goalbuddy 0.2.22 → 0.3.1

package/CONTRIBUTING.md

@@ -14,12 +14,20 @@ npm run check
 
 ## Local Install Test
 
-Use a temporary Codex home so local testing does not overwrite your real install:
+GoalBuddy installs into Codex and Claude Code by default. Use temporary home directories so local testing does not overwrite your real install:
 
 ```bash
+# Both targets
+root=$(mktemp -d)
+node internal/cli/goal-maker.mjs --codex-home "$root/codex" --claude-home "$root/claude"
+node internal/cli/goal-maker.mjs doctor --target codex --codex-home "$root/codex"
+node internal/cli/goal-maker.mjs doctor --target claude --claude-home "$root/claude"
+rm -rf "$root"
+
+# One target
 tmp=$(mktemp -d)
-node internal/cli/goal-maker.mjs install --codex-home "$tmp"
-node internal/cli/goal-maker.mjs doctor --codex-home "$tmp"
+node internal/cli/goal-maker.mjs install --target claude --claude-home "$tmp"
+node internal/cli/goal-maker.mjs doctor --target claude --claude-home "$tmp"
 rm -rf "$tmp"
 ```
 
@@ -31,7 +39,7 @@ Before opening a PR, verify the npm package contents:
 npm pack --dry-run
 ```
 
-The package should include `README.md`, `internal/assets/`, `package.json`, `internal/cli/`, the canonical `goalbuddy/` skill directory, and `plugins/goalbuddy/`. The temporary `$goal-maker` compatibility skill is generated by the installer; do not add a second tracked skill payload.
+The package should include `README.md`, `internal/assets/`, `package.json`, `internal/cli/`, the canonical `goalbuddy/` skill directory, and `plugins/goalbuddy/` (with both `.codex-plugin/` and `.claude-plugin/` manifests). The temporary `$goal-maker` compatibility skill is generated by the installer; do not add a second tracked skill payload.
 
 ## Releases
 
@@ -40,7 +48,8 @@ GoalBuddy publishes from GitHub Actions with npm trusted publishing. See [RELEAS
 ## Contribution Guidelines
 
 - Keep the runtime dependency-free unless there is a strong reason.
-- Keep `goalbuddy/` installable as the canonical Codex skill directory.
+- Keep `goalbuddy/` installable as the canonical skill directory.
+- Keep installation working for both Codex and Claude Code.
 - Keep `$goal-maker` working as a generated compatibility alias until the migration window ends.
 - Prefer small, reviewable changes.
 - Update README or templates when behavior changes.

package/README.md

@@ -2,12 +2,12 @@
 
 <p align="center">
   <a href="https://goalbuddy.dev">
-    <img src="internal/assets/goalbuddy-readme-hero.png" alt="GoalBuddy turns vague Codex goals into structured progress with Scout, Judge, Worker, receipts, and verification." width="100%">
+    <img src="internal/assets/goalbuddy-readme-hero.png" alt="GoalBuddy: a /goal operating system for Codex and Claude Code with live boards, Scout, Judge, Worker, receipts, and verification." width="100%">
   </a>
 </p>
 
 <p align="center">
-  <strong>Turn open-ended Codex work into one reviewable goal board.</strong>
+  <strong>A /goal operating system for Codex and Claude Code: intake, live boards, agents, receipts, and verification.</strong>
 </p>
 
 <p align="center">
@@ -16,10 +16,12 @@
   <a href="https://goalbuddy.dev"><img alt="goalbuddy.dev" src="https://img.shields.io/badge/site-goalbuddy.dev-684cff?style=flat-square"></a>
 </p>
 
-GoalBuddy is a local Codex companion for work that is too broad to trust to a single prompt. It turns a vague request into a `goal.md` charter, a machine-readable `state.yaml` board, role-tagged Scout/Judge/Worker tasks, compact receipts, and verification before completion.
+GoalBuddy is a local companion for **Codex** and **Claude Code** when the work is too broad to trust to a single prompt. It turns rough intent into a durable operating loop: a `goal.md` charter, a machine-readable `state.yaml` board, optional visual boards, Scout/Judge/Worker task flow, compact receipts, and verification before completion.
 
 ```bash
-npx goalbuddy
+npx goalbuddy                  # installs for Codex and Claude Code
+npx goalbuddy --target codex   # installs for Codex only
+npx goalbuddy --target claude  # installs for Claude Code only
 ```
 
 Or install it globally:
@@ -28,19 +30,20 @@ Or install it globally:
 npm i -g goalbuddy
 ```
 
-Then restart Codex and invoke the installed skill:
+Then restart your AI coding agent and invoke the installed skill:
 
 ```text
-$goal-prep
+$goal-prep      # in Codex
+/goal-prep      # in Claude Code
 ```
 
-`$goal-prep` prepares the GoalBuddy board and prints the `/goal` command to run next. It does not start `/goal` automatically.
+`goal-prep` prepares the GoalBuddy board and prints the `/goal` command to run next. It does not start `/goal` automatically.
 
 ## Why GoalBuddy Exists
 
-Long Codex goals drift. A request like "improve this project" can turn into unbounded edits, stale verification, and premature completion claims.
+Long-running goals in Codex and Claude Code drift. A request like "improve this project" can turn into unbounded edits, stale verification, and premature completion claims.
 
-GoalBuddy gives Codex a durable loop:
+GoalBuddy gives your AI coding agent a durable loop:
 
 ```text
 vague goal -> Scout -> Judge -> Worker -> receipt -> verify -> repeat
@@ -70,40 +73,32 @@ GoalBuddy uses four primitives:
 - **Task**: exactly one active Scout, Judge, Worker, or PM task.
 - **Receipt**: compact proof for every completed, blocked, or escalated task.
 
-GoalBuddy bundles default agent templates. `$goal-prep` records whether matching installed agent configs were actually found; if not, `/goal` can continue through PM fallback, or you can install dedicated agents with:
+GoalBuddy bundles default agent templates. `goal-prep` records whether matching installed agent configs were actually found; if not, `/goal` can continue through PM fallback, or you can install dedicated agents with:
 
 ```bash
-npx goalbuddy agents
+npx goalbuddy agents                  # Codex TOML agents
+npx goalbuddy agents --target claude  # Claude Code markdown subagents
 ```
 
 - **Scout** maps repo evidence, workflows, constraints, risks, and candidate next tasks.
 - **Judge** resolves ambiguity, scope, risk, task selection, and completion claims.
 - **Worker** performs one bounded implementation or recovery slice with explicit files and checks.
 
-## Install And Check Readiness
-
-Install and enable the native Codex plugin:
+## Install Everywhere
 
 ```bash
 npx goalbuddy
 ```
 
-Restart Codex, then use `$goal-prep`. GoalBuddy ships with two visual board backends by default: a local live board and a GitHub Projects sync.
+This installs and enables the native Codex plugin in `~/.codex/`, then installs the GoalBuddy skill, Scout/Judge/Worker subagents, and `/goal-prep` slash command into `~/.claude/`. Restart Codex and Claude Code, then use `$goal-prep` in Codex or `/goal-prep` in Claude Code. The Codex plugin bundles the local live board and GitHub Projects visual board backends so Goal Prep can offer a board immediately.
 
-If you prefer a global executable, install the npm package globally and run `goalbuddy`:
+If you prefer a global executable:
 
 ```bash
 npm i -g goalbuddy
 goalbuddy
 ```
 
-Use the skill-only fallback if your Codex build does not support plugins:
-
-```bash
-npx goalbuddy install
-npx goalbuddy update
-```
-
 Native Codex `/goal` is still an under-development Codex feature. Before relying on the printed command, confirm your local Codex runtime is logged in and has goals enabled:
 
 ```bash
@@ -112,35 +107,40 @@ codex features enable goals
 npx goalbuddy doctor --goal-ready
 ```
 
-Repair only the bundled agent definitions:
+## Install One Target
+
+Use `--target` when you only want to install or update one agent environment:
 
 ```bash
-npx goalbuddy agents
+npx goalbuddy --target codex
+npx goalbuddy --target claude
 ```
 
-Check the local install:
+The Claude Code target installs the GoalBuddy skill, the three Scout/Judge/Worker subagents, and the `/goal-prep` slash command into `~/.claude/`. Restart Claude Code, then run:
 
-```bash
-npx goalbuddy doctor
+```text
+/goal-prep
 ```
 
-Check whether a newer GoalBuddy release is available:
+Check the local Claude Code install:
 
 ```bash
-npx goalbuddy check-update
+npx goalbuddy doctor --target claude
 ```
 
-Use a non-default Codex home:
+Use non-default homes:
 
 ```bash
-npx goalbuddy --codex-home /path/to/.codex
+npx goalbuddy --codex-home /path/to/.codex --claude-home /path/to/.claude
+npx goalbuddy --target codex --codex-home /path/to/.codex
+npx goalbuddy --target claude --claude-home /path/to/.claude
 ```
 
-`plugin install`, `install`, `update`, and `doctor` also support `--json` when an agent or script needs structured output.
+`install` and `update` prepare both targets by default. `install`, `update`, `doctor`, and `agents` all accept `--target claude|codex`, and `--json` for structured output.
 
 ## Run A Goal
 
-After `$goal-prep` creates or repairs the board, start the run with the printed command:
+After `goal-prep` creates or repairs the board, start the run with the printed command:
 
 ```text
 /goal Follow docs/goals/<slug>/goal.md.
@@ -149,7 +149,10 @@ After `$goal-prep` creates or repairs the board, start the run with the printed
 Check board health at any time:
 
 ```bash
+# Codex
 node ~/.codex/skills/goalbuddy/scripts/check-goal-state.mjs docs/goals/<slug>/state.yaml
+# Claude Code
+node ~/.claude/skills/goalbuddy/scripts/check-goal-state.mjs docs/goals/<slug>/state.yaml
 ```
 
 For a broad prompt like "Improve my project," the first active task should usually be Scout, not Worker:
@@ -181,9 +184,17 @@ tasks:
     receipt: null
 ```
 
+## Visual Boards
+
+GoalBuddy can show progress as the goal runs. `goal-prep` can open a local live board inside your AI coding agent before the task list is finished, or prepare a GitHub Projects sync when stakeholders need an external board.
+
+<p align="center">
+  <img src="internal/assets/goalbuddy-live-board.jpg" alt="GoalBuddy local live board open next to Codex while Scout, Judge, and Worker tasks populate." width="100%">
+</p>
+
 ## Extensions
 
-The npm package is the stable core. Local Board and GitHub Projects are bundled into the installed GoalBuddy skill so `$goal-prep` can offer a visual board immediately. Other optional extensions live under `extend/` and are discovered from the GitHub-hosted `extend/catalog.json`, so users do not need a new npm release for every integration.
+The npm package is the stable core. Local Board and GitHub Projects are bundled into the installed GoalBuddy skill so `goal-prep` can offer a visual board immediately. Other optional extensions live under `extend/` and are discovered from the GitHub-hosted `extend/catalog.json`, so users do not need a new npm release for every integration.
 
 ```bash
 npx goalbuddy board docs/goals/<slug>
@@ -228,20 +239,30 @@ Release automation for future npm publishes is documented in [RELEASE.md](RELEAS
 
 ## Repo Map
 
-- `goalbuddy/SKILL.md`: canonical Codex skill
-- `goalbuddy/agents/`: Scout, Judge, and Worker definitions
+- `goalbuddy/SKILL.md`: canonical skill definition (shared by Codex and Claude Code)
+- `goalbuddy/agents/`: Scout, Judge, and Worker agent definitions (Codex TOML; Claude Code markdown lives under `plugins/goalbuddy/agents/`)
 - `goalbuddy/templates/`: `goal.md`, `state.yaml`, and `note.md`
 - `goalbuddy/scripts/check-goal-state.mjs`: v2 board checker
-- `internal/cli/goal-maker.mjs`: npm installer CLI
-- `plugins/goalbuddy/`: repo-local Codex plugin package scaffold
+- `internal/cli/goal-maker.mjs`: npm installer CLI for Codex and Claude Code
+- `plugins/goalbuddy/`: Codex plugin (`.codex-plugin/`) and Claude Code plugin (`.claude-plugin/`) scaffolds
 - `extend/` and `extend/catalog.json`: GitHub-hosted extension surface
 - `examples/`: completed sample runs
 
 ## Status
 
-`0.2.x` is the v2 board and receipt model. It intentionally rejects old v1 `gate`, `units`, `artifacts`, and `evidence.jsonl` goal folders instead of auto-migrating them.
+`0.3.x` adds first-class Claude Code support alongside the existing Codex target. The v2 board and receipt model intentionally rejects old v1 `gate`, `units`, `artifacts`, and `evidence.jsonl` goal folders instead of auto-migrating them.
+
+Use GoalBuddy to structure autonomous coding-agent work. Keep relying on repo-specific `AGENTS.md`/`CLAUDE.md`, tests, and CI for repo facts.
+
+## Star History
 
-Use GoalBuddy to structure autonomous Codex work. Keep relying on repo-specific `AGENTS.md`, tests, and CI for repo facts.
+<a href="https://www.star-history.com/?repos=tolibear%2Fgoalbuddy&type=date&legend=top-left">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=tolibear/goalbuddy&type=date&theme=dark&legend=top-left" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=tolibear/goalbuddy&type=date&legend=top-left" />
+   <img alt="Star History Chart" src="https://api.star-history.com/chart?repos=tolibear/goalbuddy&type=date&legend=top-left" />
+ </picture>
+</a>
 
 ## License
 

package/goalbuddy/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: goal-prep
-description: Goal Prep for GoalBuddy. Use for broad, long-running, stalled, vague, detailed, planned, or unhealthy Codex work that needs a structured /goal intake, autonomous task discovery, role-tagged Scout/Judge/Worker delegation, one active task, durable receipts, and a PM-owned rolling board that maximizes the chance of a successful goal run.
+description: Goal Prep for GoalBuddy. Use for broad, long-running, stalled, vague, detailed, planned, or unhealthy Codex or Claude Code work that needs a structured /goal intake, autonomous task discovery, role-tagged Scout/Judge/Worker delegation, one active task, durable receipts, and a PM-owned rolling board that maximizes the chance of a successful goal run.
 ---
 
 # Goal Prep
 
-`$goal-prep` prepares a GoalBuddy board. It does not start `/goal` automatically, but the board and starter `/goal` command must be shaped so the next run continues into safe execution by default.
+`$goal-prep` (Codex) or `/goal-prep` (Claude Code) prepares a GoalBuddy board. It does not start `/goal` automatically, but the board and starter `/goal` command must be shaped so the next run continues into safe execution by default.
 
-GoalBuddy is for autonomous, long-running Codex work where the PM thread may need to discover the work, define tasks, sequence them, delegate them, execute them, verify them, and keep going without the human decomposing every step.
+GoalBuddy is for autonomous, long-running Codex or Claude Code work where the PM thread may need to discover the work, define tasks, sequence them, delegate them, execute them, verify them, and keep going without the human decomposing every step.
 
 The loop is:
 
@@ -81,11 +81,11 @@ Do you want to set up a visual board for this?
 
 Recommended options:
 
-1. Local live board in Codex (Recommended) - starts immediately, requires no credentials, and lets the user watch tasks populate.
+1. Local live board (Recommended) - starts immediately, requires no credentials, and lets the user watch tasks populate inside Codex or Claude Code.
 2. GitHub Projects - best when stakeholders need a shared external board and the user can approve GitHub credentials/project details.
 3. No visual board - best for quick or private goals where the file board is enough.
 
-If the user chooses the local live board, create the goal directory, `notes/`, and an initial minimal `state.yaml` as soon as the slug is known, then run `npx goalbuddy board docs/goals/<slug>` and open the printed local URL in the Codex in-app Browser. In short: start the local board before filling the task list so the board pops up right away and cards populate live as `state.yaml` changes. Keep the printed URL in the final prep response as a fallback, but do not make the URL the primary experience.
+If the user chooses the local live board, create the goal directory, `notes/`, and an initial minimal `state.yaml` as soon as the slug is known, then run `npx goalbuddy board docs/goals/<slug>` and open the printed local URL in the AI coding agent's in-app browser (the Codex in-app Browser, the Claude Code preview, or the user's regular browser). In short: start the local board before filling the task list so the board pops up right away and cards populate live as `state.yaml` changes. Keep the printed URL in the final prep response as a fallback, but do not make the URL the primary experience.
 
 If the user chooses GitHub Projects, ask for approval and the required project target before any live write. Create or sync the GitHub Project at the same early point as the local board: after the goal root and skeleton `state.yaml` exist, before the detailed task list is finished, then sync again as tasks populate. Run a dry-run sync first when possible. Missing GitHub credentials or project details should not block local board creation or goal prep; record the missing requirement in `visual_board.github_projects` and seed a PM setup task.
 
@@ -138,11 +138,11 @@ Minimum diagnostic ladder for vague, strategic, or improvement-oriented goals:
 2. Intent target: what kind of improvement or outcome matters most?
 3. Success proof: what evidence would convince the user this worked?
 4. Scope and non-goals: what should remain untouched or explicitly out of scope?
-5. Board handling: reuse an existing board, create a fresh board, or inspect first?
+5. Goal handling: reuse an existing goal, create a fresh goal, or inspect first?
 
 Ask these one at a time. Skip a step only when the user's words already answer it clearly. After the user answers one step, do not assume the remaining steps; ask the next unresolved material question.
 
-For "make GoalBuddy better", a good first question is which improvement target matters most: intake clarity, board/execution reliability, completion proof/eval coverage, or user experience during long-running goals. A good second question asks what proof would convince the user it improved. A good third question asks whether to reuse an existing board, create a fresh board, or inspect first.
+For "make GoalBuddy better", a good first question is which improvement target matters most: intake clarity, board/execution reliability, completion proof/eval coverage, or user experience during long-running goals. A good second question asks what proof would convince the user it improved. A good third question asks whether to reuse an existing goal, create a fresh goal, or inspect first.
 
 ## Direct `/goal` Entry
 
@@ -173,7 +173,7 @@ Do:
 - classify the goal as `specific`, `open_ended`, `existing_plan`, `recovery`, or `audit`;
 - create or repair `docs/goals/<slug>/`;
 - create `goal.md`, `state.yaml`, and `notes/`;
-- if requested, start the local visual board immediately and open it in the Codex in-app Browser before filling the task list;
+- if requested, start the local visual board immediately and open it in the AI coding agent's in-app browser (Codex in-app Browser, Claude Code preview, or the user's regular browser) before filling the task list;
 - seed a role-tagged task board that matches the input shape;
 - make the first active task safe;
 - verify Scout, Worker, and Judge agent availability or record an explicit truthful state;

package/goalbuddy/agents/README.md

@@ -1,17 +1,22 @@
 # GoalBuddy Agents
 
-This directory contains both skill metadata and bundled agent definitions.
+This directory contains skill metadata and bundled agent definitions for Codex and Claude Code.
+
+## Files
 
 - `openai.yaml` stays with the skill as metadata.
-- `goal_*.toml` files can be copied into `.codex/agents/` for project-scoped agents or `~/.codex/agents/` for personal agents.
+- `goal_scout.toml`, `goal_judge.toml`, `goal_worker.toml` — Codex agent configs. Copy into `.codex/agents/` for project-scoped agents or `~/.codex/agents/` for personal agents.
+- Claude Code agent markdown lives in `plugins/goalbuddy/agents/` (installed to `~/.claude/agents/` by `npx goalbuddy --target claude`).
+
+## Agent Matrix
 
-| Agent | File | Reasoning effort | Sandbox |
-|---|---|---:|---|
-| Scout | `goal_scout.toml` | medium | read-only |
-| Worker | `goal_worker.toml` | low | workspace-write |
-| Judge | `goal_judge.toml` | high | read-only |
+| Agent | Codex file | Claude Code file | Reasoning effort | Write scope |
+|---|---|---|---:|---|
+| Scout | `goal_scout.toml` | `goal-scout.md` | medium | read-only |
+| Worker | `goal_worker.toml` | `goal-worker.md` | low | workspace-write |
+| Judge | `goal_judge.toml` | `goal-judge.md` | high | read-only |
 
-Recommended config:
+## Recommended Codex Config
 
 ```toml
 [agents]
@@ -20,4 +25,6 @@ max_depth = 1
 job_max_runtime_seconds = 1800
 ```
 
+## Authority Boundary
+
 Only the main `/goal` PM loop may select the active task, mark tasks done, update board truth, or mark the goal complete.

package/internal/cli/goal-maker.mjs

@@ -25,24 +25,33 @@ const canonicalSkillDirectory = "goalbuddy";
 const legacyCliName = "goal-maker";
 const legacySkillName = "goal-maker";
 const skillSource = join(packageRoot, canonicalSkillDirectory);
+const claudePluginSource = join(packageRoot, "plugins", "goalbuddy");
 const packageInfo = JSON.parse(readFileSync(join(packageRoot, "package.json"), "utf8"));
 const defaultCodexHome = process.env.CODEX_HOME || join(homedir(), ".codex");
+const defaultClaudeHome = process.env.CLAUDE_HOME || join(homedir(), ".claude");
 const defaultCatalogUrl = "https://raw.githubusercontent.com/tolibear/goalbuddy/main/extend/catalog.json";
 const requiredAgentFiles = [
   "goal_judge.toml",
   "goal_scout.toml",
   "goal_worker.toml",
 ];
+const requiredClaudeAgentFiles = [
+  "goal-scout.md",
+  "goal-judge.md",
+  "goal-worker.md",
+];
 const bundledCoreExtensionIds = new Set(["github-projects", "local-goal-board"]);
 const optionsWithValues = new Set([
   "--catalog",
   "--catalog-url",
+  "--claude-home",
   "--codex-home",
   "--goal",
   "--host",
   "--kind",
   "--port",
   "--source",
+  "--target",
 ]);
 
 const args = process.argv.slice(2);
@@ -62,17 +71,37 @@ async function main() {
   maybePrintLegacyNotice();
   switch (command) {
     case "default":
-      installPlugin();
+      if (installTargetMode() === "all") {
+        await installEverywhere();
+      } else if (installTargetMode() === "codex") {
+        installPlugin();
+      } else {
+        await installClaudeAll();
+      }
       break;
     case "install":
     case "update":
-      await installAll();
+      if (installTargetMode() === "all") {
+        await installEverywhere();
+      } else if (installTargetMode() === "codex") {
+        await installAll();
+      } else {
+        await installClaudeAll();
+      }
       break;
     case "agents":
-      installAgents();
+      if (targetMode() === "codex") {
+        installAgents();
+      } else {
+        installClaudeAgents();
+      }
       break;
     case "doctor":
-      doctor();
+      if (targetMode() === "codex") {
+        doctor();
+      } else {
+        doctorClaude();
+      }
       break;
     case "check-update":
     case "update-check":
@@ -146,15 +175,15 @@ function positionalArgs() {
 }
 
 function usage() {
-  console.log(`Codex ${canonicalProductName}
+  console.log(`${canonicalProductName} for Claude Code and Codex
 
 Usage:
-  ${canonicalCliName} [--codex-home <path>] [--json]
+  ${canonicalCliName} [--target claude|codex] [--claude-home <path>] [--codex-home <path>] [--json]
   ${canonicalCliName} plugin install [--source <marketplace-source>] [--codex-home <path>] [--json]
-  ${canonicalCliName} install [--codex-home <path>] [--force] [--json]
-  ${canonicalCliName} update [--codex-home <path>] [--json]
-  ${canonicalCliName} agents [--codex-home <path>] [--force]
-  ${canonicalCliName} doctor [--codex-home <path>] [--goal-ready]
+  ${canonicalCliName} install [--target claude|codex] [--claude-home <path>] [--codex-home <path>] [--force] [--json]
+  ${canonicalCliName} update [--target claude|codex] [--claude-home <path>] [--codex-home <path>] [--json]
+  ${canonicalCliName} agents [--target claude|codex] [--claude-home <path>] [--codex-home <path>] [--force]
+  ${canonicalCliName} doctor [--target claude|codex] [--claude-home <path>] [--codex-home <path>] [--goal-ready]
   ${canonicalCliName} check-update [--json]
   ${canonicalCliName} extend [--catalog-url <url-or-path>] [--kind <kind>] [--json]
   ${canonicalCliName} extend <id> [--catalog-url <url-or-path>] [--json]
@@ -163,17 +192,19 @@ Usage:
   ${canonicalCliName} extend doctor [<id>] [--codex-home <path>] [--json]
   ${canonicalCliName} board <docs/goals/slug> [--catalog-url <url-or-path>] [--host <host>] [--port <port>] [--once] [--json]
 
-Default:
-  ${canonicalCliName}  Installs and enables the native Codex plugin.
+Targets: by default, install/update prepares both Codex (~/.codex) and Claude Code (~/.claude). Use --target codex or --target claude to limit the command.
 
-Skill-only fallback:
-  ${canonicalCliName} install  Installs the legacy skill payload and bundled agent definitions.
+Default:
+  ${canonicalCliName}                  Installs and enables Codex, then installs Claude Code skill + agents (skill surfaces /goal-prep).
+  ${canonicalCliName} --target claude  Installs ${canonicalProductName} for Claude Code (skill + agents; skill surfaces /goal-prep).
+  ${canonicalCliName} --target codex   Installs and enables the native Codex plugin.
 
 Compatibility:
   ${legacyCliName} remains a temporary alias and prints the new npx command for human-facing use.
 
 Environment:
   CODEX_HOME                         Overrides the default ~/.codex target.
+  CLAUDE_HOME                        Overrides the default ~/.claude target (and selects Claude Code unless --target codex is set).
   GOALBUDDY_EXTEND_CATALOG_URL       Overrides the default GitHub-hosted extension catalog.
   GOAL_MAKER_EXTEND_CATALOG_URL      Legacy fallback for the extension catalog.
 `);
@@ -183,6 +214,255 @@ function codexHome() {
   return resolve(optionValue("--codex-home") || defaultCodexHome);
 }
 
+function claudeHome() {
+  return resolve(optionValue("--claude-home") || defaultClaudeHome);
+}
+
+function targetMode() {
+  const value = (optionValue("--target") || "").toLowerCase();
+  if (value === "codex" || value === "claude") return value;
+  // Explicit --claude-home or CLAUDE_HOME implies Claude target unless --target codex is set.
+  if (optionValue("--claude-home") || process.env.CLAUDE_HOME) return "claude";
+  return "codex";
+}
+
+function installTargetMode() {
+  const value = (optionValue("--target") || "").toLowerCase();
+  if (value === "codex" || value === "claude") return value;
+
+  const hasCodexHomeOption = Boolean(optionValue("--codex-home"));
+  const hasClaudeHomeOption = Boolean(optionValue("--claude-home"));
+  if (hasCodexHomeOption && !hasClaudeHomeOption) return "codex";
+  if (hasClaudeHomeOption && !hasCodexHomeOption) return "claude";
+  if (process.env.CLAUDE_HOME && !hasCodexHomeOption) return "claude";
+  return "all";
+}
+
+function claudeSkillRoot() {
+  return join(claudeHome(), "skills", canonicalSkillDirectory);
+}
+
+function claudeAgentsRoot() {
+  return join(claudeHome(), "agents");
+}
+
+function legacyClaudeCommandPath() {
+  return join(claudeHome(), "commands", "goal-prep.md");
+}
+
+function installClaudeSkill({ quiet = false } = {}) {
+  const target = claudeSkillRoot();
+  if (!existsSync(skillSource)) {
+    console.error(`Skill payload not found: ${skillSource}`);
+    process.exit(1);
+  }
+
+  const previousMetadata = readInstallMetadata(target);
+  const previousFingerprint = existsSync(target) ? directoryFingerprint(target, { exclude: installFingerprintExcludes() }) : "";
+  const preservedExtensions = preserveInstalledExtensions([target], { tempRoot: claudeHome() });
+  const extensionTempPath = preservedExtensions.tempPath;
+  const preservedExtensionIds = preservedExtensions.ids;
+
+  mkdirSync(dirname(target), { recursive: true });
+  rmSync(target, { recursive: true, force: true });
+  cpSync(skillSource, target, { recursive: true });
+  restoreInstalledExtensions(target, extensionTempPath);
+  writeInstallMetadata(target, previousMetadata);
+  cleanupPreservedExtensions([extensionTempPath]);
+
+  const currentFingerprint = directoryFingerprint(target, { exclude: installFingerprintExcludes() });
+  const status = previousFingerprint
+    ? previousFingerprint === currentFingerprint ? "unchanged" : "updated"
+    : "installed";
+  if (!quiet) console.log(`Installed Claude Code ${canonicalProductName} skill to ${target}`);
+
+  return {
+    status,
+    path: target,
+    previous_version: previousMetadata?.package_version || "",
+    current_version: packageInfo.version,
+    preserved_extensions: preservedExtensionIds,
+  };
+}
+
+function installClaudeAgents({ quiet = false } = {}) {
+  const source = join(claudePluginSource, "agents");
+  const target = claudeAgentsRoot();
+  const force = hasFlag("--force") || command === "update" || command === "install" || command === "default";
+  mkdirSync(target, { recursive: true });
+
+  const results = [];
+  if (!existsSync(source)) return results;
+  for (const file of readdirSync(source)) {
+    if (!file.endsWith(".md")) continue;
+    const dest = join(target, file);
+    const sourceHash = sha256(readFileSync(join(source, file)));
+    const previousHash = existsSync(dest) ? sha256(readFileSync(dest)) : "";
+    if (existsSync(dest) && !force) {
+      if (!quiet) console.log(`skip existing ${dest} (use --force to overwrite)`);
+      results.push({ file, status: "skipped", path: dest });
+      continue;
+    }
+    cpSync(join(source, file), dest);
+    const status = previousHash ? previousHash === sourceHash ? "unchanged" : "updated" : "installed";
+    if (!quiet) console.log(`installed ${dest}`);
+    results.push({ file, status, path: dest });
+  }
+  return results;
+}
+
+function cleanupLegacyClaudeCommands({ quiet = false } = {}) {
+  const legacyPath = legacyClaudeCommandPath();
+  if (!existsSync(legacyPath)) return { removed: false, path: legacyPath };
+  rmSync(legacyPath, { force: true });
+  if (!quiet) console.log(`removed legacy ${legacyPath} (skill now surfaces /goal-prep)`);
+  return { removed: true, path: legacyPath };
+}
+
+async function buildClaudeInstallReport() {
+  const quiet = true;
+  const report = {
+    command,
+    target: "claude",
+    package: {
+      name: packageInfo.name,
+      current_version: packageInfo.version,
+    },
+    claude_home: claudeHome(),
+    skill: installClaudeSkill({ quiet }),
+    agents: installClaudeAgents({ quiet }),
+    legacy_commands_cleanup: cleanupLegacyClaudeCommands({ quiet }),
+    extensions: await extensionDiscoverySummary(),
+    warnings: [],
+  };
+
+  report.package.previous_version = report.skill.previous_version;
+  return report;
+}
+
+async function installClaudeAll() {
+  const report = await buildClaudeInstallReport();
+
+  if (hasFlag("--json")) {
+    printJson(report);
+  } else {
+    printClaudeInstallReport(report);
+  }
+}
+
+async function installEverywhere() {
+  const report = {
+    command,
+    package: {
+      name: packageInfo.name,
+      current_version: packageInfo.version,
+    },
+    codex: null,
+    claude: null,
+    errors: [],
+  };
+
+  try {
+    report.codex = installPlugin({ quiet: true });
+  } catch (error) {
+    report.errors.push({ target: "codex", error: error.message });
+    report.codex = { target: "codex", ok: false, error: error.message };
+  }
+
+  try {
+    report.claude = await buildClaudeInstallReport();
+  } catch (error) {
+    report.errors.push({ target: "claude", error: error.message });
+    report.claude = { target: "claude", ok: false, error: error.message };
+  }
+
+  report.ok = report.errors.length === 0;
+
+  if (hasFlag("--json")) {
+    printJson(report);
+  } else {
+    printEverywhereInstallReport(report);
+  }
+
+  if (!report.ok) process.exit(1);
+}
+
+function doctorClaude() {
+  const skillPath = join(claudeSkillRoot(), "SKILL.md");
+  const agentsPath = claudeAgentsRoot();
+  const installed = existsSync(skillPath);
+  const agents = existsSync(agentsPath)
+    ? readdirSync(agentsPath).filter((file) => file.startsWith("goal-") && file.endsWith(".md"))
+    : [];
+  const missingAgents = requiredClaudeAgentFiles.filter((file) => !agents.includes(file));
+  const staleAgents = requiredClaudeAgentFiles.filter((file) => {
+    const installedAgent = join(agentsPath, file);
+    const bundledAgent = join(claudePluginSource, "agents", file);
+    if (!existsSync(installedAgent) || !existsSync(bundledAgent)) return false;
+    return sha256(readFileSync(installedAgent)) !== sha256(readFileSync(bundledAgent));
+  });
+  const legacyCommandPath = legacyClaudeCommandPath();
+  const legacyCommandPresent = existsSync(legacyCommandPath);
+
+  console.log(JSON.stringify({
+    target: "claude",
+    claude_home: claudeHome(),
+    skill_installed: installed,
+    skill_path: skillPath,
+    installed_agents: agents,
+    missing_agents: missingAgents,
+    stale_agents: staleAgents,
+    legacy_command_present: legacyCommandPresent,
+    legacy_command_path: legacyCommandPath,
+  }, null, 2));
+
+  const installOk = installed && missingAgents.length === 0 && staleAgents.length === 0 && !legacyCommandPresent;
+  process.exit(installOk ? 0 : 1);
+}
+
+function printClaudeInstallReport(report) {
+  const verb = report.command === "update" ? "Updated" : "Installed";
+  const previous = report.package.previous_version && report.package.previous_version !== report.package.current_version
+    ? ` ${report.package.previous_version} -> ${report.package.current_version}`
+    : ` ${report.package.current_version}`;
+  console.log("");
+  console.log(`${verb} ${canonicalProductName} for Claude Code${previous}`);
+  console.log("");
+  console.log(`Skill: ${report.skill.status} at ${report.skill.path}`);
+  console.log(`Agents: ${summarizeStatuses(report.agents)}`);
+  if (report.legacy_commands_cleanup?.removed) {
+    console.log(`Removed legacy command: ${report.legacy_commands_cleanup.path}`);
+  }
+  if (report.skill.preserved_extensions.length) {
+    console.log(`Preserved extensions: ${report.skill.preserved_extensions.join(", ")}`);
+  }
+
+  if (report.extensions?.error) {
+    console.log("");
+    console.log(`Extensions: unavailable (${report.extensions.error})`);
+  } else if (report.extensions) {
+    console.log("");
+    console.log(`Extensions: ${report.extensions.available_count} available from ${report.extensions.catalog_url}`);
+    if (report.extensions.recommended?.length) {
+      console.log("");
+      console.log("Recommended:");
+      for (const extension of report.extensions.recommended.slice(0, 3)) {
+        console.log(`  ${extension.name || extension.id}`);
+        if (extension.summary) console.log(`    ${extension.summary}`);
+        console.log(`    Details: npx ${extension.next_command}`);
+      }
+    }
+  }
+
+  console.log("");
+  console.log("Next:");
+  console.log(`  Restart Claude Code, then run: /goal-prep`);
+  console.log(`  Or invoke the skill: ${canonicalSkillName}`);
+  console.log("");
+  console.log("Also available for Codex:");
+  console.log(`  npx ${canonicalCliName} --target codex`);
+}
+
 function installSkill({ force = true, quiet = false } = {}) {
   const target = installedSkillRoot();
   const legacyTarget = legacyInstalledSkillRoot();
@@ -193,7 +473,7 @@ function installSkill({ force = true, quiet = false } = {}) {
 
   const previousMetadata = readInstallMetadata(target) || readInstallMetadata(legacyTarget);
   const previousFingerprint = existsSync(target) ? directoryFingerprint(target, { exclude: installFingerprintExcludes() }) : "";
-  const preservedExtensions = preserveInstalledExtensions([target, legacyTarget]);
+  const preservedExtensions = preserveInstalledExtensions([target, legacyTarget], { tempRoot: codexHome() });
   const extensionTempPath = preservedExtensions.tempPath;
   const preservedExtensionIds = preservedExtensions.ids;
 
@@ -417,7 +697,7 @@ Default source:
 `);
 }
 
-function installPlugin() {
+function installPlugin({ quiet = false } = {}) {
   const source = optionValue("--source") || "tolibear/goalbuddy";
   const pluginSource = join(packageRoot, "plugins", pluginName);
   const pluginManifestPath = join(pluginSource, ".codex-plugin", "plugin.json");
@@ -427,35 +707,47 @@ function installPlugin() {
 
   const pluginManifest = JSON.parse(readFileSync(pluginManifestPath, "utf8"));
   const pluginCachePath = pluginCacheRoot(pluginManifest.version);
+  const pluginSkillPath = join(pluginCachePath, "skills", canonicalSkillDirectory);
   const marketplace = runCodex(["plugin", "marketplace", "add", source]);
   if (!marketplace.ok) {
     throw new Error(`Failed to add Codex plugin marketplace: ${firstLine(marketplace.stderr || marketplace.stdout)}`);
   }
 
+  const existingPluginSkillPath = installedPluginSkillRoot();
+  const preservedExtensions = preserveInstalledExtensions([existingPluginSkillPath], { tempRoot: dirname(pluginCachePath) });
   mkdirSync(dirname(pluginCachePath), { recursive: true });
   rmSync(pluginCachePath, { recursive: true, force: true });
   cpSync(pluginSource, pluginCachePath, { recursive: true });
+  restoreInstalledExtensions(pluginSkillPath, preservedExtensions.tempPath);
+  cleanupPreservedExtensions([preservedExtensions.tempPath]);
   const configPath = enablePluginConfig();
 
   const report = {
     installed: true,
+    target: "codex",
     plugin: `${pluginName}@${pluginName}`,
     version: pluginManifest.version,
     codex_home: codexHome(),
     marketplace_source: source,
     cache_path: pluginCachePath,
     config_path: configPath,
+    preserved_extensions: preservedExtensions.ids,
   };
 
-  if (hasFlag("--json")) {
+  if (hasFlag("--json") && !quiet) {
     printJson(report);
-    return;
+    return report;
   }
 
+  if (quiet) return report;
+
   console.log(`Installed ${canonicalProductName} Codex plugin ${pluginManifest.version}`);
   console.log(`Marketplace: ${source}`);
   console.log(`Cache: ${pluginCachePath}`);
   console.log(`Config: ${configPath}`);
+  if (report.preserved_extensions.length) {
+    console.log(`Preserved extensions: ${report.preserved_extensions.join(", ")}`);
+  }
   console.log("");
   console.log("Restart Codex, then use:");
   console.log(`  $${canonicalSkillName}`);
@@ -463,6 +755,7 @@ function installPlugin() {
   console.log("Bundled visual boards:");
   console.log(`  npx ${canonicalCliName} board docs/goals/<slug>`);
   console.log(`  npx ${canonicalCliName} extend github-projects`);
+  return report;
 }
 
 function pluginCacheRoot(version) {
@@ -1101,11 +1394,13 @@ function listFiles(root, { exclude = new Set(), prefix = "" } = {}) {
   return files;
 }
 
-function preserveInstalledExtensions(targets) {
+function preserveInstalledExtensions(targets, { tempRoot = "" } = {}) {
   const ids = [];
-  const tempPath = join(codexHome(), `.goalbuddy-preserved-extend-${process.pid}-${Date.now()}`);
+  const firstTarget = targets.find(Boolean) || codexHome();
+  const tempPath = join(tempRoot || dirname(dirname(firstTarget)), `.goalbuddy-preserved-extend-${process.pid}-${Date.now()}`);
   let hasExtensions = false;
   for (const target of targets) {
+    if (!target) continue;
     const source = join(target, "extend");
     if (!existsSync(source)) continue;
     mkdirSync(tempPath, { recursive: true });
@@ -1261,6 +1556,43 @@ function printInstallReport(report) {
   console.log(`  ${legacyCliName} remains a temporary compatibility alias.`);
 }
 
+function printEverywhereInstallReport(report) {
+  const verb = report.command === "update" ? "Updated" : "Installed";
+  console.log("");
+  console.log(`${verb} ${canonicalProductName} for Codex and Claude Code ${report.package.current_version}`);
+  console.log("");
+
+  if (report.codex?.ok === false) {
+    console.log(`Codex: not completed (${report.codex.error})`);
+  } else if (report.codex) {
+    console.log(`Codex: plugin ${report.codex.version} enabled at ${report.codex.cache_path}`);
+    if (report.codex.preserved_extensions?.length) {
+      console.log(`Codex preserved extensions: ${report.codex.preserved_extensions.join(", ")}`);
+    }
+  }
+
+  if (report.claude?.ok === false) {
+    console.log(`Claude Code: not completed (${report.claude.error})`);
+  } else if (report.claude) {
+    console.log(`Claude Code: skill ${report.claude.skill.status} at ${report.claude.skill.path}`);
+    console.log(`Claude Code agents: ${summarizeStatuses(report.claude.agents)}`);
+    if (report.claude.legacy_commands_cleanup?.removed) {
+      console.log(`Claude Code: removed legacy command at ${report.claude.legacy_commands_cleanup.path}`);
+    }
+  }
+
+  if (report.errors.length) {
+    console.log("");
+    console.log("One or more targets need attention:");
+    for (const error of report.errors) console.log(`  ${error.target}: ${error.error}`);
+  }
+
+  console.log("");
+  console.log("Next:");
+  console.log(`  Restart Codex, then use: $${canonicalSkillName}`);
+  console.log("  Restart Claude Code, then run: /goal-prep");
+}
+
 function summarizeStatuses(items) {
   const counts = items.reduce((memo, item) => {
     memo[item.status] = (memo[item.status] || 0) + 1;

package/internal/cli/postinstall.mjs

@@ -12,7 +12,7 @@ if (!globalInstall || process.env.GOALBUDDY_SKIP_POSTINSTALL) {
   process.exit(0);
 }
 
-const result = spawnSync(process.execPath, [cliPath, "plugin", "install"], {
+const result = spawnSync(process.execPath, [cliPath], {
   encoding: "utf8",
   env: process.env,
   stdio: "inherit",
@@ -23,7 +23,7 @@ if (result.status === 0) {
 }
 
 console.error("");
-console.error("GoalBuddy installed globally, but Codex plugin setup did not complete.");
-console.error("Run this after Codex is available:");
+console.error("GoalBuddy installed globally, but setup did not complete for every target.");
+console.error("Run this after Codex and Claude Code are available:");
 console.error("  goalbuddy");
 process.exit(0);

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "goalbuddy",
-  "version": "0.2.22",
-  "description": "Turn open-ended Codex goals into GoalBuddy Scout/Judge/Worker boards with visual board surfaces, receipts, and verification.",
+  "version": "0.3.1",
+  "description": "A /goal operating system for Codex and Claude Code: Scout/Judge/Worker boards with visual board surfaces, receipts, and verification.",
   "type": "module",
   "bin": {
     "goalbuddy": "internal/cli/goal-maker.mjs",
@@ -37,6 +37,10 @@
     "codex",
     "codex-skill",
     "openai-codex",
+    "claude-code",
+    "claude-code-plugin",
+    "claude-code-skill",
+    "anthropic",
     "goalbuddy",
     "goal",
     "task-board",

package/plugins/goalbuddy/.claude-plugin/plugin.json

@@ -0,0 +1,24 @@
+{
+  "name": "goalbuddy",
+  "version": "0.3.1",
+  "description": "Turn broad Claude Code work into verified GoalBuddy boards with Scout, Judge, Worker, visual boards, and receipts.",
+  "author": {
+    "name": "tolibear",
+    "email": "support@tolibear.com",
+    "url": "https://github.com/tolibear"
+  },
+  "homepage": "https://goalbuddy.dev",
+  "repository": "https://github.com/tolibear/goalbuddy",
+  "license": "MIT",
+  "keywords": [
+    "claude-code",
+    "claude-code-plugin",
+    "claude-code-skill",
+    "goalbuddy",
+    "goal",
+    "task-board",
+    "receipts",
+    "workflow",
+    "extensions"
+  ]
+}

package/plugins/goalbuddy/.codex-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "goalbuddy",
-  "version": "0.2.22",
-  "description": "Turn broad Codex work into verified GoalBuddy boards with Scout, Judge, Worker, visual boards, and receipts.",
+  "version": "0.3.1",
+  "description": "Turn broad Codex and Claude Code work into verified GoalBuddy boards with Scout, Judge, Worker, visual boards, and receipts.",
   "author": {
     "name": "tolibear",
     "email": "support@tolibear.com",
@@ -13,6 +13,7 @@
   "keywords": [
     "goalbuddy",
     "codex",
+    "claude-code",
     "skills",
     "goal",
     "task-board",
@@ -23,8 +24,8 @@
   "skills": "./skills/",
   "interface": {
     "displayName": "GoalBuddy",
-    "shortDescription": "Turn broad Codex work into verified Scout/Judge/Worker boards",
-    "longDescription": "GoalBuddy packages a structured Codex goal workflow for broad, long-running, or ambiguous engineering work. It creates durable goal charters, task boards, visual board surfaces, receipts, verification gates, extension handoffs, and compatibility guidance for teams moving from goal-maker.",
+    "shortDescription": "Turn broad Codex or Claude Code work into verified Scout/Judge/Worker boards",
+    "longDescription": "GoalBuddy packages a structured goal workflow for broad, long-running, or ambiguous engineering work in Codex or Claude Code. It creates durable goal charters, task boards, visual board surfaces, receipts, verification gates, extension handoffs, and compatibility guidance for teams moving from goal-maker.",
     "developerName": "tolibear",
     "category": "Coding",
     "capabilities": [

package/plugins/goalbuddy/README.md

@@ -1,11 +1,14 @@
-# GoalBuddy Codex Plugin
+# GoalBuddy Plugin (Codex + Claude Code)
 
-GoalBuddy packages the canonical `$goal-prep` skill as a Codex plugin so teams can install the reusable workflow as a plugin while keeping the npm CLI for local setup, doctor checks, and extension management.
+GoalBuddy packages the canonical `goal-prep` skill as a plugin so teams can install the reusable workflow in **Codex** and **Claude Code**, while keeping the npm CLI for local setup, doctor checks, and extension management.
 
 ## What It Contains
 
-- `.codex-plugin/plugin.json`: plugin metadata and Codex UI copy.
-- `skills/goalbuddy/`: the installable GoalBuddy skill payload.
+- `.codex-plugin/plugin.json`: Codex plugin manifest and Codex UI copy.
+- `.claude-plugin/plugin.json`: Claude Code plugin manifest.
+- `skills/goalbuddy/`: the installable GoalBuddy skill payload (shared by both platforms).
+- `agents/`: Claude Code subagent definitions (`goal-scout.md`, `goal-judge.md`, `goal-worker.md`).
+- `commands/goal-prep.md`: Claude Code slash command entry point.
 - `assets/goalbuddy-icon.svg`: lightweight plugin icon.
 
 ## Local Testing
@@ -18,25 +21,36 @@ npx goalbuddy doctor
 npx goalbuddy check-update
 ```
 
-## Native Codex Install
-
-Install and enable GoalBuddy:
+## Install Both Targets
 
 ```bash
 npx goalbuddy
 ```
 
-Restart Codex, then use `$goal-prep`. The plugin bundles the local live board and GitHub Projects visual board backends so Goal Prep can offer a board immediately.
+This installs and enables the native Codex plugin in `~/.codex/`, then installs the GoalBuddy skill, Scout/Judge/Worker subagents, and `/goal-prep` slash command into `~/.claude/`.
+
+## Install One Target
+
+```bash
+npx goalbuddy --target codex
+npx goalbuddy --target claude
+```
+
+This installs the GoalBuddy skill, the three Scout/Judge/Worker subagents, and the `/goal-prep` slash command into `~/.claude/`. Restart Claude Code, then run:
+
+```text
+/goal-prep
+```
 
 Or install the npm package globally:
 
 ```bash
 npm i -g goalbuddy
-goalbuddy
+goalbuddy                  # installs for Codex and Claude Code
+goalbuddy --target codex   # installs for Codex only
+goalbuddy --target claude  # installs for Claude Code only
 ```
 
-The marketplace manifest is included for Codex discovery, but current Codex CLI builds only register the marketplace with `codex plugin marketplace add`; the npm CLI also caches and enables the plugin.
-
 For local CLI testing before npm publish:
 
 ```bash
@@ -46,4 +60,4 @@ node internal/cli/goal-maker.mjs doctor
 
 ## Release Notes
 
-The plugin is prepared for the `tolibear/goalbuddy` repo and `goalbuddy` npm package. Keep `.codex-plugin/plugin.json` aligned with `package.json` before publishing a new package release.
+The plugin is prepared for the `tolibear/goalbuddy` repo and `goalbuddy` npm package. Keep `.codex-plugin/plugin.json` and `.claude-plugin/plugin.json` aligned with `package.json` before publishing a new package release.

package/plugins/goalbuddy/agents/goal-judge.md

@@ -0,0 +1,27 @@
+---
+name: goal-judge
+description: GoalBuddy Judge. High-thinking strategic reviewer for GoalBuddy escalation: ambiguity, risky scope, source/product conflicts, safety/API/live decisions, and tranche completion. Returns a compact Judge receipt for the PM to paste into state.yaml.
+tools: Read, Grep, Glob, Bash
+---
+
+You are Judge for GoalBuddy.
+
+Thinking level: high.
+Mode: strategic reviewer and escalation authority.
+
+Think as a skeptical staff engineer and project-management systems designer. You decide and constrain; you do not broadly implement.
+
+Use when source, tests, product behavior, API/live strategy, dirty scope, giant-file risk, safety/auth/money/persistence semantics, task priority, or completion readiness is ambiguous.
+
+Do not approve based on lots of docs or lots of tests. Require coherent receipts and current verification.
+
+Return a compact Judge receipt for the PM to paste into state.yaml:
+- result
+- decision
+- evidence
+- next_allowed_task when work may continue
+- blocked_tasks when work should not proceed
+- completion decision when auditing a tranche
+- required board updates
+
+Do not broadly implement, select the active task, or mark the goal complete yourself.

package/plugins/goalbuddy/agents/goal-scout.md

@@ -0,0 +1,24 @@
+---
+name: goal-scout
+description: GoalBuddy Scout. Read-only evidence mapper for one GoalBuddy task. Finds repo/source/spec evidence, verification commands, ambiguities, and candidate next tasks. Returns a compact Scout receipt for the PM to paste into state.yaml.
+tools: Read, Grep, Glob, Bash
+---
+
+You are Scout for GoalBuddy.
+
+Thinking level: medium.
+Mode: read-only evidence mapping.
+
+You are read-only. Do not edit files, stage files, run destructive commands, or claim implementation is complete.
+
+Given one active Scout task, map repo/source/spec evidence, verification commands, health signals, improvement candidates, target files, tests, and unresolved ambiguity.
+
+Return a compact Scout receipt for the PM to paste into state.yaml:
+- result
+- summary
+- evidence paths
+- note path if findings are too large for the task card
+- spawned_tasks when useful
+- ambiguity requiring Judge
+
+Do not select the active task or mark the goal complete.

package/plugins/goalbuddy/agents/goal-worker.md

@@ -0,0 +1,26 @@
+---
+name: goal-worker
+description: GoalBuddy Worker. Low-thinking bounded implementer for exactly one GoalBuddy Worker task with allowed files, verification commands, and stop conditions. Returns a compact Worker receipt for the PM to paste into state.yaml.
+tools: Read, Edit, Write, Grep, Glob, Bash
+---
+
+You are Worker for GoalBuddy.
+
+Thinking level: low.
+Mode: one bounded writer.
+
+Execute exactly one active Worker task. Do not broaden scope.
+
+You may edit only the task's allowed_files. You may update only explicitly named control files if the PM included them in scope. Do not decide product behavior, retained/excluded scope, API/live/deployment strategy, architecture direction, parity, or completion readiness.
+
+Stop immediately if required evidence is missing, files outside scope are needed, source/tests/product conflict, verification fails twice, or the diff exceeds the task budget.
+
+Return a compact Worker receipt for the PM to paste into state.yaml:
+- result
+- changed_files
+- commands run with pass/fail
+- summary
+- remaining_blockers
+- needs_judge when strategy or ambiguity remains
+
+Do not select the next active task or mark the goal complete.

package/plugins/goalbuddy/skills/goalbuddy/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: goal-prep
-description: Goal Prep for GoalBuddy. Use for broad, long-running, stalled, vague, detailed, planned, or unhealthy Codex work that needs a structured /goal intake, autonomous task discovery, role-tagged Scout/Judge/Worker delegation, one active task, durable receipts, and a PM-owned rolling board that maximizes the chance of a successful goal run.
+description: Goal Prep for GoalBuddy. Use for broad, long-running, stalled, vague, detailed, planned, or unhealthy Codex or Claude Code work that needs a structured /goal intake, autonomous task discovery, role-tagged Scout/Judge/Worker delegation, one active task, durable receipts, and a PM-owned rolling board that maximizes the chance of a successful goal run.
 ---
 
 # Goal Prep
 
-`$goal-prep` prepares a GoalBuddy board. It does not start `/goal` automatically, but the board and starter `/goal` command must be shaped so the next run continues into safe execution by default.
+`$goal-prep` (Codex) or `/goal-prep` (Claude Code) prepares a GoalBuddy board. It does not start `/goal` automatically, but the board and starter `/goal` command must be shaped so the next run continues into safe execution by default.
 
-GoalBuddy is for autonomous, long-running Codex work where the PM thread may need to discover the work, define tasks, sequence them, delegate them, execute them, verify them, and keep going without the human decomposing every step.
+GoalBuddy is for autonomous, long-running Codex or Claude Code work where the PM thread may need to discover the work, define tasks, sequence them, delegate them, execute them, verify them, and keep going without the human decomposing every step.
 
 The loop is:
 
@@ -81,11 +81,11 @@ Do you want to set up a visual board for this?
 
 Recommended options:
 
-1. Local live board in Codex (Recommended) - starts immediately, requires no credentials, and lets the user watch tasks populate.
+1. Local live board (Recommended) - starts immediately, requires no credentials, and lets the user watch tasks populate inside Codex or Claude Code.
 2. GitHub Projects - best when stakeholders need a shared external board and the user can approve GitHub credentials/project details.
 3. No visual board - best for quick or private goals where the file board is enough.
 
-If the user chooses the local live board, create the goal directory, `notes/`, and an initial minimal `state.yaml` as soon as the slug is known, then run `npx goalbuddy board docs/goals/<slug>` and open the printed local URL in the Codex in-app Browser. In short: start the local board before filling the task list so the board pops up right away and cards populate live as `state.yaml` changes. Keep the printed URL in the final prep response as a fallback, but do not make the URL the primary experience.
+If the user chooses the local live board, create the goal directory, `notes/`, and an initial minimal `state.yaml` as soon as the slug is known, then run `npx goalbuddy board docs/goals/<slug>` and open the printed local URL in the AI coding agent's in-app browser (the Codex in-app Browser, the Claude Code preview, or the user's regular browser). In short: start the local board before filling the task list so the board pops up right away and cards populate live as `state.yaml` changes. Keep the printed URL in the final prep response as a fallback, but do not make the URL the primary experience.
 
 If the user chooses GitHub Projects, ask for approval and the required project target before any live write. Create or sync the GitHub Project at the same early point as the local board: after the goal root and skeleton `state.yaml` exist, before the detailed task list is finished, then sync again as tasks populate. Run a dry-run sync first when possible. Missing GitHub credentials or project details should not block local board creation or goal prep; record the missing requirement in `visual_board.github_projects` and seed a PM setup task.
 
@@ -138,11 +138,11 @@ Minimum diagnostic ladder for vague, strategic, or improvement-oriented goals:
 2. Intent target: what kind of improvement or outcome matters most?
 3. Success proof: what evidence would convince the user this worked?
 4. Scope and non-goals: what should remain untouched or explicitly out of scope?
-5. Board handling: reuse an existing board, create a fresh board, or inspect first?
+5. Goal handling: reuse an existing goal, create a fresh goal, or inspect first?
 
 Ask these one at a time. Skip a step only when the user's words already answer it clearly. After the user answers one step, do not assume the remaining steps; ask the next unresolved material question.
 
-For "make GoalBuddy better", a good first question is which improvement target matters most: intake clarity, board/execution reliability, completion proof/eval coverage, or user experience during long-running goals. A good second question asks what proof would convince the user it improved. A good third question asks whether to reuse an existing board, create a fresh board, or inspect first.
+For "make GoalBuddy better", a good first question is which improvement target matters most: intake clarity, board/execution reliability, completion proof/eval coverage, or user experience during long-running goals. A good second question asks what proof would convince the user it improved. A good third question asks whether to reuse an existing goal, create a fresh goal, or inspect first.
 
 ## Direct `/goal` Entry
 
@@ -173,7 +173,7 @@ Do:
 - classify the goal as `specific`, `open_ended`, `existing_plan`, `recovery`, or `audit`;
 - create or repair `docs/goals/<slug>/`;
 - create `goal.md`, `state.yaml`, and `notes/`;
-- if requested, start the local visual board immediately and open it in the Codex in-app Browser before filling the task list;
+- if requested, start the local visual board immediately and open it in the AI coding agent's in-app browser (Codex in-app Browser, Claude Code preview, or the user's regular browser) before filling the task list;
 - seed a role-tagged task board that matches the input shape;
 - make the first active task safe;
 - verify Scout, Worker, and Judge agent availability or record an explicit truthful state;

package/plugins/goalbuddy/skills/goalbuddy/agents/README.md

@@ -1,17 +1,22 @@
 # GoalBuddy Agents
 
-This directory contains both skill metadata and bundled agent definitions.
+This directory contains skill metadata and bundled agent definitions for Codex and Claude Code.
+
+## Files
 
 - `openai.yaml` stays with the skill as metadata.
-- `goal_*.toml` files can be copied into `.codex/agents/` for project-scoped agents or `~/.codex/agents/` for personal agents.
+- `goal_scout.toml`, `goal_judge.toml`, `goal_worker.toml` — Codex agent configs. Copy into `.codex/agents/` for project-scoped agents or `~/.codex/agents/` for personal agents.
+- Claude Code agent markdown lives in `plugins/goalbuddy/agents/` (installed to `~/.claude/agents/` by `npx goalbuddy --target claude`).
+
+## Agent Matrix
 
-| Agent | File | Reasoning effort | Sandbox |
-|---|---|---:|---|
-| Scout | `goal_scout.toml` | medium | read-only |
-| Worker | `goal_worker.toml` | low | workspace-write |
-| Judge | `goal_judge.toml` | high | read-only |
+| Agent | Codex file | Claude Code file | Reasoning effort | Write scope |
+|---|---|---|---:|---|
+| Scout | `goal_scout.toml` | `goal-scout.md` | medium | read-only |
+| Worker | `goal_worker.toml` | `goal-worker.md` | low | workspace-write |
+| Judge | `goal_judge.toml` | `goal-judge.md` | high | read-only |
 
-Recommended config:
+## Recommended Codex Config
 
 ```toml
 [agents]
@@ -20,4 +25,6 @@ max_depth = 1
 job_max_runtime_seconds = 1800
 ```
 
+## Authority Boundary
+
 Only the main `/goal` PM loop may select the active task, mark tasks done, update board truth, or mark the goal complete.