不肉身…
v0.3.0 · audit A · 4 stars

Every file in ooooooooooooooooooop/agent-tools

Other files named AGENTS.md@dsh-config

AGENTS.md@dsh-config AGENTS.md file
ooooooooooooooooooop/personal-ai · dsh-config/AGENTS.md
git:20260914.0c9411e · audit A · 4 stars

Browse by kind, by grade A, or by owner.