Round Verification
SeemSeam/claude_codex_bridge
Verify a CCB execution round and produce a machine-readable round result artifact.
Engine 职责定义：per-session-round 生命周期管理器。驱动 tool call 循环，管理单个 Session 的多轮对话。不感知树结构，不感知调度。
Apache-2.0Auto-check passed
Install Engine Design
$ npx skills add stello-agent/stello --skill engine-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install stello-agent/stello engine-design --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/stello-agent/stello.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/engine-design .claude/skills/engine-design && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "engine-design" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/engine-design into .claude/skills/engine-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engine-design", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/stello-agent/stello/tree/main/.agents/skills/engine-designType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add stello-agent/stello --skill engine-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install stello-agent/stello engine-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/stello-agent/stello.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/engine-design .agents/skills/engine-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "engine-design" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/engine-design into .agents/skills/engine-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engine-design", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add stello-agent/stello --skill engine-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install stello-agent/stello engine-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/stello-agent/stello.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/engine-design .cursor/skills/engine-design && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "engine-design" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/engine-design into .cursor/skills/engine-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engine-design", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/stello-agent/stello.git --path .agents/skills/engine-design--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add stello-agent/stello --skill engine-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install stello-agent/stello engine-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/stello-agent/stello.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/engine-design .gemini/skills/engine-design && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "engine-design" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/engine-design into .gemini/skills/engine-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engine-design", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install stello-agent/stello engine-designInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add stello-agent/stello --skill engine-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/stello-agent/stello.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/engine-design .github/skills/engine-design && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "engine-design" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/engine-design into .github/skills/engine-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engine-design", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add stello-agent/stello --skill engine-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install stello-agent/stello engine-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/stello-agent/stello.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/engine-design .opencode/skills/engine-design && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "engine-design" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/engine-design into .opencode/skills/engine-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engine-design", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
engine-design- GitHub stars
- 112
- Token cost
- ~720 tokens
- SKILL.md length
- 272 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Engine 职责定义：per-session-round 生命周期管理器。驱动 tool call 循环，管理单个 Session 的多轮对话。不感知树结构，不感知调度。
- SKILL.md covers 定位, Engine 做什么 / 不做什么, 核心设计决策 and 错误处理原则, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Engine Design is an agent skill from stello-agent/stello. Engine 职责定义：per-session-round 生命周期管理器。驱动 tool call 循环，管理单个 Session 的多轮对话。不感知树结构，不感知调度。
Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Conversations aren't linear — why should AI chats be? The first open-source conversation topology engine. Auto-branching session trees, inherited memory, star-map visualization… The licence is Apache-2.0.
Example prompts
- “/engine-design”
What it can do on your machine
Read from SKILL.md and the folder at commit 3bc9493. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Engine Design loads about 720 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 272 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from stello-agent/stello at commit 3bc9493, republished under its Apache-2.0 licence (© stello-agent). 272 words, ~720 tokens.
Download SKILL.mdSave it as
.claude/skills/engine-design/SKILL.md (or your agent's skills folder).- name
- engine-design
- description
- Engine 职责定义：per-session-round 生命周期管理器。驱动 tool call 循环，管理单个 Session 的多轮对话。不感知树结构，不感知调度。
Engine — Per-Session-Round 生命周期管理器
定位
Engine 是 Session 原语之上的单 Session 多轮对话管理器。
- Session = 一次 LLM 调用（原子操作）
- Engine = 一个 Session 的整轮交互生命周期（多次 turn，含 tool call 循环）
- Factory = 装配层（构建 Engine，内联 consolidation 触发逻辑）
Engine 不感知树结构，不知道其他 Session 的存在，也不感知调度策略。
Engine 做什么 / 不做什么
做：tool call 循环、consolidate() 执行、hooks fire-and-forget、生命周期边界（enter/leave/archive/fork）、fork 编排（拓扑 + session 创建）、内置 tool 注册与执行（通过 CompositeToolRuntime 统一调度）、error 事件 emit
不做：调度时机判断（由 Factory hook 内联）、持有跨 Session 状态（全局反思层由应用层在 StelloAgent 之外实现）、Session 切换检测（Orchestrator）、多 Session 管理
核心设计决策
Engine 接管 Fork 编排
Engine 负责 fork 的完整编排：创建拓扑节点（topology-first，生成 ID）→ 调用 session.fork({ id, ... }) 创建 session 实例 → 触发事件。session.fork() 天然处理 systemPrompt 继承、context 继承（含 contextFn）、prompt 写入、LLM/tools/consolidateFn/compressFn 覆盖。Orchestrator 分离"拓扑父节点"（策略决定）与"fork 来源 session"（继承内容来源）。
fork 选项中的 consolidateFn 和 compressFn 遵循继承链：fork 时指定则用新的，不指定则继承父 session 的。Agent 配置中的 session.consolidateFn 作为根 session 的默认值，后续嵌套 fork 按继承链传递。这使不同 session 可以有不同的 L3→L2 提炼策略和上下文压缩策略。
内置 tool（stello_create_session、activate_skill）在 Engine 构造时通过 createBuiltinToolEntries() 生成 ToolRegistryEntry 实例，闭包捕获 Engine 上下文，与用户 tool 统一走 CompositeToolRuntime 调度。LLM 调用 stello_create_session 时，Engine 解析 ForkProfile（如有），合成 systemPrompt，profile 的 contextFn/llm/tools 直接映射到 fork 选项，profile.skills 白名单写入 session metadata（_stello.allowedSkills），再走 forkSession 完整路径。Factory 创建子 Engine 时读取 metadata，按需用 FilteredSkillRouter 包装全局 SkillRouter。
工具注册与内置工具
内置 tool 和用户 tool 统一走 ToolRegistryEntry + CompositeToolRuntime。Engine 构造时自动创建内置 entries（闭包捕获 Engine 实例），与用户 EngineToolRuntime 组合。getToolDefinitions 和 executeTool 均委托给 CompositeToolRuntime，内置 tool 优先、同名去重。用户无需手动注册内置 tool。
Consolidation 触发内联到 Factory hook
Engine 不持有 Scheduler，也不感知"全局反思"概念。Consolidation 触发逻辑（如 consolidateEveryNTurns）由 Factory 构建闭包注入 EngineHooks。Engine 在事件点 fire-and-forget 调用 hooks，不知道背后有调度。
turn() 返回值
EngineTurnResult 只包含 { turn }。调度是 fire-and-forget 的内部副作用，结果对调用方不可见。
所有 hooks fire-and-forget
hooks 抛错时 emit error 事件 + 调用 onError hook，不中断对话周期。Scheduler 闭包失败同理。
Factory 合并 hooks
用户 hooks 和 Factory 内联 hooks 在同一 key 下都能触发，由 Factory 的 mergeHooks 保证。
错误处理原则
- session.stream() 失败 → 向上抛出（核心路径；turn() 也聚合该流）
- tool.execute() 失败 → 错误信息作为 tool result 返回给 LLM，继续循环
- hook / Scheduler 闭包失败 → emit error，不影响 turn() 返回
Streaming + Tool Call 策略
session.stream()是 Engine 驱动 LLM 的唯一底层原语，每个 tool continuation 都继续使用 stream。stream()按产生顺序输出所有 LLM 子轮的文本 chunk；工具执行期间自然暂停，下一轮继续输出。turn()复用同一个 streaming tool loop，但使用空输出 sink 聚合结果，不向调用方暴露 chunk。finalContent/rawResponse始终只代表最后一个不再请求客户端 tool 的 LLM 响应；usage 聚合整轮内所有 LLM 调用。
© stello-agent, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/engine-design of stello-agent/stello.
Open the folder on GitHubat commit 3bc9493
Compare with similar skills
Engine Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Engine Design this skillstello-agent/stello | 112 | — | ~720 | Automated safety check: Pass | Apache-2.0 | |
| Round VerificationSeemSeam/claude_codex_bridge | 3.5k | — | ~228 | Automated safety check: Pass | Custom licence | |
| Round VerificationSeemSeam/claude_codex_bridge | 3.5k | — | ~486 | Automated safety check: Pass | Custom licence | |
| Release Roundethereumjs/ethereumjs-monorepo | 2.8k | — | ~2k | Automated safety check: Pass | None | |
| UI Devwidget RoundafkT/DevUtils | 1.6k | — | ~880 | Automated safety check: Pass | Apache-2.0 | |
| Cy Review Roundcompozy/compozy | 2.8k | — | ~2.7k | Automated safety check: Pass | MIT |
Similar skills
Round Verification
SeemSeam/claude_codex_bridge
Verify integrated round evidence and return a machine-readable round result for script import.
Release Round
ethereumjs/ethereumjs-monorepo
Runs a coordinated EthereumJS npm release round in six human-gated phases — intent and readiness, CHANGELOG, version bump, publish (human executes), post-publish verification, and announcements.
UI Devwidget Round
afkT/DevUtils
在需要圆角矩形纯色背景、描边边框时，优先用 DevWidget（io.github.afkt:DevWidgetX）的 dev.widget.ui.round 包替代 shape / layer-list drawable。流程与核心坑在 SKILL，Round 系列 View、R.styleable.DevWidget 中 app:dev 属性及源码对照见…
Cy Review Round
compozy/compozy
Performs a comprehensive code review of a spec implementation and generates a review round directory with issue files compatible with cy-fix-reviews.
Rounding
RConsortium/pharma-skills
Audit R code that prepares CSR/TLF statistics for SAS-compatible rounding compliance (ties away from zero, round-once-at-display, fixed trailing-zero precision).
More from stello-agent/stello
All 13 skills in this repoFork Design
stello-agent/stello
Fork 机制完整说明。覆盖 ForkProfile 与 EngineForkOptions 的字段对齐、四层 fallback 合成链（sessionDefaults → parent → profile → forkOptions）、systemPrompt 合成三种模式、skills 三态语义、持久化边界（SerializableSessionConfig 只固化…
LLM Call Sites
stello-agent/stello
Stello 框架内所有 LLM 调用位置的消息结构速查。覆盖 Session 对话、compress、consolidate；应用层 reflection 调用由 orchestrator 自行决定。
Session Usage
stello-agent/stello
Session 对话单元的设计理念、上下文组装规则、memory / insight 槽位语义、单一 Session 模型与跨 Session 通信模型。
Stello Agent Creation
stello-agent/stello
StelloAgent 创建配置教程。完整说明 createStelloAgent 的每个配置项，包含 sessionDefaults、storage、tools、skills、forkProfiles、session 层接入、orchestration 等。
Stello Agent Usage
stello-agent/stello
StelloAgent 运行时使用教程。覆盖 Session 生命周期、createSession、turn/stream 对话、fork 配置合成链、orchestrator-facing 数据 SDK、runtime 管理、热更新等运行时 API。
Stello Usage
stello-agent/stello
Stello 仓库总览入口。快速理解各包的关系、推荐入口、编排模型、单一 Session 模型. An agent skill from stello-agent/stello.
Questions about Engine Design
What does Engine Design do?
Engine 职责定义：per-session-round 生命周期管理器。驱动 tool call 循环，管理单个 Session 的多轮对话。不感知树结构，不感知调度。. Engine Design is an agent skill from stello-agent/stello.
How do I install Engine Design in Claude Code?
Run `npx skills add stello-agent/stello --skill engine-design -a claude-code`. Or copy the skill folder (.agents/skills/engine-design in stello-agent/stello) into .claude/skills/engine-design in your project. Claude Code loads it when a task matches its description.
How do I install Engine Design in Codex?
Run `npx skills add stello-agent/stello --skill engine-design -a codex`. Or copy the skill folder (.agents/skills/engine-design in stello-agent/stello) into .agents/skills/engine-design in your project. Codex loads it when a task matches its description.
Can I use Engine Design in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add stello-agent/stello --skill engine-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/engine-design, .gemini/skills/engine-design, .github/skills/engine-design and .opencode/skills/engine-design in your project.
What does Engine Design need to run?
SKILL.md names no scripts, command-line tools or credentials: Engine Design is instructions for the agent only.
Does Engine Design access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Engine Design safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Engine Design use?
Engine Design is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Engine Design use?
About 720 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Engine Design?
Skills that share tags, products or a category with Engine Design: Round Verification (SeemSeam/claude_codex_bridge, 3.5k stars), Round Verification (SeemSeam/claude_codex_bridge, 3.5k stars), Release Round (ethereumjs/ethereumjs-monorepo, 2.8k stars) and UI Devwidget Round (afkT/DevUtils, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Engine Design?
stello-agent (a GitHub organization) maintains it in stello-agent/stello, which has 112 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on July 24, 2026.
Source: stello-agent/stello on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.