Auditable Playbook Designer
cursor/plugins
Designs a step-by-step playbook for large or unfamiliar work, runs it as a loop of hypotheses and measurements, and logs decisions so a human can review them later.
Turns a one-line idea into a task brief of up to 4000 characters that an autonomous agent can run through /goal, with measured baselines and cheat-resistant acceptance checks.
SKILL.md written in Chinese; this summary is our English description.
Install Agent Goal Brief Writer
$ npx skills add KKKKhazix/khazix-skills --skill leader -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install KKKKhazix/khazix-skills leader --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/KKKKhazix/khazix-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/leader .claude/skills/leader && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "leader" agent skill from https://github.com/KKKKhazix/khazix-skills/tree/main/leader into .claude/skills/leader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "leader", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/KKKKhazix/khazix-skills/tree/main/leaderType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add KKKKhazix/khazix-skills --skill leader -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install KKKKhazix/khazix-skills leader --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KKKKhazix/khazix-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/leader .agents/skills/leader && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "leader" agent skill from https://github.com/KKKKhazix/khazix-skills/tree/main/leader into .agents/skills/leader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "leader", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add KKKKhazix/khazix-skills --skill leader -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install KKKKhazix/khazix-skills leader --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KKKKhazix/khazix-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/leader .cursor/skills/leader && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "leader" agent skill from https://github.com/KKKKhazix/khazix-skills/tree/main/leader into .cursor/skills/leader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "leader", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/KKKKhazix/khazix-skills.git --path leader--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add KKKKhazix/khazix-skills --skill leader -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install KKKKhazix/khazix-skills leader --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KKKKhazix/khazix-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/leader .gemini/skills/leader && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "leader" agent skill from https://github.com/KKKKhazix/khazix-skills/tree/main/leader into .gemini/skills/leader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "leader", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install KKKKhazix/khazix-skills leaderInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add KKKKhazix/khazix-skills --skill leader -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/KKKKhazix/khazix-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/leader .github/skills/leader && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "leader" agent skill from https://github.com/KKKKhazix/khazix-skills/tree/main/leader into .github/skills/leader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "leader", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add KKKKhazix/khazix-skills --skill leader -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install KKKKhazix/khazix-skills leader --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KKKKhazix/khazix-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/leader .opencode/skills/leader && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "leader" agent skill from https://github.com/KKKKhazix/khazix-skills/tree/main/leader into .opencode/skills/leader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "leader", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
leader- GitHub stars
- 21k
- Token cost
- ~723 tokens
- SKILL.md length
- 124 words
- Files
- 3 (incl. references)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Turns a one-line idea into a task brief of up to 4000 characters that an autonomous agent can run through /goal, with measured baselines and cheat-resistant acceptance checks.
- Works in 5 steps: 作弊达标（最重要）：说「让测试绿」，最省力的是加 .skip、放松断言、mock… → 幻觉命令：它会平静地编造命令再甩锅环境——书里每条命令你必须亲手跑过，摸不到就写进… → 失忆：进度写 PROGRESS.md，接手会话先读它别重做；任务 0 过后先写… → …
- Writing an agent goal or task brief from a rough idea
- SKILL.md covers 流程, 写书规则, 多 agent 并行（领导点头才拆） and 语言, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The SKILL.md is written in Chinese and casts three roles: you as the leader who has the idea and makes the calls, the agent running this skill as the manager who researches, writes and accepts, and a separate executor agent that runs the brief alone with no one to ask. Because the executor follows the text literally, the manager checks facts first: in a codebase it runs commands, records baseline numbers and compares the docs with reality, searches the web where it can, and marks unverified claims as assumptions.
It then asks at most five questions in one round, only about things it cannot look up, each with two to four options and a recommendation, and if you are away it uses defaults and lists them in a section on decisions it made for you. The brief itself must stay within 4000 characters, follow the six-section layout in `references/anatomy.md`, and arrive as one code block with a one-line usage note. Work is split into execution briefs, which have an acceptance command, and exploration briefs for research or selection.
Guards in the brief cover the usual failure modes: gaming the tests with skips or weakened assertions, invented commands, lost progress (kept in a PROGRESS.md file), pressing on when measured numbers differ from the plan, and silent failures that need a reverse check. When the work comes back, the manager reruns the visible acceptance checks plus two or three private spot checks and reports in five lines or fewer. Splitting into parallel agents happens only with your approval.
When your agent uses it
- Writing an agent goal or task brief from a rough idea
- Splitting a project into briefs for several agents running in parallel
- Preparing a long autonomous run with acceptance checks and a progress file
- Checking an agent's finished work against the brief
Example prompts
- “Write a goal for an agent to cut our test suite's runtime, and measure the current baseline first.”
- “Turn this idea into a brief I can paste into /goal: migrate the docs site to the new framework.”
- “Split the refactor into briefs for two agents working in parallel.”
- “The agent says it finished the goal; check the work against the brief.”
Requirements
- A codebase the agent can run commands in, for measuring baselines (optional)
- An execution agent that supports /goal, or any agent that accepts the pasted brief
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 作弊达标（最重要）：说「让测试绿」，最省力的是加 .skip、放松断言、mock 被测对象、删测试、|| true——不是它坏，是目标函数写错。对策：基线不可退（测试数／覆盖率 ≥ 基线、skipped…
- 幻觉命令：它会平静地编造命令再甩锅环境——书里每条命令你必须亲手跑过，摸不到就写进任务 0 让它查实
- 失忆：进度写 PROGRESS.md，接手会话先读它别重做；任务 0 过后先写 ≤10 行开工回执（理解的目标／顺序／最大风险）再动工；单任务一个会话内做得完
- 一条道走到黑：任务 0 兼前提核验，量出的数字对不上就停；同一验收连败 3 次换项；结果比基线差就回滚如实报告——「没做成但说清了」合格，「做了但更糟」不合格
- 静默事故：坏了不发信号的（假绿灯、失效报警器）配反向验证——亲手制造一次失败证明会响，贴输出。判据：问「这里坏了谁会知道」，答「没人」就要
What it can do on your machine
Read from SKILL.md and the folder at commit 322346d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agent Goal Brief Writer loads about 723 tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 124 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from KKKKhazix/khazix-skills at commit 322346d, republished under its MIT licence (© KKKKhazix). 124 words, ~723 tokens.
Download SKILL.mdSave it as
.claude/skills/leader/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- leader
- description
- 把一句话的想法拆成 AI agent 能独立跑完的目标任务书。用户说「帮我给 agent 写个目标」「帮我详细拆一下这个目标」「写个任务书/brief 给 agent」「写个 goal 提示词」「让 agent 自己跑这个项目」「把活分给几个 agent 并行」时使用。先进代码库实测、必要时联网调研，再一次性提问（≤5 个），产出一份 ≤4000 字符、直接粘进 /goal 就能跑的任务书，含实测数字、白名单地界、防作弊验收和断点续跑。执行型与探索型（调研/选型/找方案）自动分流。
领导 · 你出想法，我出任务书
三个角色：领导（用户）出想法、拍板；管理者（你）调研、写书、验收；执行者（目标模式里干活的 agent）拿书独立跑完。执行者一字不差地执行、把书当唯一真理、中途没人可问——写错的事实 100% 被执行，全文不许有「来找我」。
流程
**1 调研。**自己能查的一律不问。有代码库就实测：命令真的存在吗、基线数字多少、文档和实际差多少（README 写的命令不存在、lint 是 echo 占位的假绿灯、没被 import 的文件从覆盖率报告里消失——都是真坑）。行业知识能联网就查，查不到标「假设，未验证」。摸不到环境就把自测写成任务 0。
**2 提问，一轮 ≤5 个。**只问查不到且会改变任务书的：方向取舍、验收裁量、风险偏好、时间盒；每个给 2–4 个选项加推荐。要拆多份并行必须在这轮问。领导不在场就按默认走、标「猜的」、写进书里「我替领导拍的板」一节——沉默替领导拍板是越权，摆到明面是尽职。
3 写书（规则见下节）。
**4 交付。**最终回复只有三样，过程噪音（调研表格、中途更正、分析过程）一概不带：
- 一句用法：「在执行 agent 那边输
/goal，粘贴下面整段，发出去。」（/goal是斜杠命令，没有单独输入框；没有目标模式的工具就直接粘贴发送。）附导读：领导只看三处——开头「这活为什么干」两行、「我替领导拍的板」、末尾「完成条件」的两条硬指标。 - 任务书代码块，整块可复制。
- 一句收尾：「跑完回来说一声，我来验收，给你 5 行内的人话报告。」
**一个目标、一次粘贴。**不许第二条 /goal、不许让领导存文件、不许发明开工命令。
**5 验收，是管理者的活。**明卷（验收命令）在书里，目标模式自己盯；暗卷——2–3 条执行者看不见的抽查——自留在会话侧 scratchpad，不进书。领导回来喊一声，你亲自复跑明卷＋暗卷，给 ≤5 行人话报告：过没过／干成了什么／遗留问题／下一步。执行者不能自己批卷，领导全程零命令。摸不到执行环境时才退化为「验收官提示词」，让领导转贴给一个没参与执行的 agent。
写书规则
任务书六节的结构规格与探索型改法见 references/anatomy.md——它规定每节写什么，措辞和详略由你贴合任务判断。
≤4000 字符，硬上限（/goal 官方限制，超了粘不进去）。字符花在不查就会踩的坑上，不写执行者打开仓库一眼能看到的事实；砍调研过程、重复规矩、背景故事。压不进就是活太大——拆成独立几件，一次给一件。
先分型：动笔前能写出验收命令的是执行型，全套照走。领导要答案本身（调研、选型、该不该做 X）的是探索型——硬指标只会收到凑数的答案，改四处见 anatomy.md。
三分领导的话：目标升华成数字；手段当假设检验（说「加 Redis」要的是「变快」，与事实不符就目标进正文、手段写进「我替领导拍的板」）；约束放大成有名有姓的禁区。
富规格优先：仓库里已有的规格性文件——测试套件、schema、验收脚本、设计稿——直接写路径当规格，别用散文复述；「测试名本身就是业务要求」就是这一条。调研的一部分，就是找出哪个文件是规格。
法与情报分家：「不许」是法，违反即不合格，每条溯源到一次实测或一次领导裁决；「建议」是情报，执行者有更好的路可以走、在 PROGRESS.md 记一句为什么。把情报写成法，是替执行者做它临场更懂的决定。
防它五种死法：
- 作弊达标（最重要）：说「让测试绿」，最省力的是加
.skip、放松断言、mock 被测对象、删测试、|| true——不是它坏，是目标函数写错。对策：基线不可退（测试数／覆盖率 ≥ 基线、skipped 0）、点名禁止具体姿势、判卷标准冻结、暗卷自留。若「测试要绿」与「实现不许改」冲突而代码真有 bug：点破并给方法（characterization test：锁当前行为＋标 KNOWN DEFECT），否则它必偷改实现 - 幻觉命令：它会平静地编造命令再甩锅环境——书里每条命令你必须亲手跑过，摸不到就写进任务 0 让它查实
- 失忆：进度写
PROGRESS.md，接手会话先读它别重做；任务 0 过后先写 ≤10 行开工回执（理解的目标／顺序／最大风险）再动工；单任务一个会话内做得完 - 一条道走到黑：任务 0 兼前提核验，量出的数字对不上就停；同一验收连败 3 次换项；结果比基线差就回滚如实报告——「没做成但说清了」合格，「做了但更糟」不合格
- 静默事故：坏了不发信号的（假绿灯、失效报警器）配反向验证——亲手制造一次失败证明会响，贴输出。判据：问「这里坏了谁会知道」，答「没人」就要
多 agent 并行（领导点头才拆）
每份书带同一段「全局」（整体干什么、谁管哪段、接缝在哪——接缝没人接是头号事故）。地界错开，共享写入点（lockfile 等）指定唯一归属。A 的证据经过 B 的战场只列存疑不动，B 每次 rebase 后重跑取证。建设与删除不给同一个 agent。写明「合并排队变慢是新常态，不要自行协调、不要改 CI」。
语言
全书大白话，领导一遍读懂：标题直陈功能；术语首次出现括号给半句人话；内部概念名（如「暗卷」「探索型」）不出现在书里。默认零玩笑——每句话要么改变执行者行为，要么删掉；领导点名要梗才读 references/style.md。
发出前自检
- ≤4000 字符？一个
/goal、一次粘贴？ - 分型对吗？命令亲手跑过？没问的都写进「我替领导拍的板」带默认值？
- 验收全是命令？防作弊、反向验证、三道止损、
PROGRESS.md／BLOCKED.md机制齐？ - 全文无「来找我」？大白话？零多余玩笑？
- 交付三样齐、无过程噪音？暗卷自留没进书？
- 多 agent：全局段齐、地界不重叠、取证不互相作废？
© KKKKhazix, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in leader of KKKKhazix/khazix-skills.
- SKILL.md
- references/anatomy.md
- references/style.md
Open the folder on GitHubat commit 322346d
Compare with similar skills
Agent Goal Brief Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Goal Brief Writer this skillKKKKhazix/khazix-skills | 21k | — | ~723 | Automated safety check: Pass | MIT | |
| Auditable Playbook Designercursor/plugins | 11k | 8 repos | ~1k | Automated safety check: Pass | None | |
| Launch Delivery PipelineYeachan-Heo/oh-my-claudecode | 40k | — | ~7.3k | Automated safety check: Pass | MIT | |
| Planning And Task Breakdownabashev/vfs-s3 | 106 | 8 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Ultrawork Modecode-yeongyu/lazycodex | 3.8k | — | ~6.9k | Automated safety check: Pass | MIT | |
| Incremental Implementationaddyosmani/agent-skills | 104k | 1 repos | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
- Official
Launch Delivery Pipeline
Yeachan-Heo/oh-my-claudecode
Delivery pipeline from mission brief to verified change: writes a spec, splits it into tickets, runs them in parallel, verifies and reports a decision log after a repo audit gate.
Planning And Task Breakdown
abashev/vfs-s3
Breaks work into ordered tasks. An agent skill from abashev/vfs-s3.
Ultrawork Mode
code-yeongyu/lazycodex
The binding directive for ultrawork mode: evidence-first delivery, a light or heavy process tier, and constant use of memory during the work.
Incremental Implementation
addyosmani/agent-skills
Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.
Inline Plan Execution
jnMetaCode/superpowers-zh
Executes a written implementation plan task by task in the current session, with a progress ledger, test-first gates and one fresh-context review at the end.
More from KKKKhazix/khazix-skills
Disk Storage Analyzer
KKKKhazix/khazix-skills
Scans a Mac or Windows PC read-only to find what fills the disk, grades each item by how safe it is to clean and builds an interactive HTML report.
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
Khazix WeChat Article Writer
KKKKhazix/khazix-skills
Writes long-form WeChat official account articles in the personal style of the Khazix account, from briefs, links, PDFs or rough notes, with a topic quality check.
Horizontal-Vertical Deep Research
KKKKhazix/khazix-skills
Runs a two-axis deep research method on a product, company, concept or person: its full history over time, compared with peers today, delivered as a typeset PDF report.
AIHOT AI News Lookup
KKKKhazix/khazix-skills
Answers questions about recent AI news by querying AIHOT's Chinese-language agent API live, covering daily highlights, search, hot events and the daily digest.
Related
Categories
Questions about Agent Goal Brief Writer
What does Agent Goal Brief Writer do?
Turns a one-line idea into a task brief of up to 4000 characters that an autonomous agent can run through /goal, with measured baselines and cheat-resistant acceptance checks. md is written in Chinese and casts three roles: you as the leader who has the idea and makes the calls, the agent running this skill as the manager who researches, writes and accepts, and a separate executor agent that runs the brief alone with no one to ask. Because the executor follows the text literally, the manager checks facts first: in a codebase it runs commands, records baseline numbers and compares the docs with reality, searches the web where it can, and marks unverified claims as assumptions.
When should I use Agent Goal Brief Writer?
Agent Goal Brief Writer fits situations like: writing an agent goal or task brief from a rough idea; splitting a project into briefs for several agents running in parallel; preparing a long autonomous run with acceptance checks and a progress file; checking an agent's finished work against the brief.
How do I install Agent Goal Brief Writer in Claude Code?
Run `npx skills add KKKKhazix/khazix-skills --skill leader -a claude-code`. Or copy the skill folder (leader in KKKKhazix/khazix-skills) into .claude/skills/leader in your project. Claude Code loads it when a task matches its description.
How do I install Agent Goal Brief Writer in Codex?
Run `npx skills add KKKKhazix/khazix-skills --skill leader -a codex`. Or copy the skill folder (leader in KKKKhazix/khazix-skills) into .agents/skills/leader in your project. Codex loads it when a task matches its description.
Can I use Agent Goal Brief Writer in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add KKKKhazix/khazix-skills --skill leader -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/leader, .gemini/skills/leader, .github/skills/leader and .opencode/skills/leader in your project.
What does Agent Goal Brief Writer need to run?
SKILL.md names no scripts, command-line tools or credentials: Agent Goal Brief Writer is instructions for the agent only. Our summary lists: A codebase the agent can run commands in, for measuring baselines (optional); An execution agent that supports /goal, or any agent that accepts the pasted brief.
Does Agent Goal Brief Writer access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Agent Goal Brief Writer safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Agent Goal Brief Writer use?
Agent Goal Brief Writer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Goal Brief Writer use?
About 723 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.
What are the alternatives to Agent Goal Brief Writer?
Skills that share tags, products or a category with Agent Goal Brief Writer: Auditable Playbook Designer (cursor/plugins, 11k stars), Launch Delivery Pipeline (Yeachan-Heo/oh-my-claudecode, 40k stars), Planning And Task Breakdown (abashev/vfs-s3, 106 stars) and Ultrawork Mode (code-yeongyu/lazycodex, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Goal Brief Writer?
KKKKhazix (a GitHub user) maintains it in KKKKhazix/khazix-skills, which has 21,278 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 1, 2026.
Source: KKKKhazix/khazix-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.