audit-dirty-memories
随机抽检 default memory 的长期记忆,回溯 source_ref 原始上下文,识别疑似脏记忆并向用户汇报证据。
Skill by namei32
Chalk Labs
Need help deploying audit-dirty-memories?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/namei32-audit-dirty-memories
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/audit-dirty-memories
What's inside
- Skill name
audit-dirty-memories- Description
- 随机抽检 default memory 的长期记忆,回溯 source_ref 原始上下文,识别疑似脏记忆并向用户汇报证据。
- License
- MIT
- Instructions
- 177 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- sample_memory_for_audit.py · scripts/
SKILL.md (first lines)
# Audit Dirty Memories
## 目标
随机抽检一条尚未审计、且带 `source_ref` 的 default memory 长期记忆。
如果原始上下文与记忆摘要一致,静默记录“已审计”并结束本轮。
如果原始上下文不能支持该摘要,或摘要明显把提问、计划、否定、条件写错成事实,
向用户说明这条记忆为什么可疑,并给出证据,等待用户在被动回复链路里纠正。
这个 skill 只做调查和汇报,不做 `forget_memory` 或 `memorize`。
## 状态来源
```text
default_memory:audit-dirty-memories
├─ scratchpad
│ └─ 自然语言前情:上一轮做到哪一步、下次怎么接
├─ cursor
│ └─ 结构化游标:active_memory_id / source_ref / summary / stage
└─ journal
└─ append-only 记录:entry_type=memory_audited 的已审计 memory_id
```
- `local_context.cursor` 是未完成候选的结构化来源。
- `local_context.journal_recent` 只用于快速了解最近审计结果。
- 已审计去重由固定脚本读取 Drift `skill_journal` 完成。
- 不读取、不创建 `history.json`、`state.json`、`audited.md`。
## 固定脚本
```bash
python3 skills/audit-dirty-memories/scripts/sample_memory_for_audit.py sample --drift-dir .
```
脚本只做抽样:读取 `skill_journal` 里 `entry_type=memory_audited` 的 key,
查询 `../memory/memory2.db`,排除已审计项后返回 1 条候选。
## 工作流程
```text
run
├─ 读 local_context.cursor
│ ├─ 有 active_memory_id -> 继续这条候选
│ └─ 没有 -> shell sample
├─ fetch_messages(source_ref, context=10)
├─ 判断 clean / suspicious_reported / unverifiable_old_source
├─ 必要时 message_push
└─ finish_drift
├─ scratchpad_update: 自然语言接续
├─ cursor_update: 清空或保留 active 候选
└─ journal_append: memory_audited
```
1. 先看 `select_skill` 返回的 `local_context.cursor`。
- 如果有 `active_memory_id`,继续审计这条候选。
- 如果没有,运行固定抽样命令。
2. 抽样命令:
```json
{
"command": "python3 skills/audit-dirty-memories/scripts/sample_memory_for_audit.py sample --drift-dir .",
"cwd": ".",
"description": "抽样一条待审计记忆",
"timeout": 60,
"yield_time_ms": 30000
}
```
3. 如果脚本返回 `{"found": false}`:
- `finish_drift(status="waiting", message_result="silent")`
- `briefing` 写“没有可审计候选”
- `scratchpad_update` 写“等待出现新的、带 source_ref 且尚未审计的 default memory 记忆”
- `cursor_update` 写 `{"next_action": "sample"}`
4. 如果脚本返回候选,记录 `memory_id`、`memory_type`、`summary`、`source_ref`、`happened_at`。
5. 用 `fetch_messages` 读取原始上下文:
- `source_ref` 直接传候选的完整值。
- `context` 固定为 `10`。
- 如果 `source_ref` 是 JSON 列表字符串,整段原样传给 `fetch_messages`,不要拆开。
- 如果候选意外仍是 `@post_response` 旧 source,视为 `unverifiable_old_source`。
6. 只做高置信判断:
- 原文只是提问或讨论,摘要却写成已知事实。
- 原文只是计划或意图,摘要却写成已经发生。
- 原文明显是否定,摘要却写成肯定。
- 原文有明显条件或时间限制,摘要却丢失了限制。
- 摘要的主体、时间、结果与原文明显冲突。
7. 不要把下面情况报成脏记忆:
- 摘要只是更短。
- 省略了不重要细节。
- 表达方式不同但核心事实一致。
- 只是感觉奇怪但拿不准。
## 收尾要求
clean 或 unverifiable_old_source:
```json
{
"skill_used": "default_memory:audit-dirty-memories",
"status": "completed",
"briefing": "审计 memory_id=...,结果 clean",
"message_result": "silent",
"scratchpad_update": "刚审计 memory_id=...,结果 clean;下次继续随机抽样。",
"cursor_update": {
"active_memory_id": null,
"source_ref": null,
"summary": null,
"stage": null,
"next_action": "sample"
},
"journal_append": [
{
"entry_type": "memory_audited",
"key": "...",
"payload": {
"result": "clean",
"source_ref": "...",
"summary": "..."
}From namei32/roxy-agent, MIT.
More from namei32/roxy-agent
- 0.526score
roxy-call
namei32
指导 Codex 或其他外部程序调用已运行的 Roxy,并用明确 thread ID 持续对话。当用户说调用 Roxy、程序化调用 Roxy、从 Codex 调用 Roxy、外部自动化调用、复用 Roxy session/thread、继续 Roxy 会话时使用。
SkillBFreshness: BClaude Code +9 - 0.523score
develop-roxy-plugin
namei32
创建、编写、修改并验证 Roxy 插件及插件内 Skill/MCP。用户要求创建 Roxy 插件、编写插件、把 skill 收入插件、验证插件、验证 skill、热重载后自测或递归自验证插件时使用。
SkillBFreshness: BClaude Code +9 - 0.521score
interview-coach
namei32
Analyze an authorized Telegram image batch as interview material, answer each question with evidence-aware expansion, archive polished text to Apple Notes…
SkillBFreshness: BClaude Code +9 - 0.521score
manage-workspace-mcp
namei32
安装、注册、更新、移除和诊断 Roxy 的独立 workspace MCP server。用户要求把 binary、CLI、脚本或本地项目做成常驻 MCP,询问 MCP 热重载、MCP 工具为何没出现,或需要查看非插件 MCP 状态时使用。插件自带 MCP 改用 plugin-system。
SkillBFreshness: BClaude Code +9 - 0.521score
codex-delegate
namei32
把长代码库任务委托给本机 Codex CLI 后台执行。当用户说用 codex skill、codexskill、codex delegate、委托 codex、后台 codex、阻塞 codex exec、subagent 跑 codex 时使用。
SkillBFreshness: BClaude Code +9 - 0.515score
skill-creater
namei32
创建或改写 Roxy 技能(SKILL.md)。当用户要求新建技能、适配现有技能到当前格式、或修改技能内容时使用。
SkillBFreshness: BClaude Code +9 - 0.515score
plugin-system
namei32
说明并执行 Roxy 插件安装、加载、配置、插件内 MCP、Skill、生命周期、卸载与 turn 边界更新。
SkillBFreshness: BClaude Code +9 - 0.510score
roxy-mobile
namei32
Roxy 手机端原型的现有主题快照;源代码 Theme Catalog 保持权威。
SkillBFreshness: BClaude Code +9 - 0.510score
akashic-call
namei32
兼容旧的 Akashic 调用 Skill 名称;请按当前 Roxy 调用合同执行。
SkillBFreshness: BClaude Code +9 - 0.510score
develop-akashic-plugin
namei32
兼容旧的 Akashic 插件开发 Skill 名称;请按当前 Roxy 插件合同执行。
SkillBFreshness: BClaude Code +9 - 0.499score
apple-notes-export
namei32
Use when the user explicitly asks Roxy to save important content to Apple Notes, or when a system-scoped Interview Coach grant authorizes the current Telegram…
SkillBFreshness: BClaude Code +9 - 0.469score
create-drift-skill
namei32
当此刻想反复进行的活动还没有合适 skill,或近期多轮行为显露出可发展的兴趣时,在 Drift 工作区创建或更新一个可再次选择的活动。
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Aug 7, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/namei32/roxy-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from namei32
- 0.526score
roxy-call
namei32
指导 Codex 或其他外部程序调用已运行的 Roxy,并用明确 thread ID 持续对话。当用户说调用 Roxy、程序化调用 Roxy、从 Codex 调用 Roxy、外部自动化调用、复用 Roxy session/thread、继续 Roxy 会话时使用。
SkillBFreshness: BClaude Code +9 - 0.523score
develop-roxy-plugin
namei32
创建、编写、修改并验证 Roxy 插件及插件内 Skill/MCP。用户要求创建 Roxy 插件、编写插件、把 skill 收入插件、验证插件、验证 skill、热重载后自测或递归自验证插件时使用。
SkillBFreshness: BClaude Code +9 - 0.521score
interview-coach
namei32
Analyze an authorized Telegram image batch as interview material, answer each question with evidence-aware expansion, archive polished text to Apple Notes…
SkillBFreshness: BClaude Code +9 - 0.521score
codex-delegate
namei32
把长代码库任务委托给本机 Codex CLI 后台执行。当用户说用 codex skill、codexskill、codex delegate、委托 codex、后台 codex、阻塞 codex exec、subagent 跑 codex 时使用。
SkillBFreshness: BClaude Code +9 - 0.521score
manage-workspace-mcp
namei32
安装、注册、更新、移除和诊断 Roxy 的独立 workspace MCP server。用户要求把 binary、CLI、脚本或本地项目做成常驻 MCP,询问 MCP 热重载、MCP 工具为何没出现,或需要查看非插件 MCP 状态时使用。插件自带 MCP 改用 plugin-system。
SkillBFreshness: BClaude Code +9 - 0.515score
plugin-system
namei32
说明并执行 Roxy 插件安装、加载、配置、插件内 MCP、Skill、生命周期、卸载与 turn 边界更新。
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get audit-dirty-memories running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
audit-dirty-memories skill. Agent Mart. https://agentmart.dev/skills/namei32-audit-dirty-memories (last updated 2026-10-24)