create-harness-vibe-coding 0.8.0 → 0.8.1

package/README-CN.md

@@ -15,9 +15,11 @@ npx create-harness-vibe-coding@latest my-project
 已有项目时，不要让 agent 猜。把这句话贴给它：
 
 ```text
-请按照 https://github.com/zingspark/create-harness-vibe-coding 的 README 为当前项目配置 create-harness-vibe-coding；编辑前先扫描项目根目录并询问 Agent-link 安装前置问题；如果 Harness/ 已存在，先询问如何处理再写文件；新项目走 0-1 bootstrap，老项目或老架构升级先 dry-run，保留现有文件，只合并缺失的 Harness 规范，然后遵循 Harness/SETUP.md。
+请完整阅读并严格遵循 https://github.com/zingspark/create-harness-vibe-coding，为当前项目配置 create-harness-vibe-coding。
 ```
 
+复杂规则不塞进这句话里。README 和生成后的 `Harness/SETUP.md` 才是安装、升级、合并和可选能力选择的准则。
+
 ## 你会得到什么
 
 | 文件/能力 | 作用 |
@@ -25,8 +27,8 @@ npx create-harness-vibe-coding@latest my-project
 | `CLAUDE.md` + `AGENTS.md` | 根目录 agent 入口 |
 | `Harness/README.md` | Harness 路由器 |
 | `Harness/tasks/` + `Harness/PROGRESS.md` | 跨会话任务状态 |
-| `.claude/skills/` | Claude Code 的 workflow skill 入口 |
-| `.agents/skills/` | Codex 的 repo skill 入口 |
+| `.claude/skills/` | Claude Code workflow skill 入口 |
+| `.agents/skills/` | Codex repo skill 入口 |
 | `.codex/` | Codex hooks/config |
 | `/wf` / `$wf` | 长任务 workflow |
 | `/wf-max` / `$wf-max` | 最大并行 workflow |
@@ -41,18 +43,18 @@ Claude Code 和 Codex 共用同一套核心 Harness 文档，但发现入口不
 - Codex：`.agents/skills/<name>/SKILL.md`，通常用 `$wf` 或 `/skills` 调用。
 - `.codex/` 只放 Codex 配置和 hooks；不要再使用根目录 `commands/*.toml` 伪装 Codex slash command。
 
-## 新项目
+## 安装或升级路径
 
-```bash
-npx create-harness-vibe-coding@latest my-project
-cd my-project
-```
+写文件前，agent 必须先判断当前项目属于哪一种：
 
-然后让 agent 执行：
+| 项目状态 | 必须怎么做 |
+|---|---|
+| 空项目或新项目 | 运行脚手架，然后遵循 `Harness/SETUP.md` 做 0-1 bootstrap |
+| 已有项目，没有 `Harness/` | 先扫描项目事实，先 `--dry-run`，保留现有文件，只合并缺失的 Harness 指南 |
+| 老项目或老架构迁移 | 现有代码和文档是事实来源，先 dry-run，再用 `Harness/SETUP.md` 从事实中补 PRD、研究、架构和任务计划 |
+| 已经有 `Harness/` | 不要把 `npx` 当更新器；先问用户是运行 `/wf-update` / `$wf-update` / `node Harness/scripts/wf-update-check.mjs`，保持不动，还是批准后移除重装 |
 
-```text
-读 Harness/SETUP.md。把这个项目从想法引导到第一个 vertical slice。
-```
+根目录扫描必须包括：顶层文件、`CLAUDE.md`、`AGENTS.md`、`.claude/`、`.agents/`、`.codex/`、`Harness/`、package 文件、CI 文件、应用入口、测试/构建命令、已有文档、已经安装的 skills/plugins/rules。推荐可选能力前，必须先排除已经安装的能力，避免重复推荐。
 
 ## 已有项目安全合并
 
@@ -90,7 +92,16 @@ npx create-harness-vibe-coding@latest my-app -y --recommend superpowers,codegrap
 
 本地 workflow：`browser-e2e`、`ui-ux-review`、`ts-react-frontend`、`python-backend`、`github-pr-review`。
 
-外部建议只写入 `Harness/SETUP.md`，不会自动安装第三方技能：`superpowers`、`caveman`、`agent-research`、`codegraph`。
+外部建议只写入 `Harness/SETUP.md`，不会自动安装第三方技能：
+
+| 建议 | 用途 | 链接 |
+|---|---|---|
+| `superpowers` | 社区 skill registry 和 agent workflow | <https://github.com/obra/Superpowers> |
+| `caveman` | 简洁低 token 的 agent 行为和记忆压缩 | <https://github.com/JuliusBrussee/caveman> |
+| `agent-research` | 文献、产品、依赖和生态研究类 agent skills | <https://github.com/lingzhi227/agent-research-skills> |
+| `codegraph` | 代码图谱或仓库地图工具 | <https://github.com/colbymchenry/codegraph> |
+
+这些只是给用户 agent 自行评估的 GitHub 链接。脚手架不维护第三方安装步骤，只在确认项目尚未安装同类能力后记录用户选择。
 
 不加 `-y` 时，CLI 会提供 checkbox/multiselect 选择。
 
@@ -102,13 +113,14 @@ Agent 必须先扫描根目录，再最多问 3 个阻塞问题。扫描要覆
 - `.claude/`、`.agents/`、`.codex/`
 - `Harness/`
 - `README.md`
-- package 文件、CI 文件、已有文档目录、应用入口和测试命令
+- package 文件、CI 文件、已有文档目录、应用入口、测试/构建命令
+- 已安装的 skills/plugins/rules
 
 只在影响写入时提问：
 
 - 已有 `CLAUDE.md` 或 `AGENTS.md`：合并缺失 Harness 指南、保持不动，还是跳过？
 - 已有 `Harness/`：走 `/wf-update` / `$wf-update`、dry-run 补缺、保持不动，还是批准后移除重装？
-- 要启用哪些能力：本地 workflow，或只记录外部建议？
+- 排除已安装能力后，还要启用哪些本地 workflow，或只记录哪些外部 GitHub 推荐链接？
 
 默认策略：保留已有文件，只补缺失内容。
 

package/README.md

@@ -21,7 +21,7 @@ npx create-harness-vibe-coding@latest my-project
 Already have a project? **Don't read the docs**. Paste this sentence. Your agent handles the rest.
 
 ```text
-Follow the README at https://github.com/zingspark/create-harness-vibe-coding to configure this project with create-harness-vibe-coding; before editing, scan the project root and ask the Agent-link install intake questions; if Harness/ already exists, ask how to handle it before writing; for a new project run the 0-1 bootstrap, and for an existing project or legacy architecture run a dry-run first, preserve existing files, merge only missing Harness guidance, then follow Harness/SETUP.md.
+Read and follow https://github.com/zingspark/create-harness-vibe-coding exactly to configure this project with create-harness-vibe-coding.
 ```
 
 That's it. Two paths into the harness — you type `npx`, or your agent reads the sentence.
@@ -104,6 +104,19 @@ cd my-project
 # Your agent reads Harness/SETUP.md. Done.
 ```
 
+### Install or Upgrade Path
+
+Before writing, the agent must identify which path applies:
+
+| Project state | Required action |
+|---------------|-----------------|
+| Empty or new project | Run the scaffold, then follow `Harness/SETUP.md` for 0-1 bootstrap |
+| Existing project, no `Harness/` | Scan project facts first, run `--dry-run`, preserve existing files, merge only missing Harness guidance |
+| Legacy architecture or older project docs | Treat existing code/docs as source of truth, dry-run first, then use `Harness/SETUP.md` to fill facts from observed project reality |
+| Existing `Harness/` | Do not use `npx` as an updater; ask whether to run `/wf-update`, `$wf-update`, `node Harness/scripts/wf-update-check.mjs`, keep untouched, or remove/reinstall after approval |
+
+Root scan must include top-level files, `CLAUDE.md`, `AGENTS.md`, `.claude/`, `.agents/`, `.codex/`, `Harness/`, package files, CI files, app entry points, test/build commands, existing docs, and already-installed skills/plugins/rules. Use that scan before recommending optional capabilities so you do not suggest duplicates.
+
 ### Existing project — safe merge
 
 ```bash
@@ -148,24 +161,26 @@ npx create-harness-vibe-coding@latest my-app -y --recommend superpowers,codegrap
 
 External recommendations are recorded in `Harness/SETUP.md` but not installed automatically:
 
-| Recommendation | For |
-|----------------|-----|
-| `superpowers` | Community skill registry and agent workflows |
-| `caveman` | Strict low-abstraction workflow/style capability |
-| `agent-research` | Broader product, dependency, and ecosystem research agents |
-| `codegraph` | Code graph or repository-map tooling |
+| Recommendation | For | Source |
+|----------------|-----|--------|
+| `superpowers` | Community skill registry and agent workflows | <https://github.com/obra/Superpowers> |
+| `caveman` | Terse, low-token agent behavior and memory compression | <https://github.com/JuliusBrussee/caveman> |
+| `agent-research` | Research-agent skills for literature, product, dependency, and ecosystem investigation | <https://github.com/lingzhi227/agent-research-skills> |
+| `codegraph` | Code graph or repository-map tooling | <https://github.com/colbymchenry/codegraph> |
+
+These are links for the user's agent to evaluate. The scaffold does not maintain third-party install steps; it only records selected recommendations after checking what is already installed.
 
 ### Agent-link intake
 
 When your agent reads the one-sentence prompt above, it must first scan the project root, then ask **at most 3 blocking questions** before touching files.
 
-Root scan checklist: list top-level files, detect `CLAUDE.md`, `AGENTS.md`, `.claude/`, `.agents/`, `.codex/`, `Harness/`, package files, CI files, docs folders, and obvious app entry points.
+Root scan checklist: list top-level files, detect `CLAUDE.md`, `AGENTS.md`, `.claude/`, `.agents/`, `.codex/`, `Harness/`, package files, CI files, docs folders, obvious app entry points, test/build commands, and installed skills/plugins/rules.
 
 Ask these only when they affect writes:
 
 - If `CLAUDE.md` or `AGENTS.md` already exists, should missing Harness guidance be merged, kept separate, or skipped?
 - If `Harness/` already exists, should the agent run update/dry-run, merge missing files, keep it untouched, or remove/reinstall after approval?
-- Which optional capabilities should be enabled: local workflows (`browser-e2e`, `ui-ux-review`, `ts-react-frontend`, `python-backend`, `github-pr-review`) and recommendation-only external options (`Superpowers`, `Caveman`, `agent research`, `code graph`)?
+- Which optional capabilities should be enabled, after excluding capabilities already installed: local workflows (`browser-e2e`, `ui-ux-review`, `ts-react-frontend`, `python-backend`, `github-pr-review`) and recommendation-only external links (`Superpowers`, `Caveman`, `agent research`, `code graph`)?
 
 Harness docs always live in root `Harness/`; do not route Harness files through `docs/`. If a file already exists, the agent asks first. The default is always **preserve**.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-harness-vibe-coding",
-  "version": "0.8.0",
+  "version": "0.8.1",
   "description": "Scaffold a 0-1 product harness for AI-assisted research, PRD, planning, architecture, build, test, and feedback loops",
   "type": "module",
   "bin": {

package/src/generator.js

@@ -377,7 +377,7 @@ function registerExternalRecommendations(file, content, selectedRecommendations)
   if (!selectedRecommendations.length || file !== 'Harness/SETUP.md') return content;
 
   const lines = selectedRecommendations.map(item => (
-    `- \`${item.id}\` - ${item.description} Recommendation only; not installed by this scaffold. Use the discovery/install hint: ${item.installHint}`
+    `- \`${item.id}\` - ${item.description} Recommendation only; not installed by this scaffold. Source: ${item.url}`
   ));
 
   return `${content.trimEnd()}\n\n## Selected External Recommendations\n\n${lines.join('\n')}\n`;

package/src/index.js

@@ -377,7 +377,7 @@ function printOptions() {
     console.log('');
     console.log(pc.bold('External recommendations:'));
     for (const item of catalog.externalRecommendations) {
-      console.log(`  ${pc.cyan(item.id)} - ${item.description} (${item.installMode})`);
+      console.log(`  ${pc.cyan(item.id)} - ${item.description} (${item.installMode}) ${item.url || ''}`.trimEnd());
     }
   }
   console.log('');

package/src/prompts.js

@@ -73,7 +73,7 @@ export async function askOptionalSelections(catalog) {
   const externalOptions = (catalog.externalRecommendations || []).map(item => ({
     value: item.id,
     label: item.title,
-    hint: `${item.description} Recommendation only.`,
+    hint: item.url ? `${item.description} ${item.url}` : `${item.description} Recommendation only.`,
   }));
 
   const selectedLocal = localOptions.length

package/templates/common/.harness-version

@@ -1,6 +1,6 @@
 {
-  "generator": "0.8.0",
-  "generated": "2026-07-01T04:31:49.043Z",
+  "generator": "0.8.1",
+  "generated": "2026-07-01T06:31:02.525Z",
   "options": [],
   "autoCheck": true,
   "source": "https://raw.githubusercontent.com/zingspark/create-harness-vibe-coding/main/templates/common/",
@@ -44,7 +44,7 @@
     "CLAUDE.md": "sha256-432bd4dc9bdf9958d79ae697f72d1c9723be23fb156d43889ede84e305ed5e70",
     "Harness/MEMORY.md": "sha256-68b3e2b68880814bad11aa6d444d6b736848ac14c2a758ec3225c688a2c1882e",
     "Harness/README.md": "sha256-6608f74400dbae1e73b838d6b74f02e73a0b0e54404e899628dde6ccfbf06cf4",
-    "Harness/SETUP.md": "sha256-742d37c31ed6caccd39db499dc316528ec293396fe9a1ac84c47e408f6ab9839",
+    "Harness/SETUP.md": "sha256-e0fdd6a7751595f62f15d4374e1f201fcd0aa8b8ac44528a39cbf5b04db0e3bd",
     "Harness/WF-MAX.md": "sha256-81c788ac56a0c1673a9e6bdf619efbcfa9c961ca7c5065c15b98760775f963a6",
     "Harness/WF.md": "sha256-7cce2568444295cb387fa958cd4ef9711a19697b60ce9cba0e142484e0a165ae",
     "Harness/agent-workflow.md": "sha256-1aff5e7dc1e082c559cb0a9086c4f93f6702905aff00ebb957300f463ea80b31",

package/templates/common/SETUP.md

@@ -44,18 +44,27 @@ Claude must follow this order:
 10. Run `node Harness/scripts/validate-harness.mjs --strict`.
 11. Record final verification and next feedback step in `Harness/tasks/<task-id>/PROGRESS.md`. If repeated tool failures, repeated user corrections, or reusable review/debug lessons appeared, record the concise reflection in the relevant `Harness/memory/` file.
 
-## Existing Project Bootstrap Sequence
-
+## Install or Upgrade Path
+
+Before writing, identify the project state:
+
+| Project state | Required action |
+| --- | --- |
+| Empty or new project | Run the scaffold, then follow this file for 0-1 bootstrap |
+| Existing project, no `Harness/` | Scan project facts first, run `--dry-run`, preserve existing files, merge only missing Harness guidance |
+| Legacy architecture or older project docs | Treat existing code/docs as source of truth, dry-run first, then fill PRD, research, architecture, and task plans from observed facts |
+| Existing `Harness/` | Do not use `npx` as an updater; ask whether to run `/wf-update`, `$wf-update`, `node Harness/scripts/wf-update-check.mjs`, keep untouched, or remove/reinstall after approval |
+
 When adding this harness to a project that already has source code, docs, CI, or tool configuration, treat the existing project as the source of truth before filling harness docs.
 
-1. Scan existing project facts first: top-level files, `CLAUDE.md`, `AGENTS.md`, `.claude/`, `.agents/`, `.codex/`, `Harness/`, `README.md`, package files (`package.json`, `pyproject.toml`, `go.mod`, etc.), test commands, app entry points, CI files, existing docs, and current run/build scripts.
+1. Scan existing project facts first: top-level files, `CLAUDE.md`, `AGENTS.md`, `.claude/`, `.agents/`, `.codex/`, `Harness/`, `README.md`, package files (`package.json`, `pyproject.toml`, `go.mod`, etc.), test commands, app entry points, CI files, existing docs, current run/build scripts, and already-installed skills/plugins/rules.
 2. Record discovered facts and open questions in `Harness/tasks/<task-id>/PROGRESS.md` before changing harness docs.
 3. Fill `Harness/research/PRD.md`, `Harness/research/research-results.md`, `Harness/architecture.md` from observed project facts plus explicit user input.
-4. Existing configuration is project fact. Do not overwrite `CLAUDE.md`, `AGENTS.md`, `.claude/`, `.agents/`, `.codex/`, `.gitignore`, settings, hooks, package files, CI, docs routers, or workflow docs unless the user explicitly approves that exact overwrite.
+4. Existing configuration is project fact. Do not overwrite `CLAUDE.md`, `AGENTS.md`, `.claude/`, `.agents/`, `.codex/`, `.gitignore`, settings, hooks, package files, CI, docs routers, workflow docs, or installed skills/plugins/rules unless the user explicitly approves that exact overwrite.
 5. When a harness file conflicts with an existing file, preserve the existing file and register any missing harness guidance manually using `Harness/extension.md`.
 6. Run `node Harness/scripts/validate-harness.mjs` after registration, then run `node Harness/scripts/validate-harness.mjs --strict` only after project-fact placeholders have been resolved or intentionally recorded as open.
 
-`npx create-harness-vibe-coding` is an install/safe-merge entry, not an update engine for a project that already has an installed Harness. If `Harness/` already exists, use `/wf-update` or `node Harness/scripts/wf-update-check.mjs`; root entry files and user-modified Harness docs require agent-mediated merge decisions.
+`npx create-harness-vibe-coding` is an install/safe-merge entry, not an update engine for a project that already has an installed Harness. If `Harness/` already exists, use `/wf-update`, `$wf-update`, or `node Harness/scripts/wf-update-check.mjs`; root entry files and user-modified Harness docs require agent-mediated merge decisions.
 
 ### Agent-Link Install Intake
 
@@ -68,8 +77,8 @@ When the user installs by pasting the GitHub link into an agent, scan the projec
 | Harness location | Always | Use root `Harness/`; do not write harness docs into `docs/` |
 | README ownership | root `README.md` is a public product page, package docs, or heavily customized | Preserve existing README and propose a minimal Development section |
 | README optimization | existing README is stale, sparse, missing command tables, or the user asks for diagrams/polished docs | Offer `wf-readme`; default to append-only Development notes until the user approves a structure pass or full rewrite |
-| Extensions | ECC, Superpowers, custom rules, or stack-specific skills may be useful | Recommend first; install only after user approval |
-| Optional capabilities | stack is known or the user wants setup guidance | Offer local workflows plus recommendation-only external options: Superpowers, Caveman, agent research, and code graph |
+| Extensions | ECC, custom rules, or stack-specific skills may be useful | Scan installed skills/plugins/rules first; recommend only missing capabilities; install only after user approval |
+| Optional capabilities | stack is known or the user wants setup guidance | Offer local workflows plus recommendation-only GitHub links: Superpowers, Caveman, agent research, and code graph; do not duplicate already-installed capabilities |
 | Skills | stack is known and optional skills could improve testing, frontend, backend, review, or browser evidence | Install 1-2 relevant local workflows only after user approval |
 | CI/CD | CI config exists or the project lacks a test/build gate | Document existing commands first; add CI/CD only after user approval |
 | Verification depth | browser-visible, API, database, auth, payment, or deployment behavior is affected | Require real command evidence; require browser/API evidence when relevant |
@@ -129,7 +138,7 @@ The harness validator checks for specific structural invariants. When comparing
 | `Harness/PROGRESS.md` | global task index with Active Task and task history; cross-task decisions |
 | `Harness/tasks/<id>/PROGRESS.md` | `## Current Goal`, `## Phase`, `## Heartbeat`, `## Loaded Context` headings |
 | `Harness/tasks/<id>/PLAN.md` | `## Tasks`, `## Parallel Dispatch`, `## Subagent Synthesis`, `## Verification` headings |
-| `Harness/SETUP.md` | Only meaningful for fresh projects. If the project has its own onboarding docs, skip this file entirely (it is temporary). If kept, ensure the "Existing Project Bootstrap Sequence" is present. |
+| `Harness/SETUP.md` | Temporary install/bootstrap guide for new projects, existing projects, legacy upgrades, and Harness update decisions. If kept, ensure "Install or Upgrade Path" is present. |
 | `Harness/workflows/browser-e2e.md` (if installed as optional) | `data-testid`, `accessible labels/roles`, and `inputs, buttons, filters, rows, empty/error/loading states` requirement |
 | `Harness/workflows/ts-react-frontend.md` (if installed as optional) | Same UI selector contract as above |
 
@@ -153,7 +162,7 @@ npx create-harness-vibe-coding@latest my-app ./my-app -y --preset web-app
 npx create-harness-vibe-coding@latest my-app ./my-app -y --recommend superpowers,codegraph
 ```
 
-`--recommend` records recommendation-only external capabilities in this file. It does not install third-party skills or plugins.
+`--recommend` records recommendation-only external capability links in this file. It does not install third-party skills or plugins.
 
 ### Template Fill Guide
 
@@ -200,7 +209,7 @@ False confidence is worse than a question. If you catch yourself thinking "this
 
 ## How to Find Proper Skills
 
-After the architecture stage reveals your stack, install matching agent skills. Skills teach Claude Code and Codex domain-specific patterns, testing conventions, and design rules.
+After the architecture stage reveals your stack, inspect existing `.claude/skills/`, `.agents/skills/`, plugins, hooks, and custom rules before recommending anything. Skills teach Claude Code and Codex domain-specific patterns, testing conventions, and design rules, but duplicate skills create routing noise.
 
 **Built-in route**: invoke the `/find-skills` skill (or say "help me find skills for X"). Examples:
 
@@ -211,20 +220,24 @@ After the architecture stage reveals your stack, install matching agent skills.
 "I need a skill for PostgreSQL schema design."
 ```
 
-**Superpowers**: [Superpowers](https://github.com/obra/superpowers) is a community skill registry. Search it:
-
-```bash
-# If superpowers CLI or MCP is configured
-npx skills search "react testing"
-npx skills search "python api"
-```
+**External recommendation links**:
+
+| Recommendation | Source | Purpose |
+| --- | --- | --- |
+| Superpowers | <https://github.com/obra/Superpowers> | community skill registry and agent workflows |
+| Caveman | <https://github.com/JuliusBrussee/caveman> | terse, low-token agent behavior and memory compression |
+| Agent Research | <https://github.com/lingzhi227/agent-research-skills> | research-agent skills for literature, product, dependency, and ecosystem investigation |
+| CodeGraph | <https://github.com/colbymchenry/codegraph> | code graph or repository-map tooling |
+
+These are links for the user's agent to evaluate. This scaffold does not maintain third-party install steps. If a user selects one, first check whether an equivalent capability is already installed; then present the GitHub link and ask for approval before the user's agent follows that project's own README.
 
 **Manual discovery**: search GitHub and npm directly using patterns from `Harness/research/README.md#Architecture Decision References`.
 
 **Priority order**:
-1. `/find-skills` first — fastest discovery, respects your tool environment.
-2. Superpowers registry — broad community coverage.
-3. GitHub search — when the first two miss niche domains.
+1. Existing project skills/plugins/rules first - do not recommend duplicates.
+2. `/find-skills` or the runtime's local skill discovery - fastest and respects the user's tool environment.
+3. Selected external GitHub links - let the user's agent read that project's README and install only after approval.
+4. GitHub search - when the first three miss niche domains.
 
 **What to install**: after finding skills, add the canonical copy to `.claude/skills/<name>/SKILL.md` and mirror the same file to `.agents/skills/<name>/SKILL.md` when Codex should discover it. Follow `Harness/extension.md` for compatibility. Start with 1-2 skills per stack area; more is not better.
 

package/templates/optional/catalog.json

@@ -46,15 +46,15 @@
       "title": "Superpowers",
       "description": "Community skill registry for agent workflows and reusable coding skills.",
       "installMode": "recommend-only",
-      "installHint": "run skill discovery first, then install only the selected Superpowers skills after user approval",
+      "url": "https://github.com/obra/Superpowers",
       "tags": ["skills", "community", "subagents"]
     },
     {
       "id": "caveman",
       "title": "Caveman",
-      "description": "External workflow/style capability to evaluate for strict, low-abstraction implementation behavior.",
+      "description": "External terse-agent capability to evaluate for low-token behavior and memory compression.",
       "installMode": "recommend-only",
-      "installHint": "search the configured skill/plugin sources for Caveman and install only after checking provenance",
+      "url": "https://github.com/JuliusBrussee/caveman",
       "tags": ["workflow", "implementation", "style"]
     },
     {
@@ -62,7 +62,7 @@
       "title": "Agent Research",
       "description": "External research-agent capability for broader product, dependency, and ecosystem investigation.",
       "installMode": "recommend-only",
-      "installHint": "use available skill/plugin discovery for agent research and record the chosen source in Harness/MEMORY.md",
+      "url": "https://github.com/lingzhi227/agent-research-skills",
       "tags": ["research", "agents", "discovery"]
     },
     {
@@ -70,7 +70,7 @@
       "title": "Code Graph",
       "description": "External code graph or repository map capability for dependency and architecture exploration.",
       "installMode": "recommend-only",
-      "installHint": "use available code graph tooling only after confirming it supports the project language and privacy constraints",
+      "url": "https://github.com/colbymchenry/codegraph",
       "tags": ["code graph", "architecture", "analysis"]
     }
   ]