Home / ooooooooooooooooooop / agent-tools · research/agent-harness-survey-v1/changelogs/amp/llms.txt · GitHub

llms.txt@research/agent-harness-survey-v1/changelogs/amp llmstxtA

This file is byte-identical to the first copy the registry indexed. Same content hash, same audit grade.

llms.txt@research/agent-harness-survey-v1/changelogs/amp is agent-read markdown (llmstxt) from ooooooooooooooooooop/agent-tools.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Amp

Amp is a coding agent and development environment built for the frontier.

This is an index of the Amp documentation for agents and other programmatic readers.
Each link below serves the raw Markdown rendition of a page.
The human-readable HTML version of a page is at https://ampcode.com/docs with the
`/markdown` path segment removed (for example https://ampcode.com/docs/prompting).

## Get Started

- [Introduction](https://ampcode.com/docs/markdown): Amp is a coding agent and development environment built for the frontier. Learn what Amp does, install it, and run your first agent.
- [The Dial](https://ampcode.com/docs/markdown/the-dial): Choose a mode, tune its models, and add your own agents to the dial.
- [Modes & Models](https://ampcode.com/docs/markdown/models-and-subagents): Understand the models and specialist agents Amp uses.
- [Prompting](https://ampcode.com/docs/markdown/prompting): Write prompts and work with messages, files, and other threads.
- [Designing UI](https://ampcode.com/docs/markdown/designing-ui): Explore UI designs from screenshots, refine a direction, and build it in your app.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add ooooooooooooooooooop/agent-tools/research/agent-harness-survey-v1/changelogs/amp/llms.txt@git:20260921.a69e78d
Exact content
mdr add ooooooooooooooooooop/agent-tools/research/agent-harness-survey-v1/changelogs/amp/llms.txt@sha256:0d7504b5f9ef0b88

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_k6winemwaneyhhzk.svg)](https://markdownregistry.com/a/art_k6winemwaneyhhzk)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260921.a69e78d latest2026-09-21 a69e78d 7,187 BA view

Audit of the latest version

A  14 of 14 checks passed. Deterministic, no model, same answer every run.
  • pass: Size between 200 bytes and 200 KB (7187 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 · 3 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_k6winemwaneyhhzk
GET https://markdownregistry.com/api/v1/resolve?ref=ooooooooooooooooooop/agent-tools/research/agent-harness-survey-v1/changelogs/amp/llms.txt
GET https://markdownregistry.com/api/v1/blob/0d7504b5f9ef0b88d376c143a2bd91b3d56d232c8526af73133b6f92c7991a34

Your agent 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.

More from ooooooooooooooooooop/agent-tools

AGENTS.md agents
ooooooooooooooooooop/agent-tools · AGENTS.md
git:20260920.3367b72 · audit A · 3 stars
your-skill-name 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 · 3 stars
AGENTS.md@dsh-config agents
ooooooooooooooooooop/agent-tools · dsh-config/AGENTS.md
git:20260914.0c9411e · audit A · 3 stars
llms.txt@research/agent-harness-survey-v1/changelogs/qoder llmstxt
ooooooooooooooooooop/agent-tools · research/agent-harness-survey-v1/changelogs/qoder/llms.txt
git:20260921.a69e78d · audit A · 3 stars
llms.txt@research/agent-harness-survey-v1/changelogs/replit llmstxt
ooooooooooooooooooop/agent-tools · research/agent-harness-survey-v1/changelogs/replit/llms.txt
git:20260921.a69e78d · audit A · 3 stars
agent-switchboard-ops skill
ooooooooooooooooooop/agent-tools · skills/agent-switchboard-ops/SKILL.md · 以"管理者—执行者"模式运维 agent-switchboard MCP:受管 Claude supervisor 生命周期、跨模型委派(Codex/Claude/Gemini)、验收纪律与已知陷阱对策。 用于存在任一可用委派通道(mcp_…
git:20260826.7877509 · audit A · 3 stars
chatgpt-web-bridge 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 · 3 stars
clarify-before-change 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 · 3 stars
decision-gates 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 · 3 stars
dsh-config-sync 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 · 3 stars
environment-bootstrap 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 · 3 stars
evolution-proposal 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 · 3 stars

Every file in ooooooooooooooooooop/agent-tools

Other files named llms.txt@research/agent-harness-survey-v1/changelogs/amp

llms.txt@research/agent-harness-survey-v1/changelogs/amp llmstxt
ooooooooooooooooooop/personal-ai · research/agent-harness-survey-v1/changelogs/amp/llms.txt
git:20260921.a69e78d · audit A · 3 stars

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