Codex 助手

AI 智能社区

作者仓库星标 0
作者仓库 skills-registry

解读按原文结构重写，命令、链接、术语均保留；右侧可核对作者原始 SKILL.md

原文结构

Default path：Prefer pip install "mnemos-memory[mcp]" and mnemos ui. Treat the blessed Codex setup as two parts: MCP config plus a repo-level AGENTS.md memory block. Read references/install.md for install and validation.
Claim discipline：Safe to claim: Mnemos works in Codex through MCP, shared MNEMOSCONFIGPATH, repo-level AGENTS.md, and optional maintenance Automations. Do not claim built-in prompt/tool lifecycle hooks or Claude Code parity. Hard auto-capture in Codex is host-dependent and not…
Daily loop：Start in recall mode: call mnemosretrieve with a task-focused query and repo-scoped arguments. Do the work, then switch to curator mode: store only durable facts with mnemosstore. Use mnemosinspect before storing a correction or when a retrieved memory looks…

适用与边界

当前原文没有单列适用场景。
Avoid：Do not present Codex Automations as session capture. Do not tell users to type memories manually as the primary workflow. Do not market Codex as Tier 1 until real daily-use validation is complete.

原文中的明确线索

要点：「Use this skill to put Mnemos on the supported Codex path without overstating host automation.」、「- Prefer pip install "mnemos-memory[mcp]" and mnemos ui.」、「- Safe to claim: Mnemos works in Codex through MCP, shared MNEMOSCONFIGPATH, repo-level AGENTS.md, and optional maintenance Automations.」、「1. Start in recall mode: call mnemosretrieve with a task-focused query and repo-scoped arguments.」、「- Use at the start of coding, debugging, review, or handoff tasks.」、「- Use during or near the end of a substantial task.」、「- Do not present Codex Automations as session capture.」、「--- > Source: anthony-maio/mnemos — distributed by TomeVault.」
文件与命令：pip install "mnemos-memory[mcp]"、mnemos ui、AGENTS.md、references/install.md、references/operations.md、MNEMOSCONFIGPATH、mnemosretrieve、mnemosstore

流狐整理：以上内容来自当前 SKILL.md 的章节与原词；未补写作者没有声明的工具、兼容性或能力。

Mnemos for Codex

Use this skill to put Mnemos on the supported Codex path without overstating host automation. In Codex, the practical Mnemos workflow is:

recall at the start of substantial work
curate durable facts during or after the task
consolidate before finishing

Default path

Prefer pip install "mnemos-memory[mcp]" and mnemos ui.
Treat the blessed Codex setup as two parts: MCP config plus a repo-level AGENTS.md memory block.
Read references/install.md for install and validation.
Read references/operations.md for daily use, troubleshooting, and honest capability framing.

Claim discipline

Safe to claim: Mnemos works in Codex through MCP, shared MNEMOS_CONFIG_PATH, repo-level AGENTS.md, and optional maintenance Automations.
Do not claim built-in prompt/tool lifecycle hooks or Claude Code parity.
Hard auto-capture in Codex is host-dependent and not shipped by Mnemos today.

Daily loop

Start in recall mode: call mnemos_retrieve with a task-focused query and repo-scoped arguments.
Do the work, then switch to curator mode: store only durable facts with mnemos_store.
Use mnemos_inspect before storing a correction or when a retrieved memory looks suspicious.
Finish substantial work with mnemos_consolidate.
If Mnemos MCP tools are unavailable, continue normally instead of blocking work.

Recall mode

Use at the start of coding, debugging, review, or handoff tasks.
Query for architecture, current repo conventions, recent fixes, environment quirks, and user preferences that matter for this task.
In Codex, prefer current_scope=project, scope_id=<workspace or repo name>, and allowed_scopes=project,global.

Curator mode

Use during or near the end of a substantial task.
Store decisions, constraints, environment facts, recurring bug patterns, and stable preferences.
Skip one-off chatter, ephemeral plans, stack traces without reusable lessons, and secrets.

Avoid

Do not present Codex Automations as session capture.
Do not tell users to type memories manually as the primary workflow.
Do not market Codex as Tier 1 until real daily-use validation is complete.

Source: anthony-maio/mnemos — distributed by TomeVault.

流狐档案作者与许可取自来源；运行、权限和网络为流狐检测或估算

流狐分类: AI 智能
作者声明 Agent: 未找到明确声明；不据此推断已兼容或已测试
静态检查: 88 / 100 · 启发式扫描，不代表运行安全
作者 / 版本 / 许可: @tomevault-io · 未声明 license
流狐 Token 估算: 低消耗
流狐接入估算: 即装即用
是否需要外部 API Key: 未发现要求
检测到的系统要求: 未声明
底层运行要求: 未声明
检测到的文件与系统行为: 只读
检测到的网络行为: 仅限本地
安装命令数: 无（仅作为资料）

档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。

需要注意： 未限定 allowed-tools，默认拥有全部工具权限。

输出预览 mnemos-codex.preview

作者没有在当前 SKILL.md 中定义固定输出样例。

SKILL.md SKILL.md

# Mnemos for Codex

Use this skill to put Mnemos on the supported Codex path without overstating host automation. In Codex, the practical Mnemos workflow is:

- recall at the start of substantial work
- curate durable facts during or after the task
- consolidate before finishing

## Default path

- Prefer `pip install "mnemos-memory[mcp]"` and `mnemos ui`.
- Treat the blessed Codex setup as two parts: MCP config plus a repo-level `AGENTS.md` memory block.
- Read `references/install.md` for install and validation.
- Read `references/operations.md` for daily use, troubleshooting, and honest capability framing.

## Claim discipline

- Safe to claim: Mnemos works in Codex through MCP, shared `MNEMOS_CONFIG_PATH`, repo-level `AGENTS.md`, and optional maintenance Automations.
- Do not claim built-in prompt/tool lifecycle hooks or Claude Code parity.
- Hard auto-capture in Codex is host-dependent and not shipped by Mnemos today.

## Daily loop

1. Start in recall mode: call `mnemos_retrieve` with a task-focused query and repo-scoped arguments.
2. Do the work, then switch to curator mode: store only durable facts with `mnemos_store`.
3. Use `mnemos_inspect` before storing a correction or when a retrieved memory looks suspicious.
4. Finish substantial work with `mnemos_consolidate`.
5. If Mnemos MCP tools are unavailable, continue normally instead of blocking work.

## Recall mode

- Use at the start of coding, debugging, review, or handoff tasks.
- Query for architecture, current repo conventions, recent fixes, environment quirks, and user preferences that matter for this task.
- In Codex, prefer `current_scope=project`, `scope_id=<workspace or repo name>`, and `allowed_scopes=project,global`.

## Curator mode

- Use during or near the end of a substantial task.

…

证据边界与执行链路

作者原文负责流程事实；流狐只索引当前章节、要点、文件与命令。

章节    -> Default path → Claim discipline → Daily loop → Recall mode → Curator mode → Avoid
要点    -> Use this skill to put Mnemos on the supported Codex path without overstating host automation. · - Prefer pip install "mnemos-memory[mcp]" and mnemos ui. · - Safe to claim: Mnemos works in Codex through MCP, shared MNEMOSCONFIGPATH, repo-level AGENTS.md, and optional maintenance Automations. · 1. Start in recall mode: call mnemosretrieve with a task-focused query and repo-scoped arguments. · - Use at the start of coding, debugging, review, or handoff tasks. · - Use during or near the end of a substantial task. · - Do not present Codex Automations as session capture. · --- > Source: [anthony-maio/mnemos](https://github.com/anthony-maio/mnemos) — distributed by [TomeVault](https://tomevault.io).
文件/命令 -> pip install "mnemos-memory[mcp]" · mnemos ui · AGENTS.md · references/install.md · references/operations.md · MNEMOSCONFIGPATH · mnemosretrieve · mnemosstore
内容 SHA-256 -> b24ecd650de6