local-file-organizer

local-file-organizer is a skill for Claude Code, Codex from patrick-fu/awesome-skills. It costs 36 tokens per session (2,304 once invoked), scanned A, original, MIT.

A file-organization guide for examining a messy directory file by file and grouping or renaming items by their actual purpose. It also keeps a reversible record of approved changes.

In plain words
What is it for?
Use it to inventory files, plan or carry out safe reorganization, handle uncertain items, and review what the files reveal when explicitly requested.
Why use it?
It reduces the risk of misclassifying, losing, or permanently deleting files while making a directory easier to maintain.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions subagents.

Part of the personal-setup plugin — 2 skills shipped together

Good fit Use it to inventory files, plan or carry out safe reorganization, handle uncertain items, and review what the files reveal when explicitly requested.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/patrick-fu/awesome-skills/local-file-organizer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add patrick-fu/awesome-skills --skill local-file-organizer
Clone the repo
git clone --depth 1 https://github.com/patrick-fu/awesome-skills

Made for: Claude Code, Codex.

Or install personal-setup, the plugin that ships this one along with the rest of its 2 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for local-file-organizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/local-file-organizer/github.svg)](https://agentmods.dev/skills/patrick-fu/awesome-skills/local-file-organizer)
Your own site
<a href="https://agentmods.dev/skills/patrick-fu/awesome-skills/local-file-organizer"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/local-file-organizer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for local-file-organizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/patrick-fu/awesome-skills/local-file-organizer"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/local-file-organizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.02304
Opus 5 $0.00018 $0.01152
Sonnet 5 $0.00007 $0.00461
Haiku 4.5 $0.00004 $0.00230

Measured 11d ago against content hash dc5b3086f608, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

local-file-organizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

local-file-organizer/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local File Organizer

整理的交付物不是“看起来整齐”,而是一个可解释、可回滚、能继续维护的系统。

选择分支

只走用户需要的分支,完成后即停止:

  • 盘点:只读检查并给出结构、命名与清理方案。
  • 执行:在盘点后按已授权的变更账本移动、重命名或去重。
  • 复盘:仅在用户明确要求时,从已检查的材料提炼人生与工作线索。读取 复盘规则;不因整理文件而自动生成。

选择整理深度

  • 标准模式:适合快速梳理或规模很大的同质资料;允许按可解释规则分组。
  • 原子化深度模式:递归到安全最小单元,逐文件理解、分类和命名。用户提出“深度梳理” “全部拆解”“具体到每个文件”或不保留原目录时使用;该模式禁止用抽样代替逐项结论。

安全最小单元通常是单个文件;存在内部路径引用的代码仓库、应用包、照片图库、设计工程、 媒体项目或依赖目录是完整性包。先把完整性包作为一个原子,只有用户明确授权拆包后, 才继续分析其内部文件。

安全契约

  • 先解析目标的绝对路径、排除项与每个空间的用途。现有目录是线索,不是分类真相。
  • 默认保持可逆。把不确定项放入 ReviewPendingDelete;可用系统废纸篓时优先使用。
  • 单独标出符号链接、硬链接、云端占位文件、完整性包、权限边界及跨卷移动。
  • 区分内容归属与文件系统所有者。默认保留 UID/GID、ACL、权限、扩展属性和时间信息; 分类整理不构成 chownchmod 或权利转移授权。
  • 只读取完成分类所需的最少内容。报告中省略证件号、地址、账户、健康、合同等敏感细节。
  • 永久删除需要对当前清单中明确类别的单独授权。“清理一下”不构成删除授权。
  • 跨卷或云盘操作先复制并验证,再处理源文件;目标未验证前,源文件保持不变。

工作流

1. 建立空间契约

为每个根目录确定一个主要职责,例如 CurrentWorkInboxArchiveMediaWorkPersonalVault。若职责无法从请求中可靠判断,用普通文本给出 2–3 个 方案,标注推荐项及一句取舍。

记录:

  • 目标与排除路径
  • 空间职责
  • 用户要盘点、执行还是复盘
  • 标准模式或原子化深度模式
  • 可接受的改名、移动与删除范围

完成标准:每个根目录只有一个主要职责,边界与授权无歧义。

2. 建立证据清单

先只读盘点。沿证据阶梯逐级深入,证据足够判断用途即停止:

  1. 原始路径、名称、类型、逻辑大小和时间;
  2. UID/GID、权限、ACL、扩展属性、链接与云端状态;
  3. EXIF、媒体标签、文档属性、PDF 元数据、项目清单等格式元数据;
  4. 文本提取、OCR、图片视觉分析、音视频转写等内容检查;
  5. 与相邻文件、版本、项目和时间线的关系。
  • 先判断真实用途,再决定归宿;原目录名称只提供上下文。
  • 分开记录内容归属/权利与技术所有者。内容归属可使用 PersonalEmployer/CompanyClient/CollaboratorFamily/SharedThirdParty/LicensedUnknown,并按实际材料调整。
  • 标准模式可以为同质文件建立证据分组,但决定删除时不得依赖抽样。
  • 原子化深度模式递归枚举每个叶子文件和完整性包;每项单独记录,不保留“因数量太多而 未读”的模糊分组。
  • 文件名相似只产生“疑似重复”;大小一致并经内容哈希确认后才是“完全重复”。
  • 相似照片、不同导出、版本稿和项目内副本是独立审查项,不并入完全重复。

完成标准:标准模式中的每项均被记录或落入有规则、有数量的证据分组;原子化深度模式中, 每个叶子文件或未拆完整性包都有稳定 ID、用途、内容归属、证据、拟议名称与目标位置。 权限、加密、损坏等无法判断的项目明确标为 Unknown,不得静默跳过。

3. 分片只读分析

当文件量大、格式多且宿主支持 sub-agent 时,可把内容判断分成互不重叠的只读批次:

  • 主代理先冻结范围、分类词表、稳定 ID 和输出字段,再按目录、格式或时间切片。
  • 每个 sub-agent 只接收必要上下文而非完整对话历史,读取分配清单并返回证据、用途、 内容归属/权利、建议名称、目标位置、置信度和未决问题。
  • sub-agent 不移动、重命名、删除文件,也不自行扩展范围。
  • 主代理合并唯一账本,复核低置信度、敏感、冲突及高风险项目。

完成标准:所有分片均已返回或明确失败;ID 无遗漏、无重叠;冲突由主代理统一裁决。

Read the full file on GitHub · 167 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 167 lines · 36 tokens per session scan A dc5b3086f608

Subscribe to this mod's changes

local-file-organizer is a skill published in the GitHub repository patrick-fu/awesome-skills (58 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 2,304 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.