12-week-year

12-week-year is a skill for Claude Code, Codex from muyuhill/100books-to-skills. It costs 67 tokens per session (1,735 once invoked), scanned A, original, MIT.

A 12-week planning and execution framework from Brian Moran’s book The 12 Week Year. It replaces a long annual plan with short cycles containing measurable goals, weekly plans, time blocks, and progress scores.

In plain words
What is it for?
Turning a vision into two or three measurable goals, planning weekly actions, tracking execution, scheduling focused work, and reviewing progress every 12 weeks.
Why use it?
A year can feel distant enough to encourage delay. Twelve-week cycles create a shorter deadline and regular checks on whether planned actions are happening.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Turning a vision into two or three measurable goals, planning weekly actions, tracking execution, scheduling focused work, and reviewing progress every 12 weeks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/muyuhill/100books-to-skills/12-12-week-year
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 muyuhill/100books-to-skills --skill 12-12-week-year
Clone the repo
git clone --depth 1 https://github.com/muyuhill/100books-to-skills

Made for: Claude Code, Codex.

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 12-week-year

README.md
[![agentmods](https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/12-12-week-year/github.svg)](https://agentmods.dev/skills/muyuhill/100books-to-skills/12-12-week-year)
Your own site
<a href="https://agentmods.dev/skills/muyuhill/100books-to-skills/12-12-week-year"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/12-12-week-year/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 12-week-year

Your own site · 80×15
<a href="https://agentmods.dev/skills/muyuhill/100books-to-skills/12-12-week-year"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/12-12-week-year.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,735 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.01735
Opus 5 $0.00034 $0.00868
Sonnet 5 $0.00013 $0.00347
Haiku 4.5 $0.00007 $0.00173

Measured 12d ago against content hash f7fc0e375001, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

12-week-year 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 12d 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.

skills/12周工作法-12-week-year/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The 12 Week Year — 把一年当 12 周过的执行系统

年度目标的问题不是目标本身,是周期太长。你觉得「还有 11 个月呢」→ 10 个月过去了 → 最后两周冲刺 → 失败 → 明年再定新目标。

这本书的方案:把一年拆成 12 个「12 周年」。 每 12 周就是一个完整的「年」——有计划、有执行、有评估。一年不是 12 个月,是 4 个 12 周冲刺周期。


核心概念:摒弃「年化思维」

为什么年度计划会失败

  • 年初:雄心勃勃,感觉时间无限
  • 3 月:开始松懈,反正还有 9 个月
  • 9 月:有点慌,但还在拖
  • 12 月:疯狂冲刺两周 → 失败 → 下一年再来

12 周的威力:12 周足够做成大事(比你以为的短),又足够短让你有紧迫感(比年度计划紧)。

周期化(Periodization)

运动员训练靠周期化——不是全年匀速练,而是分成赛季前、赛季中、恢复期。你的工作也一样:12 周冲刺 → 休息 → 下一个 12 周冲刺。


执行系统:3 个原则 + 5 项修炼

三大原则

  1. 问责 = 所有权:不是别人盯着你,是你自己拥有结果。不完成不是老板的问题,是你的问题。
  2. 兴趣 vs 承诺:有兴趣你会找时间,有承诺你会创造时间。区别在于「没有退路」。
  3. 当下的伟大:结果不在未来,在每一天的每一次选择。此刻你选择刷手机还是做那件事,决定了 12 周后的结果。

五项修炼

# 修炼 怎么做
1 愿景 写下 12 周后你想要的生活/事业是什么样
2 12 周计划 把愿景翻译成 2-3 个具体可衡量的目标
3 流程控制 每周计划 + 每周记分卡 — 这就是你的「方向盘」
4 记分 每周给自己打分。不记分 = 不知道进度 = 一定会偏
5 时间利用 三个时间块:战略块(最重要任务)、缓冲块(杂务)、休息块

框架:愿景 → 12 周计划 → 周计划 → 执行

┌─────────────────────────────────────────────────────────┐
│  愿景:12 周后我想成为什么样?                            │
│    ↓                                                    │
│  12 周目标:选 2-3 个,每个可衡量(不是"变好",是"完成X")│
│    ↓                                                    │
│  每周战术:为每个目标拆出本周做什么                        │
│    ↓                                                    │
│  每日执行:每天最重要的 1-3 件事必须完成                   │
│    ↓                                                    │
│  每周记分:完成率打分(%),追踪趋势                      │
└─────────────────────────────────────────────────────────┘

12 周目标设定

  • 最多 2-3 个。多了等于没有。
  • 可衡量:"写 12 篇文章"(✔) vs "提高写作能力"(✘)
  • 结果导向:"收入增加 5000 元"(✔) vs "努力工作"(✘)

周计划模板

每周一写下:

  1. 本周为每个 12 周目标要做的战术动作(不是"继续做",是具体的)
  2. 每天最重要的 1-3 件事
  3. 哪些事要说「不」(保护你的战略时间)

每周记分卡

周末给每个战术动作打分:

  • ✅ 完成 = 1 分
  • ❌ 未完成 = 0 分

算出百分比。85% 以上是优秀。低于 65% 需要调整——要么战术不对,要么你在逃避。


时间块系统

块类型 干什么 时长建议
战略块 最重要、最需要专注的任务 每天 2-3 小时
缓冲块 处理邮件、杂务、低能量任务 每天 1-2 小时
休息块 不工作。真的不工作。 每周至少半天

Read the full file on GitHub · 153 lines

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. 12d ago First seen · 153 lines · 67 tokens per session scan A f7fc0e375001

Subscribe to this mod's changes

12-week-year is a skill published in the GitHub repository muyuhill/100books-to-skills (12 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,735 once invoked, about $0.0003 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.

Related

Other skills, from other repositories