Coding Agent Session Finder
code-yeongyu/oh-my-openagent
Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.
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。
Install Session Usage
$ npx skills add stello-agent/stello --skill session-usage -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install stello-agent/stello session-usage --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/session-usage .claude/skills/session-usage && 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 "session-usage" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/session-usage into .claude/skills/session-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-usage", 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/session-usageType 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 session-usage -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install stello-agent/stello session-usage --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/session-usage .agents/skills/session-usage && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "session-usage" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/session-usage into .agents/skills/session-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-usage", 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 session-usage -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install stello-agent/stello session-usage --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/session-usage .cursor/skills/session-usage && 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 "session-usage" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/session-usage into .cursor/skills/session-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-usage", 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/session-usage--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 session-usage -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install stello-agent/stello session-usage --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/session-usage .gemini/skills/session-usage && 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 "session-usage" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/session-usage into .gemini/skills/session-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-usage", 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 session-usageInstalls 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 session-usage -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/session-usage .github/skills/session-usage && 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 "session-usage" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/session-usage into .github/skills/session-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-usage", 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 session-usage -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 session-usage --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/session-usage .opencode/skills/session-usage && 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 "session-usage" agent skill from https://github.com/stello-agent/stello/tree/main/.agents/skills/session-usage into .opencode/skills/session-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-usage", 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
session-usage- GitHub stars
- 112
- Token cost
- ~763 tokens
- SKILL.md length
- 245 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
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。
- Tasks that involve Agent memory
- SKILL.md covers 单一 Session 模型, 上下文组装规则, 三个上下文槽位的语义 and 跨 Session 通信模型, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Session Usage is an agent skill from 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。
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Agent memory. 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.
When your agent uses it
- Tasks that involve Agent memory
Example prompts
- “/session-usage”
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
Session Usage loads about 763 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 245 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). 245 words, ~763 tokens.
Download SKILL.mdSave it as
.claude/skills/session-usage/SKILL.md (or your agent's skills folder).- name
- session-usage
- description
- 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。
Session 使用
单一 Session 模型
@stello-ai/session 只对外暴露一种 Session。对话起点是一个 parentId === null 的 root session（由 agent.createSession() 创建），其余通过 agent.forkSession() 挂在父节点下。Root 与 child 在运行时行为完全一致——差异仅在 TopologyNode.parentId。
一棵树可以有任意多 root，互相独立（森林）。
Session 始终是单次 LLM 调用原语：send() 单次调用 + 持久化，tool call 循环由 @stello-ai/core 的 Engine 驱动。
上下文组装规则
这是固定规则，不暴露扩展点（设计决策 #7）。
system prompt → session_identity(label) → insight(若有，消费后清除) → L3 历史 → 当前用户消息- system prompt 来自
getSystemPrompt(sessionId)，全局每 Session 一份。 - session_identity 由
label自动生成的<session_identity>系统消息，告知 LLM 当前所在子会话身份。 - insight 来自
getInsight(sessionId)，一次性：被消费后 send() 内置触发clearInsight。 - L3 历史 来自
listRecords(sessionId)，会先经removeIncompleteToolCallGroups净化掉因中断/崩溃残留的不完整 tool call 组。 - memory 槽位不进入 send() 上下文——它是对外暴露的描述，由 orchestrator-facing 视角消费，详见下文。
当估算 token 数超过 maxContextTokens * 0.8 时，会调用闭包注入的 compressFn，将历史压缩为一段 system 摘要，与近期消息拼接。Session 内部缓存压缩结果，避免每次 send() 都调用 compressFn。
三个上下文槽位的语义
每个 Session 在 SessionStorage 中有三个独立内容槽位：
| 槽位 | 写入者 | 消费者 | 生命周期 |
|---|---|---|---|
systemPrompt | fork 合成链固化 / 应用层 | Session.send() 组装上下文 | 持久（每次 send 读取） |
insight | Orchestrator（应用层通过 putInsight） | Session.send() 消费一次后清除 | 一次性 inbox |
memory | 应用层（通过 consolidate 输出 / 直接 putMemory） | Orchestrator-facing 反思层（listSessionDigests） | 持久（被外部读，不进 send） |
关键不变量：memory 不进入 Session 自身的 LLM 上下文。它是面向外部视角的描述——上层可以批量收集所有 Session 的 memory 做反思、规划、调度，再通过 putInsight 把派生的洞察定向回写给目标 Session。Session 自身不感知这个回路。
跨 Session 通信模型
子 Session 之间完全不感知。唯一的跨 Session 信息通道：
所有 Session 的 memory ──┐
├─→ 应用层反思层（任意 LLM）──→ putInsight(targetId, content)
┘
（StelloAgent.listSessionDigests 一次性取齐）- 反思层由应用层实现：应用层可以用任意频率、任意 LLM、任意策略对
listSessionDigests的结果做综合，再把派生 insight 定向回写。 - insight 是一次性的：每次 reflection 写入新 insight；target session 下一次 send() 注入后自动 clear。重复 reflect 不会累积。
- memory 是持久的：
putMemory的语义是替换不是追加。
fork() 的语义
Session 层 fork(options) 完成上下文继承：
- 创建一个新 Session 实例（id 由调用方传入，topology-first）
- 按
context: 'none' | 'inherit' | ForkContextFn决定是否拷贝父 session 的 L3 记录 - 不复制 memory / insight 槽位
- 一次性继承后两个 Session 互相独立
Engine 在编排层会先创建 TopologyNode（拿到 ID），再调用 session.fork({ id })。调用方通过 agent.forkSession() 一次完成两步，详见 skill fork-design。
LLM Adapter
包内置两个 adapter：OpenAI 兼容协议和 Anthropic 协议（均为 optional peerDependencies）。也可自行实现 LLMAdapter 接口，但 stream() 是必需能力，不支持 complete-only adapter。
Session 始终以 stream 作为底层传输：stream() 实时转发文本增量，send() 使用同一执行器静默消费并聚合完整结果。complete() 仅是 adapter 对直接调用方保留的流式聚合 facade，不得切回 provider 的非流式端点。
ConsolidateFn / CompressFn
- ConsolidateFn：L3 → memory 的提炼函数，由应用层定义输出格式，框架对 memory 内容格式完全无感知。
- CompressFn：超 token 阈值时把对话历史压缩为一段摘要，注入到上下文里。
- 两者都不注入 LLM——应用层通过闭包自行选择 LLM tier（设计决策 #12）。
© 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/session-usage of stello-agent/stello.
Open the folder on GitHubat commit 3bc9493
Compare with similar skills
Session Usage 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 |
|---|---|---|---|---|---|---|
| Session Usage this skillstello-agent/stello | 112 | — | ~763 | Automated safety check: Pass | Apache-2.0 | |
| Coding Agent Session Findercode-yeongyu/oh-my-openagent | 70k | 1 repos | ~2.8k | Automated safety check: Pass | Custom licence | |
| Claude-Mem Cloud Syncthedotmack/claude-mem | 98k | 1 repos | ~1k | Automated safety check: Notes | Apache-2.0 | |
| Cognee CLI Memory Commandstopoteretes/cognee | 32k | 1 repos | ~2.2k | Automated safety check: Notes | Apache-2.0 | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Claude-Mem Searchthedotmack/claude-mem | 98k | 1 repos | ~511 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Claude-Mem Cloud Sync
thedotmack/claude-mem
Checks claude-mem cloud sync status and guides you through connecting a cmem.ai Pro account without the sync token ever passing through the chat.
Cognee CLI Memory Commands
topoteretes/cognee
Drives cognee from the terminal with remember, recall, forget and improve memory commands, dataset and config management and database migrations.
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
Claude-Mem Search
thedotmack/claude-mem
Searches the user's persistent cross-session memory for timestamped observations synthesized from past agent sessions on cmem.ai.
Beads Task Memory
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
More from stello-agent/stello
All 12 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。
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.
Storage Design
stello-agent/stello
存储接口的设计原则、SessionMeta 与 TopologyNode 解耦、上下文槽位、单一 SessionStorage 接口。触发条件：理解或实现 SessionStorage / SessionTree。
Related
Categories
Questions about Session Usage
What does Session Usage do?
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。. Session Usage is an agent skill from stello-agent/stello.
When should I use Session Usage?
Session Usage fits situations like: tasks that involve Agent memory.
How do I install Session Usage in Claude Code?
Run `npx skills add stello-agent/stello --skill session-usage -a claude-code`. Or copy the skill folder (.agents/skills/session-usage in stello-agent/stello) into .claude/skills/session-usage in your project. Claude Code loads it when a task matches its description.
How do I install Session Usage in Codex?
Run `npx skills add stello-agent/stello --skill session-usage -a codex`. Or copy the skill folder (.agents/skills/session-usage in stello-agent/stello) into .agents/skills/session-usage in your project. Codex loads it when a task matches its description.
Can I use Session Usage 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 session-usage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/session-usage, .gemini/skills/session-usage, .github/skills/session-usage and .opencode/skills/session-usage in your project.
What does Session Usage need to run?
SKILL.md names no scripts, command-line tools or credentials: Session Usage is instructions for the agent only.
Does Session Usage 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 Session Usage 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 Session Usage use?
Session Usage 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 Session Usage use?
About 763 tokens (SKILL.md is roughly 3.1k 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 Session Usage?
Skills that share tags, products or a category with Session Usage: Coding Agent Session Finder (code-yeongyu/oh-my-openagent, 70k stars), Claude-Mem Cloud Sync (thedotmack/claude-mem, 98k stars), Cognee CLI Memory Commands (topoteretes/cognee, 32k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Session Usage?
stello-agent (a GitHub organization) maintains it in stello-agent/stello, which has 112 GitHub stars. The repository holds 12 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.