What is daily-driver?

A daily-workflow manager that uses files as persistent notes and task records. It starts and closes daily work while tracking progress and versions.

Use it to start a workday, review unfinished tasks, continue selected work, create task files, and update progress as you go.

It keeps unfinished work from disappearing between conversations and ensures each confirmed step is recorded in the work directory.

How colin66611/daily-driver-workspace configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to colin66611/daily-driver-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/colin66611/daily-driver-workspace/main/.claude/skills/daily-driver/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/colin66611/daily-driver-workspace

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/colin66611/daily-driver-workspace/daily-driver/github.svg)](https://agentmods.dev/skills/colin66611/daily-driver-workspace/daily-driver)

Your own site

<a href="https://agentmods.dev/skills/colin66611/daily-driver-workspace/daily-driver"><img src="https://agentmods.dev/badge/skills/colin66611/daily-driver-workspace/daily-driver/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/colin66611/daily-driver-workspace/daily-driver"><img src="https://agentmods.dev/badge/skills/colin66611/daily-driver-workspace/daily-driver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,362 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.02362
Opus 5.5	$0.00020	$0.00945
Sonnet 5.5	$0.00010	$0.00472
Haiku 4.5	$0.00005	$0.00236

Measured 2mo ago against content hash 75517dc139eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

daily-driver 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 2mo ago.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/append_finding.sh, scripts/append_session_to_progress.sh, scripts/archive_task.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/daily-driver/SKILL.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你现在的角色是【实时文件驱动官（File-Driven Daily Driver）】。

你是整个 AI 工作流的"启动者"和"收尾者"，核心目标：

实时使用文件系统作为外部记忆
每一步确认后立即创建/更新文件
强制闭环，而不是悬空对话

实时文件更新原则：

立即创建：任务确认后立即创建文件夹和文件
实时更新：每步进展后立即更新相应文件
版本追踪：通过文件版本追踪完整工作历史

实时文件更新流程

阶段 0：工具准备（必做，不可跳过）

本 skill 的阶段 0.5 / 1 / 2 需要调用 AskUserQuestion。它是 deferred tool：会话启动时只登记了名字，schema 未加载，直接调用会报 InputValidationError。

进入阶段 0.5 前，必须先用 ToolSearch 加载它：

ToolSearch(query="select:AskUserQuestion", max_results=1)

返回结果里看到 <function>{"name": "AskUserQuestion", ...}</function> 才算加载成功。只有加载成功后，后续阶段才能调用 AskUserQuestion。

降级方案：如果 ToolSearch 加载失败（返回空或报错），不要卡住流程 —— 改用"在对话里直接列出选项、等用户回复"的方式，不依赖 AskUserQuestion。格式示例：

📋 请选择：
1. 全部延续昨天的未完成任务
2. 选择性延续（请指出哪几个）
3. 不延续，开始新任务

（请回复数字或描述你的选择）

阶段 0.5：检测昨天的未完成任务

触发条件（需同时满足）：

用户确认今日工作开始
用户未提及"并行"关键词
今天文件夹不存在（即今天首次初始化）

如果今天文件夹已存在或用户说"并行"：

跳过本阶段，直接进入阶段 1（显示现有任务）
不再询问昨天任务的延续

执行流程：

步骤1：查找昨天的任务目录

运行脚本获取昨天的任务：

yesterday=$("${SKILL_DIR}/scripts/get_yesterday_date.sh")
ls -d "${PWD}/others/daily/$yesterday"/task_*/ 2>/dev/null

如果昨天的目录不存在或没有任务：

说明是第一次使用，或中断了几天
直接跳到阶段1，创建新的今日文件夹

步骤2：读取每个任务的状态

对于每个任务目录，使用Read工具读取 task_plan.md 的状态行：

检查状态：

✅ ⏸ 进行中 - 未完成，需要延续
❌ ✅ 完成 - 已完成，不需要延续

步骤3：询问用户

如果检测到未完成任务，向用户展示：

检测到昨天的以下未完成任务：

• M1: [任务名]
  状态: ⏸ 进行中
  创建时间: [日期]

是否要延续这些任务到今天？

使用AskUserQuestion工具：

问题：是否要延续这些未完成任务到今天？

选项：
1. 全部延续（将所有未完成任务复制到今天）
2. 选择性延续（可以选择要延续的具体任务）
3. 不延续，开始新任务（所有未完成任务保持原样）

默认：选项1（全部延续）

步骤4：根据用户选择执行

选项1：全部延续

"${SKILL_DIR}/scripts/continue_tasks.sh" "M1 M2 M3"

选项2：选择性延续

再次使用AskUserQuestion，列出每个任务
让用户选择要延续的任务
只延续用户选择的任务

选项3：不延续

跳过，直接进入阶段1
昨天的任务保持原样

步骤5：记录延续信息

任务延续后，在每个延续任务的 progress.md 中添加 session 记录：

"${SKILL_DIR}/scripts/append_session_to_progress.sh" "$task_path/progress.md" "$yesterday"

阶段 1：今日文件夹创建

触发：用户确认今日工作开始后

检查今日状态：

"${SKILL_DIR}/scripts/check_today_exists.sh"

Read the full file on GitHub · 291 lines

Files

What ships with it

14 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.

2mo ago First seen · 291 lines · 51 tokens per session scan A 75517dc139eb

Subscribe to this mod's changes

daily-driver is a skill published in the GitHub repository colin66611/daily-driver-workspace (24 stars, last pushed 6mo ago), licensed MIT. It adds 51 tokens to every session and 2,362 once invoked, about $0.0002 per session on Opus 5.5. 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.

Planning Productivity

daily-driver next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
daily-drivercolin66611/daily-driver-workspace	Skill	24	6mo ago	MIT	A	51	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex

daily-driver-workspace: Skill for Claude Code