create-agentic-starter 0.1.11 → 0.1.13

package/README.md

@@ -1,28 +1,10 @@
 # create-agentic-starter
 
-`create-agentic-starter` scaffolds a reusable AI working area inside an existing project.
+`create-agentic-starter` adds a reusable AI workflow to an existing project.
 
-It is meant for teams who repeatedly do the same early project work:
+It is built for teams who want one standard setup for project understanding, planning, documentation, execution tracking, and future day-to-day project updates.
 
-- collect requirements
-- understand screenshots, notes, and references
-- define architecture
-- prepare BRD, FRD, estimate, proposal, plan, and task outputs
-
-Instead of rebuilding prompts, folders, and working conventions for every new project, this package gives the team a standard `.agentic/` setup that works across AI tools such as Codex, Claude, Cursor, Zed, and similar agentic workflows.
-
-## What This Project Is Trying To Achieve
-
-The package creates a lightweight but structured workflow inside the target project so an AI agent can:
-
-- understand the project from the files already present
-- gather missing context from the user
-- keep project memory in one place
-- generate internal drafts
-- create user-facing deliverables under `.docs/`
-- use starter export scripts for `.docx`, `.xlsx`, and `.pptx` outputs
-
-The goal is not to generate code for the product itself on day one. The goal is to standardize the project kick-off and delivery-document workflow so any team member can start from the same foundation.
+Instead of starting from scratch in every new repo, this creates a ready-to-use `.agentic/` workspace that can be used with tools like Codex, Claude, Cursor, Zed, Antigravity, and similar AI workflows.
 
 ## How To Run It
 
@@ -40,71 +22,36 @@ bunx create-agentic-starter
 
 The command is non-interactive. It does not ask setup questions.
 
-## What The Command Does
+## What It Does
 
 When you run it, it will:
 
 - recreate `.agentic/`
-- create `.docs/` for user-facing outputs
-- preserve an existing `AGENTS.md` and append a marked `create-agentic-starter` section when needed
-- never modify `.gitignore`
-- never modify `README.md`
-- print the next step for the team: start with `@.agentic/init.md`
-
-## What Gets Created
-
-The scaffold sets up:
-
-- `.agentic/init.md`
-- `.agentic/context.md`
-- `.agentic/commands/`
-- `.agentic/workspace/project/`
-- `.agentic/workspace/memory/`
-- `.agentic/workspace/documents/`
-- `.agentic/workspace/scripts/`
-- `.docs/`
-- `AGENTS.md`
-
-This gives you a clear split:
-
-- `.agentic/workspace/project/` for raw project materials
-- `.agentic/workspace/memory/` for AI-maintained project understanding
-- `.agentic/workspace/documents/` for internal drafts and structured export input
-- `.agentic/workspace/scripts/` for starter export scripts
-- `.docs/` for final user-facing outputs
+- create a reusable workspace for AI prompts, memory, scripts, and outputs
+- preserve an existing `AGENTS.md` and append its guide section
+- print the next step: start with `@.agentic/init.md`
 
-## Export Scripts
+## Why This Is Useful
 
-The scaffold includes starter export scripts under `.agentic/workspace/scripts/` for:
+This setup helps your team keep project context inside the repo itself.
 
-- `.docx` via `docx`
-- `.pptx` via `pptxgenjs`
-- `.xlsx` via `exceljs`
+- prompts can live with the project
+- project memory can be updated over time
+- workflows can evolve as the project grows
+- everything can be version controlled with git
+- the context stays in your codebase instead of being spread across chats and tools
 
-These scripts are intentionally starter implementations. They are expected to be adapted by the AI agent when the user provides:
+You can also:
 
-- a custom template
-- a preferred document style
-- a specific export structure
+- add your own commands under `.agentic/commands/`
+- edit the generated prompts
+- remove anything you do not want
+- shape the workflow around your team
 
-## Typical Workflow
+## Basic Flow
 
 1. Run `npx create-agentic-starter` or `bunx create-agentic-starter` in the target project.
 2. Open that project in your AI tool.
 3. Start a new session with `@.agentic/init.md`.
-4. Let the agent understand the project, ask questions, and update memory files.
-5. Continue with commands in `.agentic/commands/` such as:
-   - `@.agentic/commands/project-requirements.md`
-   - `@.agentic/commands/architecture.md`
-   - `@.agentic/commands/create-brd.md`
-   - `@.agentic/commands/create-frd.md`
-   - `@.agentic/commands/create-estimate.md`
-   - `@.agentic/commands/create-proposal.md`
-   - `@.agentic/commands/create-plan.md`
-   - `@.agentic/commands/create-tasks.md`
-
-## Notes
-
-- The scaffold is designed to be lightweight and easy to drop into an existing repo.
-- It is prompt-driven first, with export scripts available when the workflow needs generated Office documents.
-- `AGENTS.md` is used as the human-readable guide inside the target project.
+4. Let the agent understand the project and continue with the commands you need.
+5. Keep extending the workflow as your team needs more project operations over time.

package/dist/index.js

@@ -1,12 +1,12 @@
 #!/usr/bin/env node
-import{mkdir as $,rm as N,writeFile as P}from"fs/promises";import g from"path";import{readFile as k,writeFile as f}from"fs/promises";import A from"path";function u(e){return e.replace(/[.*+?^${}()|[\]\\]/g,"\\$&")}function F(e,r,s,a){let c=new RegExp(`${u(s)}[\\s\\S]*?${u(a)}\\n?`,"m");if(c.test(e))return e.replace(c,`${r}
+import{mkdir as P,rm as D,writeFile as G}from"fs/promises";import g from"path";import{readFile as A,writeFile as f}from"fs/promises";import F from"path";function u(e){return e.replace(/[.*+?^${}()|[\]\\]/g,"\\$&")}function h(e,r,s,a){let c=new RegExp(`${u(s)}[\\s\\S]*?${u(a)}\\n?`,"m");if(c.test(e))return e.replace(c,`${r}
 `);let o=e.endsWith(`
 `)?`
 `:`
 
 `;return`${e}${o}${r}
-`}async function E(e,r,s,a,c){let o=A.join(e,r);try{let n=await k(o,"utf8"),S=F(n,s,a,c);await f(o,S,"utf8")}catch(n){if(n.code!=="ENOENT")throw n;await f(o,`${s}
-`,"utf8")}}import{readFileSync as h}from"fs";import i from"path";import{fileURLToPath as y}from"url";function t(e){let r=process.argv[1]?i.dirname(i.resolve(process.argv[1])):i.dirname(y(import.meta.url));return h(i.join(r,e),"utf8")}var w="AGENTS.md",m="<!-- from create-agentic-starter:agents:start -->",p="<!-- from create-agentic-starter:agents:end -->",M=t("./templates/meta/agents.md").trimEnd(),T=`${m}
-${M}
+`}async function E(e,r,s,a,c){let o=F.join(e,r);try{let i=await A(o,"utf8"),k=h(i,s,a,c);await f(o,k,"utf8")}catch(i){if(i.code!=="ENOENT")throw i;await f(o,`${s}
+`,"utf8")}}import{existsSync as y,readFileSync as $,realpathSync as w}from"fs";import n from"path";import{fileURLToPath as M}from"url";function t(e){let r=[n.dirname(w(M(import.meta.url))),process.argv[1]?n.dirname(w(process.argv[1])):null,process.argv[1]?n.dirname(n.resolve(process.argv[1])):null].filter(s=>!!s);for(let s of r){let a=n.join(s,e);if(y(a))return $(a,"utf8")}throw new Error(`Template not found: ${e}. Checked: ${r.join(", ")}`)}var T="AGENTS.md",m="<!-- from create-agentic-starter:agents:start -->",p="<!-- from create-agentic-starter:agents:end -->",N=t("./templates/meta/agents.md").trimEnd(),j=`${m}
+${N}
 ${p}
-`;var j={".agentic/commands/project-requirements.md":t("./templates/commands/project-requirements.md"),".agentic/commands/architecture.md":t("./templates/commands/architecture.md"),".agentic/commands/create-brd.md":t("./templates/commands/create-brd.md"),".agentic/commands/create-frd.md":t("./templates/commands/create-frd.md"),".agentic/commands/create-estimate.md":t("./templates/commands/create-estimate.md"),".agentic/commands/create-proposal.md":t("./templates/commands/create-proposal.md"),".agentic/commands/create-plan.md":t("./templates/commands/create-plan.md"),".agentic/commands/create-tasks.md":t("./templates/commands/create-tasks.md")};var _={".agentic/init.md":t("./templates/core/init.md"),".agentic/context.md":t("./templates/core/context.md")};var l=[".agentic"],d=[".agentic",".agentic/commands",".agentic/workspace",".agentic/workspace/project",".agentic/workspace/memory",".agentic/workspace/documents",".agentic/workspace/scripts",".docs",".docs/brd",".docs/frd",".docs/estimate",".docs/proposal",".docs/plan",".docs/tasks"];var x={".agentic/workspace/scripts/README.md":t("./templates/scripts/README.md"),".agentic/workspace/scripts/_shared.js":t("./templates/scripts/_shared.js"),".agentic/workspace/scripts/generate_brd.js":t("./templates/scripts/generate_brd.js"),".agentic/workspace/scripts/generate_frd.js":t("./templates/scripts/generate_frd.js"),".agentic/workspace/scripts/generate_estimate.js":t("./templates/scripts/generate_estimate.js"),".agentic/workspace/scripts/generate_proposal.js":t("./templates/scripts/generate_proposal.js"),".agentic/workspace/scripts/generate_plan.js":t("./templates/scripts/generate_plan.js"),".agentic/workspace/scripts/generate_tasks.js":t("./templates/scripts/generate_tasks.js")};var R=()=>({..._,...j,...x});async function D(e){await Promise.all(l.map(r=>N(g.join(e,r),{recursive:!0,force:!0})))}async function G(e){await Promise.all(d.map(r=>$(g.join(e,r),{recursive:!0})))}async function O(e){let r=R();await Promise.all(Object.entries(r).map(([s,a])=>P(g.join(e,s),a,"utf8")))}async function I(){let e=process.cwd();await D(e),await G(e),await O(e),await E(e,w,T,m,p),console.log(""),console.log("create-agentic-starter: scaffold created successfully."),console.log(`Project folder: ${e}`),console.log(""),console.log("Next steps:"),console.log("1. Open your AI tool in this folder."),console.log("2. Start a new chat with @.agentic/init.md"),console.log("")}I().catch(e=>{let r=e instanceof Error?e.message:String(e);console.error(`create-agentic-starter: failed to scaffold project. ${r}`),process.exitCode=1});
+`;var x={".agentic/commands/project-requirements.md":t("./templates/commands/project-requirements.md"),".agentic/commands/architecture.md":t("./templates/commands/architecture.md"),".agentic/commands/create-brd.md":t("./templates/commands/create-brd.md"),".agentic/commands/create-frd.md":t("./templates/commands/create-frd.md"),".agentic/commands/create-estimate.md":t("./templates/commands/create-estimate.md"),".agentic/commands/create-proposal.md":t("./templates/commands/create-proposal.md"),".agentic/commands/create-plan.md":t("./templates/commands/create-plan.md"),".agentic/commands/create-tasks.md":t("./templates/commands/create-tasks.md")};var _={".agentic/init.md":t("./templates/core/init.md"),".agentic/context.md":t("./templates/core/context.md")};var l=[".agentic"],d=[".agentic",".agentic/commands",".agentic/workspace",".agentic/workspace/project",".agentic/workspace/memory",".agentic/workspace/documents",".agentic/workspace/scripts",".docs",".docs/brd",".docs/frd",".docs/estimate",".docs/proposal",".docs/plan",".docs/tasks"];var S={".agentic/workspace/scripts/README.md":t("./templates/scripts/README.md"),".agentic/workspace/scripts/_shared.js":t("./templates/scripts/_shared.js"),".agentic/workspace/scripts/generate_brd.js":t("./templates/scripts/generate_brd.js"),".agentic/workspace/scripts/generate_frd.js":t("./templates/scripts/generate_frd.js"),".agentic/workspace/scripts/generate_estimate.js":t("./templates/scripts/generate_estimate.js"),".agentic/workspace/scripts/generate_proposal.js":t("./templates/scripts/generate_proposal.js"),".agentic/workspace/scripts/generate_plan.js":t("./templates/scripts/generate_plan.js"),".agentic/workspace/scripts/generate_tasks.js":t("./templates/scripts/generate_tasks.js")};var R=()=>({..._,...x,...S});async function O(e){await Promise.all(l.map(r=>D(g.join(e,r),{recursive:!0,force:!0})))}async function v(e){await Promise.all(d.map(r=>P(g.join(e,r),{recursive:!0})))}async function I(e){let r=R();await Promise.all(Object.entries(r).map(([s,a])=>G(g.join(e,s),a,"utf8")))}async function b(){let e=process.cwd();await O(e),await v(e),await I(e),await E(e,T,j,m,p),console.log(""),console.log("create-agentic-starter: scaffold created successfully."),console.log(`Project folder: ${e}`),console.log(""),console.log("Next steps:"),console.log("1. Open your AI tool in this folder."),console.log("2. Start a new chat with @.agentic/init.md"),console.log("")}b().catch(e=>{let r=e instanceof Error?e.message:String(e);console.error(`create-agentic-starter: failed to scaffold project. ${r}`),process.exitCode=1});

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-agentic-starter",
-  "version": "0.1.11",
+  "version": "0.1.13",
   "description": "Scaffold a minimal AI-powered project delivery workflow inside the current folder.",
   "license": "MIT",
   "type": "module",
@@ -10,6 +10,11 @@
   "files": [
     "dist"
   ],
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/MONESH-M-S/create-agentic-starter.git"
+  },
+  "homepage": "https://github.com/MONESH-M-S/create-agentic-starter#readme",
   "publishConfig": {
     "access": "public"
   },