@givolt/i3-composer-agent 1.0.0 → 2.0.0

package/evals/cases/{using-agent-skills.json → i3-using-agent-skills.json}

@@ -1,5 +1,5 @@
 {
-  "skill_name": "using-agent-skills",
+  "skill_name": "i3-using-agent-skills",
   "trigger": {
     "positive": [
       {
@@ -18,11 +18,11 @@
     "negative": [
       {
         "prompt": "Debug the null pointer crash in checkout",
-        "owner": "debugging-and-error-recovery"
+        "owner": "i3-debugging-and-error-recovery"
       },
       {
         "prompt": "Make the modal accessible for keyboard users",
-        "owner": "frontend-ui-engineering"
+        "owner": "i3-frontend-ui-engineering"
       }
     ]
   },
@@ -32,7 +32,7 @@
       "prompt": "A user asks: 'the login page is broken after yesterday's deploy'. Decide which skill applies and why.",
       "expected_output": "Correct routing through the decision tree with the chosen skill and rationale",
       "files": [
-        "using-agent-skills"
+        "i3-using-agent-skills"
       ],
       "expectations": [
         "The chosen skill matches the decision tree in the meta-skill",

package/evals/fixtures/{git-workflow-and-versioning → i3-git-workflow-and-versioning}/.eval/working-tree.patch

@@ -1,6 +1,6 @@
-diff --git a/git-workflow-and-versioning/app.js b/git-workflow-and-versioning/app.js
---- a/git-workflow-and-versioning/app.js
-+++ b/git-workflow-and-versioning/app.js
+diff --git a/i3-git-workflow-and-versioning/app.js b/i3-git-workflow-and-versioning/app.js
+--- a/i3-git-workflow-and-versioning/app.js
++++ b/i3-git-workflow-and-versioning/app.js
 @@ -1,7 +1,15 @@
  'use strict';
 

package/evals/plugin/code-review-fires/graders/skill-fired.md

@@ -1,5 +1,5 @@
 ---
 type: tool_used
 tool: Skill
-input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(code-review-and-quality|review)"'
+input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(i3-code-review-and-quality|review)"'
 ---

package/evals/plugin/code-review-stays-quiet/graders/not-fired.md

@@ -1,7 +1,7 @@
 ---
 type: tool_used
 tool: Skill
-input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(code-review-and-quality|review)"'
+input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(i3-code-review-and-quality|review)"'
 min: 0
 max: 0
 arm: both

package/evals/plugin/code-review-stays-quiet/graders/tdd-fired.md

@@ -1,6 +1,6 @@
 ---
 type: tool_used
 tool: Skill
-input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(test-driven-development|test)"'
+input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(i3-test-driven-development|test)"'
 arm: with-only
 ---

package/evals/plugin/code-review-stays-quiet/prompt.md

@@ -1,6 +1,6 @@
 ---
-description: A test-first request that belongs to test-driven-development. The review skill must not fire.
-expected_outcome: The reply proposes a failing test first; code-review-and-quality is never invoked.
+description: A test-first request that belongs to i3-test-driven-development. The review skill must not fire.
+expected_outcome: The reply proposes a failing test first; i3-code-review-and-quality is never invoked.
 max_turns: 12
 allowed_tools: [Read, Glob, Grep, Skill]
 ---

package/evals/plugin/code-review-stays-quiet-on-commit-message/graders/not-fired.md

@@ -1,7 +1,7 @@
 ---
 type: tool_used
 tool: Skill
-input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(code-review-and-quality|review)"'
+input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(i3-code-review-and-quality|review)"'
 min: 0
 max: 0
 arm: both

package/evals/plugin/code-review-stays-quiet-on-commit-message/prompt.md

@@ -1,6 +1,6 @@
 ---
-description: A pasted diff with a request that belongs to git-workflow-and-versioning. Guards the "even when the diff is pasted inline" clause of the review skill's description, since a pasted diff alone must not make the review skill fire.
-expected_outcome: A commit message; code-review-and-quality is never invoked.
+description: A pasted diff with a request that belongs to i3-git-workflow-and-versioning. Guards the "even when the diff is pasted inline" clause of the review skill's description, since a pasted diff alone must not make the review skill fire.
+expected_outcome: A commit message; i3-code-review-and-quality is never invoked.
 max_turns: 12
 allowed_tools: [Read, Glob, Grep, Skill]
 ---

package/hooks/SDD-CACHE.md

@@ -1,10 +1,10 @@
 # sdd-cache hook
 
-Cross-session citation cache for [`source-driven-development`](../skills/source-driven-development/SKILL.md). Skips redundant `WebFetch` calls without weakening the skill's "verify against current docs" guarantee.
+Cross-session citation cache for [`i3-source-driven-development`](../skills/i3-source-driven-development/SKILL.md). Skips redundant `WebFetch` calls without weakening the skill's "verify against current docs" guarantee.
 
 ## Why
 
-`source-driven-development` fetches official docs for every framework-specific decision. Working on the same project across sessions means fetching the same pages over and over. Caching the content as local memory would contradict the skill — docs change, and a stale cache hides that.
+`i3-source-driven-development` fetches official docs for every framework-specific decision. Working on the same project across sessions means fetching the same pages over and over. Caching the content as local memory would contradict the skill — docs change, and a stale cache hides that.
 
 This hook caches fetched content on disk, but **revalidates with the origin server on every reuse** via HTTP `If-None-Match` / `If-Modified-Since`. Content is only served from cache when the server responds `304 Not Modified`, which is a fresh verification — not a memory read.
 
@@ -48,7 +48,7 @@ This hook caches fetched content on disk, but **revalidates with the origin serv
 
 2. Make sure `.claude/sdd-cache/` is in your `.gitignore` (already included in this repo).
 
-3. Use `/source-driven-development` (or the skill) as usual. No changes to the skill or the agent's workflow — the cache is transparent.
+3. Use `/i3-source-driven-development` (or the skill) as usual. No changes to the skill or the agent's workflow — the cache is transparent.
 
 ## Mental model
 

package/hooks/SIMPLIFY-IGNORE.md

@@ -1,6 +1,6 @@
 # simplify-ignore hook
 
-Block-level protection for `/code-simplify`. Mark code that should never be simplified — the model won't see it.
+Block-level protection for `/i3-code-simplify`. Mark code that should never be simplified — the model won't see it.
 
 ## Setup
 
@@ -42,7 +42,7 @@ result[3] = buf[3] ^ key[3];
 }
 ```
 
-3. Run `/code-simplify` — protected blocks become `/* BLOCK_de115a1d: perf-critical */` placeholders. The model reasons about surrounding code without seeing the protected implementation.
+3. Run `/i3-code-simplify` — protected blocks become `/* BLOCK_de115a1d: perf-critical */` placeholders. The model reasons about surrounding code without seeing the protected implementation.
 
 > **Note:** The hook stores temporary backups in `.claude/.simplify-ignore-cache/`. Make sure this path is in your `.gitignore`.
 

package/hooks/session-start-test.sh

@@ -37,7 +37,7 @@ if (hasJq) {
     throw new Error('additionalContext is missing startup preface');
   }
   if (!ctx.includes('# Using i3 Composer Agent')) {
-    throw new Error('additionalContext is missing using-agent-skills content');
+    throw new Error('additionalContext is missing i3-using-agent-skills content');
   }
 } else if (!ctx.includes('jq is required')) {
   throw new Error('additionalContext is missing jq fallback guidance');

package/hooks/session-start.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 # i3-composer-agent session start hook
-# Injects the using-agent-skills meta-skill into a new session.
+# Injects the i3-using-agent-skills meta-skill into a new session.
 #
 # Not wired by the plugin: hosts that already route skills from their
 # descriptions (Claude Code, Codex CLI) would run a second router on top of
@@ -13,7 +13,7 @@
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
 SKILLS_DIR="$(dirname "$SCRIPT_DIR")/skills"
-META_SKILL="$SKILLS_DIR/using-agent-skills/SKILL.md"
+META_SKILL="$SKILLS_DIR/i3-using-agent-skills/SKILL.md"
 
 if ! command -v jq >/dev/null 2>&1; then
   echo '{"hookSpecificOutput": {"hookEventName": "SessionStart", "additionalContext": "i3-composer-agent: jq is required for the session-start hook but was not found on PATH. Install jq (e.g. `brew install jq` or `apt-get install jq`) to enable meta-skill injection. Skills remain available individually."}}'
@@ -29,5 +29,5 @@ if [ -f "$META_SKILL" ]; then
 $CONTENT" \
     '{hookSpecificOutput: {hookEventName: "SessionStart", additionalContext: $context}}'
 else
-  echo '{"hookSpecificOutput": {"hookEventName": "SessionStart", "additionalContext": "i3-composer-agent: using-agent-skills meta-skill not found. Skills may still be available individually."}}'
+  echo '{"hookSpecificOutput": {"hookEventName": "SessionStart", "additionalContext": "i3-composer-agent: i3-using-agent-skills meta-skill not found. Skills may still be available individually."}}'
 fi

package/package.json

@@ -82,7 +82,7 @@
     "upstreamCommit": "1401c8b8030e023baeebb31781a6653fe8e93026",
     "upstreamRepository": "https://github.com/addyosmani/agent-skills"
   },
-  "version": "1.0.0",
+  "version": "2.0.0",
   "repository": {
     "type": "git",
     "url": "https://github.com/49780522/i3-composer-agent.git"

package/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "i3-composer-agent",
-  "version": "1.0.0",
+  "version": "2.0.0",
   "description": "Production-grade engineering skills for AI coding agents covering the development lifecycle from spec to ship.",
   "homepage": "https://github.com/49780522/i3-composer-agent",
   "repository": "https://github.com/49780522/i3-composer-agent"

package/rebrand/INSTALLATION-SPEC.md

@@ -0,0 +1,47 @@
+# Installation wizard correction
+
+The published 1.0.0 CLI prepares plugin files but does not implement the
+installation wizard previously described to the user. Restore the promised
+installation flow, including the user's confirmed multiple-tool selection and
+CodeBuddy desktop IDE target.
+
+## Acceptance contract
+
+- Running the package in an interactive terminal opens a tool multi-select,
+  project/global scope selection, destination summary, and confirmation.
+- Host flags preselect tools rather than silently preparing a plugin. The tool
+  catalog preserves the installation paths from the pinned Vercel Skills CLI
+  registry; CodeBuddy, Codex, Claude Code, Cursor and other tools remain choices.
+- Native installation copies all skills and their shared references. CodeBuddy
+  and Claude Code also receive the nine existing command workflows and personas.
+  Portable command references use the installed i3- Skill IDs. Prefix migration
+  follows PREFIX-SPEC.md, with backups and rollback for owned legacy paths.
+- Shared destinations are installed once when several tools use the same path.
+- Existing assets require confirmed replacement and are retained in backups.
+  Unrelated settings and project files are untouched. Failed installation rolls
+  back completed writes; cancellation and dry runs write nothing.
+- `--prepare`, `--extract`, and existing explicit `--dir` calls retain complete
+  plugin preparation. Plain `--version` remains machine-readable.
+- Noninteractive installation requires explicit tools, scope and `--yes`;
+  replacement additionally requires `--force`.
+- Packaging tests exercise the shipped CLI; a real terminal session verifies
+  the wizard. File discovery and actual model execution are separate evidence.
+
+## Implementation and verification
+
+Keep upstream content unchanged on `agent/source`; all fork changes live under
+`rebrand/`. Distribution modules and tests are replayed from `rebrand/overlay/`.
+Use Node.js built-ins and the existing `node:test` conventions. No new runtime
+dependency is required. Keep the upstream baseline at 0.6.12 and the release
+version at 1.0.0 during development. Recommend and obtain the user's approval
+for a new release version before changing it or publishing.
+
+On 2026-10-07 the user accepted the recommended 1.0.1 correction release and
+authorized publication. The upstream baseline remains 0.6.12.
+
+Slices: first prove native multi-tool installation fails on the published CLI;
+then implement directory planning and copying; then add the interactive flow;
+finally verify conflicts, rollback, package extraction and terminal execution.
+
+Commands: `node --test tests/installer.test.cjs`, `npm test`, `npm run validate`,
+`npm run rebrand:check`, and `npm pack` in a generated branded candidate.

package/rebrand/MAINTENANCE.md

@@ -91,15 +91,17 @@ npm pack --pack-destination ../releases/next
 - `overlay/`：本项目的 npm CLI、发行测试、品牌校验和发行 CI；上游相关文件改变时需合并审查。
 - `templates/`：品牌 README 和安装指南；上游对应说明改变时同步模板。
 - 目录数量、Skill 表、命令表和插件描述由已记录的目录生成，不固定为 25/9。
-- Skill frontmatter 保留原文；校验比较换行规范化后的哈希，兼容 LF/CRLF 检出。
+- 源码保留上游 Skill 名称；品牌版 Skill 和命令使用 i3- 前缀，按 PREFIX-SPEC.md 重放。
+- Skill frontmatter 只映射 name；还原 name 后比较换行规范化的上游哈希，兼容 LF/CRLF。
 - LICENSE、NOTICE、真实上游链接、历史评估说明和标准名称保留。
 - 如果上游新增根 package.json，重放会失败，先适配分发配置和依赖再继续。
 
 ## 发布及验收
 
-维护流程与安装能力分开验收。当前 npm CLI 准备文件并打印宿主注册命令；
+维护流程与安装能力分开验收。默认 npm CLI 使用多工具安装向导；`--prepare`
+保留完整插件准备和宿主注册提示。两种模式分别验收，不把准备文件等同于安装。
 实际宿主安装范围、启用、命令执行以及交互向导仍需各自验证。
-Codex 的生命周期斜杠命令适配是独立工作，已有 Skill ID 不因维护流程改名。
+Codex 的生命周期斜杠命令适配是独立工作；原生 Skill 通过 $i3-<名称> 调用。
 
 发布审核通过后，发布已经测过的 tarball，先使用试用标签，完成 registry 安装验证后再更新 latest：
 

package/rebrand/NOTICE.md

@@ -5,5 +5,11 @@ i3 Composer Agent is a branded distribution of
 The initial distribution is based on upstream commit `1401c8b` (version 0.6.12).
 
 The original MIT license and copyright notice are preserved in LICENSE.
-Givolt maintains the branding, npm distribution, and bundle preparation CLI.
-The original skill IDs, command workflows, and persona definitions are retained.
+Givolt maintains the branding, npm distribution, and installation CLI.
+Skill IDs and command filenames use an i3- prefix in this distribution.
+The original command workflows and persona definitions are retained.
+
+The tool installation directory presets in `bin/agent-targets.json` are adapted
+from Vercel's [Skills CLI registry](https://github.com/vercel-labs/skills/blob/48dc9e8eb8aa19040e91cb90ba0b642c9cbad57e/src/agents.ts)
+at commit `48dc9e8eb8aa19040e91cb90ba0b642c9cbad57e`. Copyright (c) 2026
+Vercel, Inc. Its MIT license is retained in `bin/skills-registry.LICENSE`.

package/rebrand/PREFIX-SPEC.md

@@ -0,0 +1,16 @@
+# i3 command and Skill identifiers
+
+The user approved applying the existing i3 naming convention on 2026-10-07.
+This supersedes the earlier preservation of unprefixed distribution identifiers.
+
+- `agent/source` keeps upstream files and identifiers unchanged. Changes live in `rebrand/`.
+- Branded Skill directories and YAML `name` fields use `i3-<upstream-id>`.
+- All three command directories use `i3-<upstream-stem>` filenames, retaining the existing `plan`/`planning` host mapping.
+- Native commands include `/i3-spec` and `/i3-build`; plugin commands include `/i3-composer-agent:i3-spec`.
+- Rewrite local references, hooks, routing fixtures and documentation together. Preserve external upstream links, attribution, and Skill frontmatter other than `name`.
+- Retain helper script filenames and executable permissions when their containing Skill directory is renamed.
+- Replay and validation accept only a complete reviewed source catalog or its mapped branded catalog. Replaying branded output is idempotent.
+- Installation migrates only legacy Skill/command paths listed in this package's prior installation manifest. Back up retired paths and support rollback. Unowned commands and skills remain in place.
+- Verify source tests, branded validation/tests, routing/hooks, packed CLI installation, migration, rollback and the actual project installation. IDE discovery and model execution require separate host verification.
+
+Release 2.0.0 applies this breaking identifier change. The user authorized publication on 2026-10-07. Publish and verify the reviewed new-version tarball; previously published tarballs remain immutable. The upstream baseline stays at 0.6.12.

package/rebrand/UNIFICATION-SPEC.md

@@ -8,7 +8,7 @@
 - `agent/source` 保留上游原始名称和源码，在 `rebrand/` 保存本项目的分发工具与转换规则。
 - 候选从 `agent/source` 创建，在候选中重放；`main` 保存经过验证的品牌快照。
 - GSD 仓库只读，不使用它的源码、分支或安装产物。
-- Skill ID、流程命令内容、Persona、参考文件和 MIT 来源署名保持既有契约。
+- 源码保留上游 Skill ID；品牌版按 PREFIX-SPEC.md 使用 i3- 前缀。流程内容、Persona、参考文件和 MIT 来源署名保持。
 - 本次完善源码同步和品牌重放；交互安装向导、Codex 命令适配及新的 npm 发布独立处理。
 
 ## 实现与命令
@@ -24,7 +24,7 @@
 1. 从干净上游源码及本项目规则能生成完整品牌包，重复重放不产生差异。
 2. 在 `agent/source` 上执行写入式重放必须失败且不修改源码。
 3. 记录上游新增 Skill/Command 后能生成相应清单和说明；删失或改写已记录 Skill ID 时校验失败。
-4. 上游的 25 个 Skill frontmatter、24 个非元 Skill、4 个 Persona、7 个共享参考保持原始内容；9 个流程只变品牌命名空间。
+4. 品牌版的 Skill name、目录和命令文件名统一使用 i3-；frontmatter 的其他字段、Persona、共享参考和流程契约保持。
 5. 本地候选通过完整测试，并从打包结果运行 CLI 与校验。
 6. 独立品牌仓库中的源/发行分支及远程关系正确；首次发布标签保持原来的 0.6.12 提交。
 

package/rebrand/VALIDATION.md

@@ -11,8 +11,8 @@
 
 ## 品牌候选
 
-- Skill、命令、Persona、references 和全部已记录普通运行文件与上游目录一致。
-- Skill frontmatter 的名称和字段内容保持；换行差异不作为字段变更。
+- Skill 和命令路径按 PREFIX-SPEC.md 映射为 i3- 名称；其余已记录运行文件保持目录一致。
+- Skill frontmatter 只改 name；逆向映射 name 后比较上游哈希，换行差异不作为字段变更。
 - 新增上游 Skill/Command 能进入目录、品牌说明和打包；缺失内容会失败。
 - 文字补丁失去匹配时必须失败，不能静默遗漏。
 - 重放后 --check 成功，完整 Node、路由与 hook 检查通过。
@@ -26,3 +26,7 @@
 源或包校验不等于 registry 发布，也不等于实际宿主启用和模型执行。
 英文确定性 TF-IDF 路由分数不能代替中文或真实模型行为验收。
 安装向导、宿主范围、升级和移除沿用安装遗漏审计的独立验收项。
+
+交互安装修复必须覆盖多工具选择、项目/全局目录、共享 references、命令与
+Persona 文件、冲突保护、备份、失败回滚和取消不写入。对打包后的 CLI 运行
+真实终端向导，不能用 bundle 准备测试代替；安装文件也不等于 IDE 或模型验收。

package/rebrand/VERSIONING.md

@@ -2,9 +2,9 @@
 
 本规则已经用户确认，仅适用于 i3 Composer Agent 仓库。
 
-| 信息 | 权威来源 | 本次确认值 |
+| 信息 | 权威来源 | 当前发行值 |
 | --- | --- | --- |
-| i3 发行版本 | brand.json 的 releaseVersion | 1.0.0 |
+| i3 发行版本 | brand.json 的 releaseVersion | 2.0.0 |
 | 上游版本 | upstream.json 的 upstreamVersion | 0.6.12 |
 | 上游提交 | upstream.json 的 upstreamCommit | 1401c8b8030e023baeebb31781a6653fe8e93026 |
 
@@ -20,13 +20,16 @@ package.json 的 i3ComposerAgent 来源字段。package.template.json 不保存
 README、CLI 帮助和准备完成提示显示：
 
 ```text
-i3 Composer Agent v1.0.0
+i3 Composer Agent v2.0.0
 Based on agent-skills v0.6.12
 ```
 
-在上述例子中，--version 输出 1.0.0，保留脚本使用的单一版本格式。--dry-run 的 JSON
+在上述例子中，--version 输出 2.0.0，保留脚本使用的单一版本格式。--dry-run 的 JSON
 分别提供 version、upstreamVersion、upstreamCommit。
 
 已经发布的 @givolt/i3-composer-agent@0.6.12 及其 Git 标签作为历史记录保留。
 之前的 0.6.13 是未发布候选，新的独立版本候选替代它。
-1.0.0 的源码与打包验证不代表 npm 发布；发布仍按 MAINTENANCE.md 单独执行。
+1.0.0 已发布。1.0.1 用于修复安装向导遗漏，版本与发布已由用户确认。
+2.0.0 为命令和 Skill 的 i3- 前缀变更；使用者需要调整调用名，因此递增 major。
+用户于 2026-10-07 要求修改并授权发布；上游版本和提交保持不变。
+源码与打包验证不代表 npm 发布；发布仍按 MAINTENANCE.md 单独执行。

package/rebrand/apply.cjs

@@ -5,6 +5,7 @@ const fs = require('node:fs');
 const path = require('node:path');
 const { spawnSync } = require('node:child_process');
 const { validateCatalog, frontmatter } = require('./catalog.cjs');
+const { skillId, runtimePath, rewriteReferences } = require('./identifiers.cjs');
 const brand = require('./brand.json');
 const upstream = require('./upstream.json');
 const root = path.resolve(__dirname, '..');
@@ -20,7 +21,24 @@ if (mode === '--apply') {
     process.exit(1);
   }
 }
-const inventory = validateCatalog(root, upstream);
+const branded = fs.existsSync(path.join(root, 'skills', skillId(upstream.skills[0])));
+validateCatalog(root, upstream, { branded });
+const inventory = upstream;
+const renames = new Map();
+if (!branded) {
+  for (const id of inventory.skills) renames.set(`skills/${id}`, `skills/${skillId(id)}`);
+  for (const file of inventory.runtimeFiles.filter(file => /^(?:\.claude\/commands|\.gemini\/commands|commands)\/[^/]+\.(?:md|toml)$/.test(file))) renames.set(file, runtimePath(file));
+  for (const target of renames.values()) if (fs.existsSync(path.join(root, target))) throw new Error(`Brand destination already exists: ${target}`);
+}
+for (const id of inventory.skills) {
+  for (const file of [`evals/cases/${id}.json`, `evals/fixtures/${id}`]) {
+    if (fs.existsSync(path.join(root, file))) {
+      const target = runtimePath(file);
+      if (fs.existsSync(path.join(root, target))) throw new Error(`Brand destination already exists: ${target}`);
+      renames.set(file, target);
+    }
+  }
+}
 const packageFile = path.join(root, 'package.json');
 if (fs.existsSync(packageFile) && JSON.parse(fs.readFileSync(packageFile, 'utf8')).name !== brand.npmName) {
   console.error('Upstream package.json now exists; explicitly adapt the distribution overlay before replaying.');
@@ -30,6 +48,7 @@ const changes = new Map();
 function update(relative, content) {
   const file = path.join(root, relative);
   if (!fs.existsSync(file) || fs.readFileSync(file, 'utf8') !== content) changes.set(relative, content);
+  else changes.delete(relative);
 }
 function transform(content, relative) {
   const head = /^skills\/[^/]+\/SKILL\.md$/.test(relative) ? frontmatter(content) : '';
@@ -43,7 +62,7 @@ function transform(content, relative) {
     .replaceAll('addy-agent-skills', brand.name)
     .replaceAll('agent-skills@addy-agent-skills', `${brand.name}@${brand.name}`)
     .replaceAll('agent-skills@agent-skills', `${brand.name}@${brand.name}`)
-    .replaceAll('agent-skills:', `${brand.name}:`)
+    .replace(/(?<![\w-])agent-skills:/g, `${brand.name}:`)
     .replaceAll('/path/to/agent-skills', `/path/to/${brand.name}`)
     .replaceAll('./agent-skills', `./${brand.name}`)
     .replace(/(?<![\w/.-])agent-skills(?![\w-])/g, brand.name)
@@ -74,7 +93,9 @@ function transform(content, relative) {
       .replace(/\[[^\]]+\]\(https:\/\/github\.com\/addyosmani\/agent-skills\/issues\/(\d+)\)/g,
         (_, issue) => `[upstream agent-skills #${issue}](https://github.com/addyosmani/agent-skills/issues/${issue})`);
   }
-  return head + result;
+  const name = head.match(/^name:\s*([^\s]+)\s*$/m)?.[1];
+  const brandedHead = name && inventory.skills.includes(name) ? head.replace(/^name:.*$/m, `name: ${skillId(name)}`) : head;
+  return brandedHead + rewriteReferences(result, false, inventory, !relative.startsWith('scripts/'));
 }
 const skipDirectories = new Set(['.git', 'node_modules', 'rebrand', 'dist', 'tests', 'bin']);
 const skipFiles = new Set(['LICENSE', 'NOTICE.md', 'CHANGELOG.md', 'package.json', 'README.md', 'evals/README.md', 'evals/skill-impact.md', 'docs/comparison.md', 'scripts/validate-brand.cjs', 'scripts/lib/skill-lint.js', 'scripts/lib/skill-lint-test.js']);
@@ -83,7 +104,7 @@ function walk(directory, prefix = '') {
     const relative = prefix ? `${prefix}/${entry.name}` : entry.name;
     if (entry.isDirectory()) {
       if (!skipDirectories.has(entry.name) && !relative.startsWith('evals/results')) walk(path.join(directory, entry.name), relative);
-    } else if (entry.isFile() && !skipFiles.has(relative) && /\.(?:md|js|cjs|sh|toml|yml)$/.test(entry.name)) {
+    } else if (entry.isFile() && !skipFiles.has(relative) && /\.(?:md|js|cjs|sh|toml|yml|json|patch|diff)$/.test(entry.name)) {
       const original = fs.readFileSync(path.join(root, relative), 'utf8');
       update(relative, transform(original, relative));
     }
@@ -116,7 +137,7 @@ for (const relative of ['plugin.json', '.claude-plugin/plugin.json', '.codex-plu
     manifest.interface.developerName = brand.maintainer;
     manifest.interface.shortDescription = 'Engineering workflow skills';
     manifest.interface.longDescription = `${brand.displayName} packages ${inventory.skills.length} engineering skills from Addy Osmani's Agent Skills, covering requirements, planning, implementation, testing, review, and shipping.`;
-    manifest.interface.defaultPrompt = manifest.interface.defaultPrompt.map(prompt => prompt.replaceAll('Agent Skills', brand.displayName));
+    manifest.interface.defaultPrompt = manifest.interface.defaultPrompt.map(prompt => rewriteReferences(prompt.replaceAll('Agent Skills', brand.displayName)));
   }
   update(relative, JSON.stringify(manifest, null, 2) + '\n');
 }
@@ -164,7 +185,8 @@ pkg.i3ComposerAgent.upstreamRepository = brand.upstream;
 update('package.json', JSON.stringify(pkg, null, 2) + '\n');
 update('NOTICE.md', fs.readFileSync(path.join(__dirname, 'NOTICE.md'), 'utf8'));
 function description(relative) {
-  const head = fs.readFileSync(path.join(root, relative), 'utf8').match(/^---\r?\n([\s\S]*?)\r?\n---/)?.[1] || '';
+  const file = path.join(root, branded ? runtimePath(relative) : relative);
+  const head = fs.readFileSync(file, 'utf8').match(/^---\r?\n([\s\S]*?)\r?\n---/)?.[1] || '';
   return (head.match(/^description:\s*(.*)$/m)?.[1] || '').replace(/^["']|["']$/g, '').replaceAll('|', '\\|');
 }
 const values = {
@@ -173,8 +195,8 @@ const values = {
   SKILL_COUNT: inventory.skills.length,
   COMMAND_COUNT: inventory.commands.length,
   PERSONA_COUNT: inventory.personas.length,
-  SKILL_TABLE: inventory.skills.map(id => `| [${id}](skills/${id}/SKILL.md) | ${description(`skills/${id}/SKILL.md`)} |`).join('\n'),
-  COMMAND_TABLE: inventory.commands.map(id => `| /${brand.name}:${id} | ${description(`.claude/commands/${id}.md`)} |`).join('\n'),
+  SKILL_TABLE: inventory.skills.map(id => `| [${skillId(id)}](skills/${skillId(id)}/SKILL.md) | ${description(`skills/${id}/SKILL.md`)} |`).join('\n'),
+  COMMAND_TABLE: inventory.commands.map(id => `| /${brand.name}:${skillId(id)} | ${description(`.claude/commands/${id}.md`)} |`).join('\n'),
 };
 for (const [relative, template] of [
   ['README.md', 'README.md'], ['docs/codex-setup.md', 'codex-setup.md'], ['docs/codebuddy-setup.md', 'codebuddy-setup.md'],
@@ -190,5 +212,6 @@ if (mode === '--apply') for (const [relative, content] of changes) {
   fs.writeFileSync(path.join(root, relative), content);
 }
 if (mode === '--apply') fs.chmodSync(path.join(root, 'bin/i3-composer-agent.cjs'), 0o755);
-console.log(JSON.stringify({ mode, changedFiles: [...changes.keys()] }, null, 2));
-if (mode === '--check' && changes.size) process.exitCode = 1;
+if (mode === '--apply') for (const [source, target] of renames) fs.renameSync(path.join(root, source), path.join(root, target));
+console.log(JSON.stringify({ mode, changedFiles: [...changes.keys()], renamedPaths: Object.fromEntries(renames) }, null, 2));
+if (mode === '--check' && (changes.size || renames.size)) process.exitCode = 1;

package/rebrand/brand.json

@@ -9,5 +9,5 @@
   "repository": "https://github.com/49780522/i3-composer-agent",
   "sourceBranch": "agent/source",
   "releaseBranch": "main",
-  "releaseVersion": "1.0.0"
+  "releaseVersion": "2.0.0"
 }

package/rebrand/catalog.cjs

@@ -4,6 +4,7 @@ const fs = require('node:fs');
 const path = require('node:path');
 const crypto = require('node:crypto');
 const assert = require('node:assert/strict');
+const { skillId, runtimePath } = require('./identifiers.cjs');
 const runtimeRoots = ['skills', 'references', 'agents', 'commands', '.claude/commands', '.gemini/commands', 'hooks', '.claude-plugin', '.codex-plugin', '.agents/plugins'];
 const runtimeFiles = ['plugin.json', 'LICENSE'];
 
@@ -46,10 +47,23 @@ function catalog(root) {
   for (const name of runtimeFiles) if (fs.existsSync(path.join(root, name))) files.push(name);
   return describe(files, file => fs.readFileSync(path.join(root, file), 'utf8'));
 }
-function validateCatalog(root, expected) {
+function validateCatalog(root, expected, { branded = false } = {}) {
   const actual = catalog(root);
+  const mapped = branded ? {
+    ...expected,
+    skills: expected.skills.map(skillId),
+    commands: expected.commands.map(skillId),
+    runtimeFiles: expected.runtimeFiles.map(file => runtimePath(file, false, expected)).sort(),
+    skillFrontmatter: Object.fromEntries(expected.skills.map(id => {
+      const name = skillId(id);
+      const head = frontmatter(fs.readFileSync(path.join(root, 'skills', name, 'SKILL.md'), 'utf8'));
+      const normalized = head.replace(new RegExp(`^name:.*$`, 'm'), `name: ${id}`).replace(/\r\n/g, '\n');
+      actual.skillFrontmatter[name] = crypto.createHash('sha256').update(normalized).digest('hex');
+      return [name, expected.skillFrontmatter[id]];
+    })),
+  } : expected;
   for (const field of ['skills', 'commands', 'personas', 'references', 'runtimeFiles', 'skillFrontmatter']) {
-    assert.deepEqual(actual[field], expected[field], `upstream preservation failed: ${field}`);
+    assert.deepEqual(actual[field], mapped[field], `upstream preservation failed: ${field}`);
   }
   return actual;
 }

package/rebrand/fork-patches.json

@@ -1,4 +1,19 @@
 [
+  {
+    "file": "scripts/lib/skill-lint.js",
+    "from": "const SECTION_EXEMPT_SKILLS = {",
+    "to": "const SECTION_EXEMPT_SKILLS = {\n  'i3-using-agent-skills': 'Branded alias of the reviewed upstream meta-skill.',\n  'i3-idea-refine': 'Branded alias of the reviewed upstream legacy structure.',"
+  },
+  {
+    "file": "scripts/validate-artifact-paths.js",
+    "from": "function findViolations(relPath) {",
+    "to": "GUARDED_FILES.push(...GUARDED_FILES.filter(relative => /(?:^|\\/)commands\\//.test(relative)).map(relative => relative.replace(/(commands\\/)([^/]+)(\\.md|\\.toml)$/, '$1i3-$2$3')));\n\nfunction findViolations(relPath) {"
+  },
+  {
+    "file": "scripts/validate-commands.js",
+    "from": "  plan: 'planning',",
+    "to": "  plan: 'planning',\n  'i3-plan': 'i3-planning',"
+  },
   {
     "file": "scripts/validate-versions.js",
     "from": "const manifestPaths = [\n  \"plugin.json\",",

package/rebrand/identifiers.cjs

@@ -0,0 +1,41 @@
+'use strict';
+
+const upstream = require('./upstream.json');
+const prefix = 'i3-';
+const skillId = id => prefix + id;
+const escape = value => value.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
+
+function runtimePath(relative, reverse = false, inventory = upstream) {
+  const skills = new Map(inventory.skills.map(id => reverse ? [skillId(id), id] : [id, skillId(id)]));
+  relative = relative.replace(/^(skills|evals\/fixtures)\/([^/]+)(?=\/|$)/, (match, folder, id) => skills.has(id) ? `${folder}/${skills.get(id)}` : match);
+  relative = relative.replace(/^evals\/cases\/([^/]+)\.json$/, (match, id) => skills.has(id) ? `evals/cases/${skills.get(id)}.json` : match);
+  const commands = inventory.runtimeFiles.filter(file => /^(?:\.claude\/commands|\.gemini\/commands|commands)\/[^/]+\.(?:md|toml)$/.test(file));
+  for (const file of commands) {
+    const branded = file.replace(/([^/]+)\.(md|toml)$/, `${prefix}$1.$2`);
+    if (relative === (reverse ? branded : file)) return reverse ? file : branded;
+  }
+  return relative;
+}
+
+function rewriteReferences(content, reverse = false, inventory = upstream, commandReferences = true) {
+  const skills = new Map(inventory.skills.map(id => reverse ? [skillId(id), id] : [id, skillId(id)]));
+  const names = [...new Set([...inventory.commands, ...inventory.runtimeFiles.filter(file => /commands\/[^/]+\.toml$/.test(file)).map(file => file.split('/').at(-1).slice(0, -5))])];
+  const commands = new Map(names.map(id => reverse ? [prefix + id, id] : [id, prefix + id]));
+  const skillPattern = new RegExp(`(?<![\\w-])(${[...skills.keys()].map(escape).join('|')})(?![\\w-]|\\.(?:sh|py|js|cjs)\\b)`, 'g');
+  const commandPattern = [...commands.keys()].map(escape).join('|');
+  const slash = new RegExp(`(?<![\\w/.-])/(${commandPattern})(?![\\w-])`, 'g');
+  const filenames = new RegExp(`(commands/)(${commandPattern})\\.(md|toml)\\b`, 'g');
+  const namespace = new RegExp(`((?:agent-skills|i3-composer-agent|\\$\\{name\\}):)(${commandPattern})(?![\\w-])`, 'g');
+  // External links refer to the upstream repository's original paths.
+  return content.split(/(https?:\/\/[^\s)'"<>`]+)/g).map(part => {
+    if (/^https?:\/\//.test(part)) return part;
+    part = part.replace(skillPattern, match => skills.get(match));
+    if (!commandReferences) return part;
+    return part
+    .replace(slash, (_, id) => '/' + commands.get(id))
+    .replace(filenames, (_, folder, id, extension) => `${folder}${commands.get(id)}.${extension}`)
+    .replace(namespace, (_, scope, id) => scope + commands.get(id));
+  }).join('');
+}
+
+module.exports = { prefix, skillId, runtimePath, rewriteReferences };

package/rebrand/overlay/CHANGELOG.md

@@ -1,6 +1,34 @@
 # i3 Composer Agent changes
 
-## 1.0.0 — Unreleased
+## 2.0.0 — 2026-10-07
+
+Upstream baseline: agent-skills 0.6.12 at commit 1401c8b8030e023baeebb31781a6653fe8e93026.
+
+### Changed
+
+- Commands and Skill IDs use the `i3-` prefix, such as `/i3-spec` and `$i3-spec-driven-development`.
+- Native upgrades back up and retire this package's manifest-owned unprefixed paths. Unowned entries remain in place; failed migrations roll back.
+- Local command references, hooks, routing fixtures and setup documentation follow the renamed identifiers.
+
+### Migration
+
+- Replace `/spec`, `/plan`, `/build` and other lifecycle calls with `/i3-spec`, `/i3-plan`, `/i3-build` and their prefixed equivalents. Plugin calls use `/i3-composer-agent:i3-<command>`.
+- Replace Skill calls such as `$spec-driven-development` with `$i3-spec-driven-development`.
+- Upgrade with `npx @givolt/i3-composer-agent@2.0.0 --codebuddy`, confirm replacement, then reload the host. The installer backs up manifest-owned legacy entries before retiring them.
+- Keep using the pinned 1.0.1 package if a consuming workflow needs the old identifiers. Existing published versions remain available.
+
+## 1.0.1 — 2026-10-07
+
+Upstream baseline: agent-skills 0.6.12 at commit 1401c8b8030e023baeebb31781a6653fe8e93026.
+
+### Fixed
+
+- Restore the promised terminal installation wizard with multiple tool selection, project/global scope, a destination summary and confirmation.
+- Install complete native skill files and shared references; include short lifecycle commands and personas for CodeBuddy and Claude Code.
+- Protect existing assets with confirmed replacement, backups and rollback on installation failure.
+- Retain complete plugin preparation with --prepare and existing explicit --dir calls.
+
+## 1.0.0 — 2026-10-07
 
 Upstream baseline: agent-skills 0.6.12 at commit 1401c8b8030e023baeebb31781a6653fe8e93026.