Harness Evolution Feedback Loop
revfactory/harness
Collects feedback on how an agent harness performed, generalizes it, and updates the harness agents, skills and orchestrator along with a change-history table.
Initialize new project with CLAUDE.md, .knowledge/ structure, company rules, and git
$ npx skills add Stanshy/AgentHub --skill project-kickoff -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Stanshy/AgentHub project-kickoff --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/Stanshy/AgentHub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.knowledge/company/skill-templates/project-kickoff .claude/skills/project-kickoff && 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 "project-kickoff" agent skill from https://github.com/Stanshy/AgentHub/tree/main/.knowledge/company/skill-templates/project-kickoff into .claude/skills/project-kickoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-kickoff", 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/Stanshy/AgentHub/tree/main/.knowledge/company/skill-templates/project-kickoffType 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 Stanshy/AgentHub --skill project-kickoff -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Stanshy/AgentHub project-kickoff --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Stanshy/AgentHub.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.knowledge/company/skill-templates/project-kickoff .agents/skills/project-kickoff && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "project-kickoff" agent skill from https://github.com/Stanshy/AgentHub/tree/main/.knowledge/company/skill-templates/project-kickoff into .agents/skills/project-kickoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-kickoff", 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 Stanshy/AgentHub --skill project-kickoff -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Stanshy/AgentHub project-kickoff --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Stanshy/AgentHub.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.knowledge/company/skill-templates/project-kickoff .cursor/skills/project-kickoff && 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 "project-kickoff" agent skill from https://github.com/Stanshy/AgentHub/tree/main/.knowledge/company/skill-templates/project-kickoff into .cursor/skills/project-kickoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-kickoff", 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/Stanshy/AgentHub.git --path .knowledge/company/skill-templates/project-kickoff--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 Stanshy/AgentHub --skill project-kickoff -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Stanshy/AgentHub project-kickoff --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Stanshy/AgentHub.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.knowledge/company/skill-templates/project-kickoff .gemini/skills/project-kickoff && 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 "project-kickoff" agent skill from https://github.com/Stanshy/AgentHub/tree/main/.knowledge/company/skill-templates/project-kickoff into .gemini/skills/project-kickoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-kickoff", 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 Stanshy/AgentHub project-kickoffInstalls 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 Stanshy/AgentHub --skill project-kickoff -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Stanshy/AgentHub.git skills-src && mkdir -p .github/skills && cp -r skills-src/.knowledge/company/skill-templates/project-kickoff .github/skills/project-kickoff && 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 "project-kickoff" agent skill from https://github.com/Stanshy/AgentHub/tree/main/.knowledge/company/skill-templates/project-kickoff into .github/skills/project-kickoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-kickoff", 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 Stanshy/AgentHub --skill project-kickoff -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Stanshy/AgentHub project-kickoff --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Stanshy/AgentHub.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.knowledge/company/skill-templates/project-kickoff .opencode/skills/project-kickoff && 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 "project-kickoff" agent skill from https://github.com/Stanshy/AgentHub/tree/main/.knowledge/company/skill-templates/project-kickoff into .opencode/skills/project-kickoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-kickoff", 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.
project-kickoffInitialize new project with CLAUDE.md, .knowledge/ structure, company rules, and git
Project Kickoff is an agent skill from Stanshy/AgentHub. Initialize new project with CLAUDE.md, .knowledge/ structure, company rules, and git
Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Agent instruction files and Skill authoring. It works with Git. The repository describes itself as: One person, one software company. Manage 47 AI agents from a single Electron app — with Harness Engineering (Skills + Hooks + FileWatchers) for disciplined, traceable AI workflows. The licence is MIT.
7 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 5300820. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteGlobBashFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Project Kickoff loads about 528 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 96 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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
.env.env.*allowed-tools: Read, Write, Glob, BashAutomated 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.
The full file from Stanshy/AgentHub at commit 5300820, republished under its MIT licence (© Stanshy). 96 words, ~528 tokens.
.claude/skills/project-kickoff/SKILL.md (or your agent's skills folder).PM 啟動新專案時使用,確保所有基礎結構就位。
/project-kickoff <project-type> <project-name>$0: 專案類型(web-app / api-service / mobile-app / library)$ARGUMENTS: 完整參數檢查現有結構
部署 CLAUDE.md
{專案名稱} 佔位符).knowledge/company/project-templates/{type}/CLAUDE.md.template建立 .knowledge/ 結構
.knowledge/ 目錄architecture.md(從模板目錄)project-overview.md(標題 + 佔位符)postmortem-log.md(標題 + 空表格)file-index.md(替換 {專案名稱}、填入今日日期).knowledge/company/project-templates/{type}/file-index.md.template部署共用規則
company-rules.md → .knowledge/company-rules.mdteam-workflow.md → .knowledge/team-workflow.md建立 Roadmap
5a. 建立 proposal/ 目錄(若已存在則跳過)
5b. 建立 proposal/roadmap.md(若已存在則跳過):
# {專案名稱} — 產品路線圖
## 產品定位
> {一句話描述產品}
## 目標用戶
> {描述}
## 核心價值
> {描述}
## 版本規劃
| Sprint | 主題 | 目標 | 狀態 |
|--------|------|------|------|
| Sprint 1 | {待定} | {待定} | 🔲 規劃中 |
## 長期願景
> {描述}Git 初始化
6a. 檢查是否已有 git repo(.git/ 目錄存在):
git initgit init6b. 建立 .gitignore(若已存在則跳過):
node_modules/
dist/
.env
.env.*
.claude/
coverage/
*.log
.DS_Store6c. 執行初始 commit(若 working tree 有變更):
git add -A
git commit -m "chore: project kickoff — {project-name}"輸出下一步 Checklist
✅ 專案初始化完成
Git:已初始化 ✅
初始 commit:chore: project kickoff — {project-name} ✅
Roadmap:proposal/roadmap.md ✅
下一步:
- [ ] 填寫 CLAUDE.md 專案簡介佔位符
- [ ] 填寫技術棧表格
- [ ] 填寫 proposal/roadmap.md 產品定位
- [ ] 執行 /product-diagnosis 做 G0 前置診斷
- [ ] 撰寫 Sprint 提案書(/sprint-proposal)
- [ ] 執行 /dev-plan 建立 sprint branch© Stanshy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .knowledge/company/skill-templates/project-kickoff of Stanshy/AgentHub.
Open the folder on GitHubat commit 5300820
Project Kickoff 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 |
|---|---|---|---|---|---|---|
| Project Kickoff this skillStanshy/AgentHub | 202 | — | ~528 | Automated safety check: Notes | MIT | |
| Harness Evolution Feedback Looprevfactory/harness | 9.1k | — | ~855 | Automated safety check: Pass | Apache-2.0 | |
| Prompt Security Hardeninged3dai/ed3d-plugins | 250 | — | ~2.5k | Automated safety check: Warn | None | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Harness Agent Team Designerrevfactory/harness | 9.1k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 |
revfactory/harness
Collects feedback on how an agent harness performed, generalizes it, and updates the harness agents, skills and orchestrator along with a change-history table.
ed3dai/ed3d-plugins
A skill your agent uses when writing skills, CLAUDE.md files, agent prompts, or any directives that involve shell commands, environment variables, API credentials, file creation, or git operations -…
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
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.
revfactory/harness
Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.
ccusage/ccusage
Guides repo-local skill creation and updates. An agent skill from ccusage/ccusage.
Stanshy/AgentHub
Generate a development plan with task breakdown and section 10 tracking tables
Stanshy/AgentHub
Scan child projects for pitfalls and propose company standard updates
Stanshy/AgentHub
Six-question diagnostic framework for G0 pre-check — validate product direction before development starts
Stanshy/AgentHub
L1 internal review with auto-detection, design comparison, and Gate escalation path
Stanshy/AgentHub
L1 計畫模式 SOP — 強制上下文載入 + Plan Mode 評估 + 任務拆解. An agent skill from Stanshy/AgentHub.
Stanshy/AgentHub
L1 Code Review SOP — 強制規範對照 + 審核決策,不得跳過任何 checkpoint. An agent skill from Stanshy/AgentHub.
Works with
Categories
Initialize new project with CLAUDE.md, .knowledge/ structure, company rules, and git. Project Kickoff is an agent skill from Stanshy/AgentHub.
Project Kickoff fits situations like: tasks that involve Agent instruction files; tasks that involve Skill authoring.
Run `npx skills add Stanshy/AgentHub --skill project-kickoff -a claude-code`. Or copy the skill folder (.knowledge/company/skill-templates/project-kickoff in Stanshy/AgentHub) into .claude/skills/project-kickoff in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Stanshy/AgentHub --skill project-kickoff -a codex`. Or copy the skill folder (.knowledge/company/skill-templates/project-kickoff in Stanshy/AgentHub) into .agents/skills/project-kickoff in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Stanshy/AgentHub --skill project-kickoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/project-kickoff, .gemini/skills/project-kickoff, .github/skills/project-kickoff and .opencode/skills/project-kickoff in your project.
Going by SKILL.md and its folder, Project Kickoff needs the command-line tools its instructions call (git). Its frontmatter pre-approves these tools: Read, Write, Glob, Bash.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Project Kickoff is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 528 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Project Kickoff: Harness Evolution Feedback Loop (revfactory/harness, 9.1k stars), Prompt Security Hardening (ed3dai/ed3d-plugins, 250 stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Stanshy (a GitHub user) maintains it in Stanshy/AgentHub, which has 202 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on April 9, 2026.
Source: Stanshy/AgentHub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.