maxsimcli 5.0.7 → 5.1.0

package/README.md

@@ -1,6 +1,6 @@
 # MAXSIM
 
-Your AI coding assistant forgets things between sessions. MAXSIM keeps it on track.
+Meta-prompting and project orchestration system for Claude Code.
 
 [![npm version](https://img.shields.io/npm/v/maxsimcli?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/maxsimcli)
 [![npm downloads](https://img.shields.io/npm/dm/maxsimcli?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/maxsimcli)
@@ -22,7 +22,7 @@ That is context rot. It gets worse the bigger your project grows.
 
 MAXSIM breaks your work into phases, plans each one separately, and runs every task in a fresh agent with only the context it needs. Your decisions, requirements, and project state live in a `.planning/` directory. Agents read from it and write back to it. Nothing gets lost between sessions.
 
-It does not call any LLM API directly. MAXSIM orchestrates Claude Code agents through markdown prompts and workflow files. No API keys, no extra costs beyond your existing Claude Code usage.
+It does not call any LLM API directly. MAXSIM orchestrates Claude Code agents through markdown prompts and workflow files. No API keys, no extra costs beyond your existing Claude Code usage. v6 is Claude Code only.
 
 You install it with one command. It lands in your project's `.claude/` directory and shows up as slash commands in Claude Code.
 
@@ -52,15 +52,15 @@ That is the core loop. Init, plan, execute, verify. Each phase is isolated, each
 
 ## What You Get
 
-MAXSIM ships 9 slash commands, 4 agents, 21 skills, and 23 workflows. Here is what that means in practice.
+MAXSIM ships 9 slash commands, 4 agents, 14 skills, and 20 workflows. Here is what that means in practice.
 
 **Spec-driven development.** All work flows through structured markdown files in `.planning/`. PROJECT.md, ROADMAP.md, STATE.md, REQUIREMENTS.md. The spec is the single source of truth. Agents read from it and update it as they work.
 
-**4 agents with clear roles.** Executor builds things. Planner creates plans. Researcher investigates the codebase. Verifier checks the results. Each one does one job.
+**4 generic agents with clear roles.** Executor builds things. Planner creates plans. Researcher investigates the codebase. Verifier checks the results. Each one does one job.
 
-**4 model profiles.** Pick `quality`, `balanced`, `budget`, or `tokenburner` to control which Claude model tier each agent uses. You can override individual agents too.
+**3 model profiles.** Pick `quality`, `balanced`, or `budget` to control which Claude model tier each agent uses. You can override individual agents too.
 
-**GitHub Issues as the source of truth.** Phases become tracking issues. Plans become sub-issues. A 4-column project board (To Do, In Progress, In Review, Done) mirrors your `.planning/` state.
+**GitHub Issues as the source of truth.** Phases become tracking issues. Plans become sub-issues. A 4-column project board (To Do, In Progress, In Review, Done) tracks execution progress.
 
 **Parallel execution with git worktrees.** Independent plans run concurrently in separate worktrees. MAXSIM groups them into dependency-ordered waves and runs each wave in parallel.
 
@@ -84,20 +84,10 @@ Run this from your project root. Everything goes into `.claude/`.
 
 | Flag | Alias | What it does |
 |------|-------|-------------|
-| `--local` | `-l` | Install to current project (default) |
-| `--uninstall` | `-u` | Remove all MAXSIM files |
-| `--config-dir <path>` | `-c` | Custom target directory |
-| `--force-statusline` | | Replace existing statusline config |
+| `--uninstall` | | Remove all MAXSIM files from `.claude/` |
+| `--quiet` | `-q` | Suppress output |
 | `--help` | `-h` | Show usage |
-| `--version` | | Print version |
-
-### Skill Management
-
-```bash
-npx maxsimcli skill-list                # Show installed skills
-npx maxsimcli skill-install <name>      # Add a skill
-npx maxsimcli skill-update [name]       # Update one or all
-```
+| `--version` | `-v` | Print version |
 
 ### What Lands in Your Project
 
@@ -105,11 +95,12 @@ The installer copies these files into `.claude/`:
 
 - 9 slash commands (`/maxsim:init`, `/maxsim:plan`, etc.)
 - 4 agent definitions (executor, planner, researcher, verifier)
-- 21 skills (TDD, debugging, code review, and more)
-- 23 workflow files
-- 14 reference documents, 2 rules files
-- 5 hooks (statusline, update checker, sounds)
+- 14 skills (TDD, debugging, code review, and more)
+- 20 workflow files
+- 15 reference documents, 2 rules files
+- 6 hooks (statusline, update checker, sounds, capture-learnings)
 - 1 tool binary (`maxsim-tools.cjs`)
+- `CLAUDE.md` in your project root
 
 ### Directory Layout
 
@@ -118,22 +109,20 @@ The installer copies these files into `.claude/`:
 ├── commands/maxsim/          # 9 slash commands
 ├── maxsim/
 │   ├── bin/maxsim-tools.cjs  # Tool binary
-│   ├── workflows/            # 23 workflows
+│   ├── workflows/            # 20 workflows
 │   ├── templates/            # Planning document templates
-│   ├── references/           # 14 reference docs
-│   ├── VERSION
-│   └── CHANGELOG.md
-├── agents/                   # 4 agents (maxsim-*.md)
-├── skills/                   # 21 skill directories
+│   ├── references/           # 15 reference docs
+│   └── hooks/                # 6 hook scripts (.cjs)
+├── agents/                   # 4 agents
+├── skills/                   # 14 skill directories
 ├── rules/                    # 2 rules files
-├── hooks/                    # 5 hook scripts (.js)
 ├── settings.json
-└── package.json
+└── CLAUDE.md                 # Generated project context
 ```
 
 ### Upgrading
 
-Run `npx maxsimcli@latest` again. The installer backs up your current install to `.claude/maxsim-backup/`, saves your local modifications to `.claude/maxsim-local-patches/`, preserves custom skills and agents, then updates everything.
+Run `npx maxsimcli@latest` again. The installer overwrites MAXSIM-managed files. Custom skills you have added to `.claude/skills/` and your own agents are not touched.
 
 ### Uninstall
 
@@ -149,15 +138,15 @@ Removes MAXSIM files from `.claude/`. Your own skills, agents, and Claude Code c
 
 | Command | What it does |
 |---------|-------------|
-| `/maxsim:init` | Set up a new project or onboard an existing codebase |
-| `/maxsim:plan <phase>` | Research, discuss, and create plans for a phase |
-| `/maxsim:execute <phase>` | Run plans for a phase (serial or parallel) |
-| `/maxsim:go <phase>` | Plan + execute in one step |
-| `/maxsim:quick <description>` | Run an ad-hoc task outside the phase system |
-| `/maxsim:progress` | Show project progress |
-| `/maxsim:debug` | Start a debug session |
-| `/maxsim:settings` | View and change configuration |
-| `/maxsim:help` | Show available commands |
+| `/maxsim:init` | Initialize MaxsimCLI in current project with GitHub integration |
+| `/maxsim:plan <phase>` | Plan a specific phase with discussion, research, and task breakdown |
+| `/maxsim:execute <phase>` | Execute all plans in a phase with parallel agents and auto-verification |
+| `/maxsim:go` | Auto-detect project state and execute the right action |
+| `/maxsim:quick <description>` | Quick task — create a GitHub Issue and execute in simplified flow |
+| `/maxsim:progress` | Show project status from GitHub Project Board with next-action recommendation |
+| `/maxsim:debug` | Systematic debugging with reproduce-hypothesize-isolate-verify-fix cycle |
+| `/maxsim:settings` | View and modify MaxsimCLI configuration |
+| `/maxsim:help` | Show available MaxsimCLI commands and usage |
 
 ## Core Workflow
 
@@ -165,7 +154,7 @@ MAXSIM organizes development into phases. Each phase moves through five stages.
 
 **1. Initialize** (`/maxsim:init`)
 
-Run once per project. Creates the `.planning/` directory with PROJECT.md, ROADMAP.md, STATE.md, REQUIREMENTS.md, and config.json. Optionally connects GitHub Issues for tracking.
+Run once per project. Creates the `.planning/` directory with PROJECT.md, ROADMAP.md, STATE.md, REQUIREMENTS.md, and config files. Optionally connects GitHub Issues and a Project Board for tracking.
 
 **2. Plan** (`/maxsim:plan <phase>`)
 
@@ -215,21 +204,18 @@ Phase numbers are flexible. Integer (`01`, `02`), letter suffixes for parallel t
 | Researcher | Investigates | Explores the codebase, gathers technical context, can use Brave Search |
 | Verifier | Checks results | Validates plan structure, artifacts, requirement evidence, commit integrity |
 
-Each agent is a markdown file at `.claude/agents/maxsim-{name}.md` with YAML frontmatter for tools, model tier, and preloaded skills.
-
-A 5th type, Debugger, exists in the model profile system for debug sessions but has no standalone agent file.
+Each agent is a markdown file at `.claude/agents/{name}.md` with YAML frontmatter for tools, model tier, and preloaded skills.
 
 ### Model Profiles
 
 Set `model_profile` in `.planning/config.json` to control which Claude model each agent uses:
 
-| Agent Type | `quality` | `balanced` (default) | `budget` | `tokenburner` |
-|------------|-----------|---------------------|----------|---------------|
-| executor | opus | sonnet | sonnet | opus |
-| planner | opus | opus | sonnet | opus |
-| researcher | opus | sonnet | haiku | opus |
-| verifier | sonnet | sonnet | haiku | opus |
-| debugger | sonnet | sonnet | haiku | opus |
+| Agent Type | `quality` | `balanced` (default) | `budget` |
+|------------|-----------|---------------------|----------|
+| planner | opus | opus | sonnet |
+| executor | opus | sonnet | sonnet |
+| researcher | opus | sonnet | haiku |
+| verifier | sonnet | sonnet | haiku |
 
 `opus` maps to `inherit`, meaning it uses your Claude Code session model. `sonnet` and `haiku` are passed directly to subagent invocations.
 
@@ -251,9 +237,7 @@ Override individual agents regardless of profile:
 
 ## GitHub Integration
 
-MAXSIM tracks phase and plan progress through GitHub Issues. Your `.planning/` files hold project-level documents (roadmap, state, config). Execution progress lives in GitHub.
-
-You need GitHub CLI (`gh`) installed and authenticated, plus a GitHub-hosted repository.
+MAXSIM tracks phase and plan progress through GitHub Issues. Your `.planning/` files hold project-level documents (roadmap, state, config). Execution progress lives in GitHub. GitHub CLI (`gh`) and a GitHub-hosted repository are required for this feature.
 
 ### Setup
 
@@ -267,7 +251,7 @@ Configured during `/maxsim:init`:
 
 Each phase gets a tracking issue. Each plan becomes a sub-issue linked to its phase. Plan content goes into structured comments. Completion data (commit SHA, files changed) gets posted to task issues. Progress is computed from open vs closed sub-issue counts.
 
-A local `.planning/github-issues.json` caches the mapping between phase numbers and issue numbers. It is a performance cache, the system rebuilds it from GitHub when needed.
+A local cache file maps phase numbers to GitHub issue numbers and is rebuilt from GitHub when needed.
 
 ### Tool Commands
 
@@ -291,24 +275,56 @@ Project config lives in `.planning/config.json`, created during `/maxsim:init`.
 
 | Setting | Type | Default | What it does |
 |---------|------|---------|-------------|
-| `model_profile` | `'quality' \| 'balanced' \| 'budget' \| 'tokenburner'` | `'balanced'` | Model tier for all agents |
+| `execution.modelProfile` | `'quality' \| 'balanced' \| 'budget'` | `'balanced'` | Model tier for all agents |
 | `model_overrides` | `Record<AgentType, ModelTier>` | | Per-agent model overrides |
-| `commit_docs` | `boolean` | `true` | Auto-commit `.planning/` changes |
-| `search_gitignored` | `boolean` | `false` | Include gitignored files in codebase mapping |
-| `branching_strategy` | `'none' \| 'phase' \| 'milestone'` | `'none'` | Git branching strategy |
-| `phase_branch_template` | `string` | `'maxsim/phase-{phase}-{slug}'` | Branch name template for phases |
-| `milestone_branch_template` | `string` | `'maxsim/{milestone}-{slug}'` | Branch name template for milestones |
+| `execution.parallelism.maxAgentsPerWave` | `number` | `3` | Cap on concurrent agents per wave |
+| `execution.parallelism.maxRetries` | `number` | `3` | Max retries per failed plan |
+| `execution.parallelism.competitionStrategy` | `'none' \| 'quick' \| 'standard' \| 'deep'` | `'standard'` | Parallel competition strategy |
+| `execution.verification.strictMode` | `boolean` | `true` | Enforce all verification gates |
+| `execution.verification.requireCodeReview` | `boolean` | `true` | Code review gate |
+| `execution.verification.autoResolveConflicts` | `boolean` | `true` | Auto-resolve merge conflicts |
+| `worktrees.basePath` | `string` | `'.maxsim-worktrees/'` | Worktree base directory |
+| `worktrees.autoCleanup` | `boolean` | `true` | Remove worktrees after completion |
+| `worktrees.branchPrefix` | `string` | `'maxsim/'` | Branch prefix for worktree branches |
+| `automation.autoCommitOnSuccess` | `boolean` | `true` | Auto-commit `.planning/` changes |
+| `automation.conventionalCommits` | `boolean` | `true` | Enforce conventional commit format |
+| `planning.commit_docs` | `boolean` | `true` | Commit planning artifacts to git |
+| `planning.search_gitignored` | `boolean` | `false` | Include gitignored files in searches |
+| `git.branching_strategy` | `'none' \| 'phase' \| 'milestone'` | `'none'` | Git branching strategy |
+| `git.phase_branch_template` | `string` | `'maxsim/phase-{phase}-{slug}'` | Branch name template for phases |
+| `git.milestone_branch_template` | `string` | `'maxsim/{milestone}-{slug}'` | Branch name template for milestones |
 | `workflow.research` | `boolean` | `true` | Run research before planning |
 | `workflow.plan_checker` | `boolean` | `true` | Run plan checker agent |
 | `workflow.verifier` | `boolean` | `true` | Run verifier after execution |
-| `parallelization` | `boolean` | `true` | Allow parallel plan execution |
-| `worktree_mode` | `'auto' \| 'always' \| 'never'` | `'auto'` | When to use git worktrees |
-| `max_parallel_agents` | `number` | `10` | Cap on concurrent agents |
-| `brave_search` | `boolean` | `false` | Let researcher agents use Brave Search |
-| `review.spec_review` | `boolean` | `true` | Spec review gate |
-| `review.code_review` | `boolean` | `true` | Code review gate |
-| `review.simplify_review` | `boolean` | `true` | Simplification review gate |
-| `review.retry_limit` | `number` | `3` | Max retries per review gate |
+
+### Config Example
+
+```json
+{
+  "execution": {
+    "modelProfile": "balanced",
+    "parallelism": {
+      "maxAgentsPerWave": 3,
+      "maxRetries": 3,
+      "competitionStrategy": "standard"
+    },
+    "verification": {
+      "strictMode": true,
+      "requireCodeReview": true,
+      "autoResolveConflicts": true
+    }
+  },
+  "worktrees": {
+    "basePath": ".maxsim-worktrees/",
+    "autoCleanup": true,
+    "branchPrefix": "maxsim/"
+  },
+  "automation": {
+    "autoCommitOnSuccess": true,
+    "conventionalCommits": true
+  }
+}
+```
 
 ### User-Level Defaults
 
@@ -330,44 +346,31 @@ Put global defaults in `~/.maxsim/defaults.json`. These merge with hardcoded def
 
 Skills are reusable prompt modules that agents load on demand. Each skill is a `SKILL.md` file with YAML frontmatter and a markdown body.
 
-### Built-in Skills (21)
+### Built-in Skills (14)
 
 | Skill | Category | What it does |
 |-------|----------|-------------|
-| `tdd` | Task | Test-driven development, Red-Green-Refactor cycle |
+| `tdd` | Task | Test-driven development, Red-Green-Refactor cycle with atomic commits |
 | `systematic-debugging` | Methodology | Root-cause analysis: reproduce, hypothesize, isolate, verify, fix |
-| `verification-before-completion` | Methodology | Requires evidence before marking work as done |
-| `maxsim-simplify` | Task | Finds duplication, dead code, and unnecessary complexity |
+| `verification` | Methodology | Evidence-based verification with quality gates and anti-rationalization enforcement |
+| `maxsim-simplify` | Task | Reviews changed code for reuse opportunities and unnecessary complexity |
 | `code-review` | Task | Checks security, interfaces, error handling, test coverage |
-| `memory-management` | Task | Persists patterns and decisions to project memory |
-| `using-maxsim` | Task | Routes work through the spec-driven workflow |
-| `brainstorming` | Task | Explores multiple approaches before picking a design |
-| `roadmap-writing` | Task | Creates structured roadmaps with phased planning |
-| `sdd` | Task | Spec-driven development, sequential tasks with fresh context |
+| `project-memory` | Task | GitHub-native persistence for learnings, decisions, and patterns |
+| `using-maxsim` | Task | Routes work through MaxsimCLI commands based on project state |
+| `brainstorming` | Task | Explores multiple approaches with structured comparison before committing |
+| `roadmap-writing` | Task | Creates phased roadmaps with dependency graphs and GitHub Milestone structure |
 | `maxsim-batch` | Task | Decomposes tasks for parallel worktree execution |
-| `agent-system-map` | Reference | Overview of the agent system |
 | `commit-conventions` | Convention | Conventional commit format and version trigger rules |
-| `evidence-collection` | Methodology | Structured evidence gathering for verification |
-| `github-artifact-protocol` | Reference | How to read and write GitHub Issue artifacts |
-| `github-tools-guide` | Reference | Guide to the GitHub CLI commands |
+| `github-operations` | Reference | Unified GitHub interaction: artifacts, comments, CLI, issue lifecycle |
 | `handoff-contract` | Protocol | Agent-to-agent handoff protocol |
-| `input-validation` | Protocol | Input validation rules for agents |
-| `research-methodology` | Methodology | Structured research approach for agents |
-| `tool-priority-guide` | Reference | Which tools to prefer for which tasks |
-| `verification-gates` | Protocol | Review gate protocol with pass/fail criteria |
+| `research` | Methodology | Systematic investigation using parallel agents and source hierarchy |
 
 ### Skill Types
 
-Protocol skills load automatically (handoff-contract, verification-gates, input-validation). Methodology skills guide how agents think. Task skills are user-invocable workflows like TDD or code review. Reference skills provide static information.
+Protocol skills load automatically (handoff-contract). Methodology skills guide how agents think. Task skills are user-invocable workflows like TDD or code review. Reference skills provide static information.
 
 ### Managing Skills
 
-```bash
-npx maxsimcli skill-list              # Show installed skills
-npx maxsimcli skill-install <name>    # Add a skill
-npx maxsimcli skill-update [name]     # Update one or all
-```
-
 Built-in skills update when you upgrade MAXSIM. Custom skills you place in `.claude/skills/` are preserved.
 
 ---
@@ -382,9 +385,7 @@ Each parallel plan gets a worktree at `.maxsim-worktrees/{planId}/` on its own b
 
 ### When It Activates
 
-In `auto` mode (default), parallel execution kicks in when one wave has more than 2 plans and `parallelization` is `true` in config. Set `worktree_mode` to `always` or `never` for manual control. `max_parallel_agents` caps concurrent agents at 10 by default.
-
-You need `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` set in your environment and a git repository.
+Parallel execution kicks in when a wave has at least `parallelization.min_plans_for_parallel` plans (default 2). `execution.parallelism.maxAgentsPerWave` caps concurrent agents per wave (default 3). `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` is set automatically in `settings.json` during installation.
 
 Before running in parallel, MAXSIM checks that plans do not modify the same files. If there is a conflict, it falls back to sequential mode.
 
@@ -392,14 +393,15 @@ Before running in parallel, MAXSIM checks that plans do not modify the same file
 
 ## Hooks
 
-MAXSIM installs 5 Claude Code hooks:
+MAXSIM installs 6 Claude Code hooks:
 
 | Hook | Event | What it does |
 |------|-------|-------------|
 | `maxsim-statusline` | `statusLine` | Shows model tier, phase number, board column, and milestone progress |
 | `maxsim-check-update` | `SessionStart` | Checks npm for new MAXSIM versions in the background |
-| `maxsim-notification-sound` | `PostToolUse` | Plays a sound when Claude asks you a question |
+| `maxsim-notification-sound` | `Notification` | Plays a sound when Claude asks you a question |
 | `maxsim-stop-sound` | `Stop` | Plays a sound when Claude finishes |
+| `maxsim-capture-learnings` | `Stop` | Appends a dated learning entry to `.claude/agent-memory/` from the last 5 commits |
 | `maxsim-sync-reminder` | `PostToolUse` | No-op stub, kept for structural reasons |
 
 ### Statusline

package/dist/assets/CHANGELOG.md

@@ -1,3 +1,10 @@
+## [5.0.7](https://github.com/maystudios/maxsimcli/compare/v5.0.6...v5.0.7) (2026-03-13)
+
+
+### Bug Fixes
+
+* **website:** unify header, remove gradient/twitter, add drift detection tile ([67d115d](https://github.com/maystudios/maxsimcli/commit/67d115d99e2d47855efaf31005dab6219dd057e4))
+
 ## [5.0.6](https://github.com/maystudios/maxsimcli/compare/v5.0.5...v5.0.6) (2026-03-12)
 
 

package/dist/assets/hooks/maxsim-capture-learnings.cjs

@@ -0,0 +1,128 @@
+//#region \0rolldown/runtime.js
+var __create = Object.create;
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __getProtoOf = Object.getPrototypeOf;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __copyProps = (to, from, except, desc) => {
+	if (from && typeof from === "object" || typeof from === "function") {
+		for (var keys = __getOwnPropNames(from), i = 0, n = keys.length, key; i < n; i++) {
+			key = keys[i];
+			if (!__hasOwnProp.call(to, key) && key !== except) {
+				__defProp(to, key, {
+					get: ((k) => from[k]).bind(null, key),
+					enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable
+				});
+			}
+		}
+	}
+	return to;
+};
+var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", {
+	value: mod,
+	enumerable: true
+}) : target, mod));
+
+//#endregion
+let node_fs = require("node:fs");
+node_fs = __toESM(node_fs);
+let node_path = require("node:path");
+node_path = __toESM(node_path);
+let node_child_process = require("node:child_process");
+require("node:os");
+
+//#region src/hooks/shared.ts
+/** Shared utilities for MAXSIM hooks. */
+function readStdinJson(callback) {
+	let input = "";
+	process.stdin.setEncoding("utf8");
+	process.stdin.on("data", (chunk) => {
+		input += chunk;
+	});
+	process.stdin.on("end", () => {
+		try {
+			callback(JSON.parse(input));
+		} catch {
+			process.exit(0);
+		}
+	});
+}
+const CLAUDE_DIR = ".claude";
+
+//#endregion
+//#region src/hooks/maxsim-capture-learnings.ts
+/**
+* Stop hook — capture session learnings into agent memory.
+*
+* Behaviour:
+*  - Reads the Stop event JSON from stdin (includes cwd, session_id).
+*  - Checks if a MaxsimCLI project exists in cwd (.claude/maxsim/config.json).
+*  - If yes: reads the last 5 git commits to summarise what was done.
+*  - Appends a dated learning entry to .claude/agent-memory/maxsim-learner/MEMORY.md.
+*  - Creates the directory structure if it does not exist.
+*  - Always exits 0 — never blocks the user.
+*/
+/** Returns true when .claude/maxsim/config.json exists in the given directory. */
+function isMaxsimProject(projectDir) {
+	try {
+		return node_fs.existsSync(node_path.join(projectDir, CLAUDE_DIR, "maxsim", "config.json"));
+	} catch {
+		return false;
+	}
+}
+/** Reads the last N git commits as oneline strings. Returns empty array on failure. */
+function recentCommits(projectDir, n = 5) {
+	try {
+		const result = (0, node_child_process.spawnSync)("git", [
+			"log",
+			`--oneline`,
+			`-${n}`
+		], {
+			cwd: projectDir,
+			encoding: "utf8",
+			timeout: 4e3,
+			stdio: [
+				"ignore",
+				"pipe",
+				"ignore"
+			],
+			windowsHide: true
+		});
+		if (result.status !== 0) return [];
+		return (result.stdout ?? "").split("\n").map((l) => l.trim()).filter(Boolean);
+	} catch {
+		return [];
+	}
+}
+/** Formats today's date as YYYY-MM-DD. */
+function today() {
+	return (/* @__PURE__ */ new Date()).toISOString().slice(0, 10);
+}
+/** Appends a learning entry to the MEMORY.md file, creating dirs as needed. */
+function appendLearning(memoryPath, sessionId, commits) {
+	const dir = node_path.dirname(memoryPath);
+	node_fs.mkdirSync(dir, { recursive: true });
+	const sessionLabel = sessionId ? ` (${sessionId.slice(0, 8)})` : "";
+	const commitLines = commits.length > 0 ? commits.map((c) => `- commit: ${c}`).join("\n") : "- no commits recorded this session";
+	const entry = [
+		`## Session ${today()}${sessionLabel}`,
+		`- ${commits.length} commit(s) made this session`,
+		commitLines,
+		""
+	].join("\n");
+	node_fs.appendFileSync(memoryPath, `\n${entry}`, "utf8");
+}
+readStdinJson((input) => {
+	try {
+		const projectDir = input.cwd ?? process.cwd();
+		if (!isMaxsimProject(projectDir)) process.exit(0);
+		const memoryPath = node_path.join(projectDir, CLAUDE_DIR, "agent-memory", "maxsim-learner", "MEMORY.md");
+		const commits = recentCommits(projectDir, 5);
+		appendLearning(memoryPath, input.session_id, commits);
+	} catch {}
+	process.exit(0);
+});
+
+//#endregion
+//# sourceMappingURL=maxsim-capture-learnings.cjs.map

package/dist/assets/hooks/maxsim-capture-learnings.cjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"maxsim-capture-learnings.cjs","names":["fs","path"],"sources":["../../../src/hooks/shared.ts","../../../src/hooks/maxsim-capture-learnings.ts"],"sourcesContent":["/** Shared utilities for MAXSIM hooks. */\n\nimport { spawnSync } from 'node:child_process';\nimport * as os from 'node:os';\n\nexport function readStdinJson<T>(callback: (data: T) => void): void {\n  let input = '';\n  process.stdin.setEncoding('utf8');\n  process.stdin.on('data', (chunk: string) => {\n    input += chunk;\n  });\n  process.stdin.on('end', () => {\n    try {\n      const data = JSON.parse(input) as T;\n      callback(data);\n    } catch {\n      process.exit(0);\n    }\n  });\n}\n\nexport const CLAUDE_DIR = '.claude';\n\n/** Returns true when running on Windows. */\nexport function isWindows(): boolean {\n  return os.platform() === 'win32';\n}\n\n/** Returns true when running on macOS. */\nexport function isMac(): boolean {\n  return os.platform() === 'darwin';\n}\n\n/**\n * Play a system sound file cross-platform.\n * Never throws — sound failure is always silently swallowed.\n *\n * @param soundFile Absolute path to a WAV/MP3/etc. file, or a named system\n *                  sound token recognised by the platform helper (e.g. the\n *                  Windows-only SystemAsterisk token).\n */\nexport function playSound(soundFile: string): void {\n  try {\n    if (isWindows()) {\n      // PowerShell's SoundPlayer works with WAV files synchronously.\n      // For named system sounds (no extension) fall back to rundll32.\n      const isWav = soundFile.toLowerCase().endsWith('.wav');\n      if (isWav) {\n        spawnSync(\n          'powershell',\n          [\n            '-NoProfile',\n            '-NonInteractive',\n            '-Command',\n            `(New-Object System.Media.SoundPlayer '${soundFile.replace(/'/g, \"''\")}').PlaySync()`,\n          ],\n          { stdio: 'ignore' },\n        );\n      } else {\n        // Named system sound token (e.g. \"SystemAsterisk\") or unsupported format —\n        // use the rundll32 winsound bridge.\n        spawnSync(\n          'rundll32',\n          ['user32.dll,MessageBeep'],\n          { stdio: 'ignore' },\n        );\n      }\n    } else if (isMac()) {\n      spawnSync('afplay', [soundFile], { stdio: 'ignore' });\n    } else {\n      // Linux: try paplay (PulseAudio) then aplay (ALSA)\n      const paplay = spawnSync('paplay', [soundFile], { stdio: 'ignore' });\n      if (paplay.status !== 0) {\n        spawnSync('aplay', [soundFile], { stdio: 'ignore' });\n      }\n    }\n  } catch {\n    // Never crash on sound failure\n  }\n}\n","/**\n * Stop hook — capture session learnings into agent memory.\n *\n * Behaviour:\n *  - Reads the Stop event JSON from stdin (includes cwd, session_id).\n *  - Checks if a MaxsimCLI project exists in cwd (.claude/maxsim/config.json).\n *  - If yes: reads the last 5 git commits to summarise what was done.\n *  - Appends a dated learning entry to .claude/agent-memory/maxsim-learner/MEMORY.md.\n *  - Creates the directory structure if it does not exist.\n *  - Always exits 0 — never blocks the user.\n */\n\nimport * as fs from 'node:fs';\nimport * as path from 'node:path';\nimport { spawnSync } from 'node:child_process';\nimport { readStdinJson, CLAUDE_DIR } from './shared.js';\n\ninterface StopInput {\n  cwd?: string;\n  session_id?: string;\n  stop_reason?: string;\n  [key: string]: unknown;\n}\n\n/** Returns true when .claude/maxsim/config.json exists in the given directory. */\nfunction isMaxsimProject(projectDir: string): boolean {\n  try {\n    return fs.existsSync(path.join(projectDir, CLAUDE_DIR, 'maxsim', 'config.json'));\n  } catch {\n    return false;\n  }\n}\n\n/** Reads the last N git commits as oneline strings. Returns empty array on failure. */\nfunction recentCommits(projectDir: string, n = 5): string[] {\n  try {\n    const result = spawnSync(\n      'git',\n      ['log', `--oneline`, `-${n}`],\n      {\n        cwd: projectDir,\n        encoding: 'utf8',\n        timeout: 4000,\n        stdio: ['ignore', 'pipe', 'ignore'],\n        windowsHide: true,\n      },\n    );\n    if (result.status !== 0) return [];\n    return (result.stdout ?? '')\n      .split('\\n')\n      .map((l) => l.trim())\n      .filter(Boolean);\n  } catch {\n    return [];\n  }\n}\n\n/** Formats today's date as YYYY-MM-DD. */\nfunction today(): string {\n  return new Date().toISOString().slice(0, 10);\n}\n\n/** Appends a learning entry to the MEMORY.md file, creating dirs as needed. */\nfunction appendLearning(memoryPath: string, sessionId: string | undefined, commits: string[]): void {\n  const dir = path.dirname(memoryPath);\n  fs.mkdirSync(dir, { recursive: true });\n\n  const sessionLabel = sessionId ? ` (${sessionId.slice(0, 8)})` : '';\n  const commitLines =\n    commits.length > 0\n      ? commits.map((c) => `- commit: ${c}`).join('\\n')\n      : '- no commits recorded this session';\n\n  const entry = [\n    `## Session ${today()}${sessionLabel}`,\n    `- ${commits.length} commit(s) made this session`,\n    commitLines,\n    '',\n  ].join('\\n');\n\n  fs.appendFileSync(memoryPath, `\\n${entry}`, 'utf8');\n}\n\nreadStdinJson<StopInput>((input) => {\n  try {\n    const projectDir = input.cwd ?? process.cwd();\n\n    if (!isMaxsimProject(projectDir)) {\n      process.exit(0);\n    }\n\n    const memoryPath = path.join(\n      projectDir,\n      CLAUDE_DIR,\n      'agent-memory',\n      'maxsim-learner',\n      'MEMORY.md',\n    );\n\n    const commits = recentCommits(projectDir, 5);\n    appendLearning(memoryPath, input.session_id, commits);\n  } catch {\n    // Never crash — always let the Stop event complete cleanly\n  }\n\n  process.exit(0);\n});\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAKA,SAAgB,cAAiB,UAAmC;CAClE,IAAI,QAAQ;AACZ,SAAQ,MAAM,YAAY,OAAO;AACjC,SAAQ,MAAM,GAAG,SAAS,UAAkB;AAC1C,WAAS;GACT;AACF,SAAQ,MAAM,GAAG,aAAa;AAC5B,MAAI;AAEF,YADa,KAAK,MAAM,MAAM,CAChB;UACR;AACN,WAAQ,KAAK,EAAE;;GAEjB;;AAGJ,MAAa,aAAa;;;;;;;;;;;;;;;;ACI1B,SAAS,gBAAgB,YAA6B;AACpD,KAAI;AACF,SAAOA,QAAG,WAAWC,UAAK,KAAK,YAAY,YAAY,UAAU,cAAc,CAAC;SAC1E;AACN,SAAO;;;;AAKX,SAAS,cAAc,YAAoB,IAAI,GAAa;AAC1D,KAAI;EACF,MAAM,2CACJ,OACA;GAAC;GAAO;GAAa,IAAI;GAAI,EAC7B;GACE,KAAK;GACL,UAAU;GACV,SAAS;GACT,OAAO;IAAC;IAAU;IAAQ;IAAS;GACnC,aAAa;GACd,CACF;AACD,MAAI,OAAO,WAAW,EAAG,QAAO,EAAE;AAClC,UAAQ,OAAO,UAAU,IACtB,MAAM,KAAK,CACX,KAAK,MAAM,EAAE,MAAM,CAAC,CACpB,OAAO,QAAQ;SACZ;AACN,SAAO,EAAE;;;;AAKb,SAAS,QAAgB;AACvB,yBAAO,IAAI,MAAM,EAAC,aAAa,CAAC,MAAM,GAAG,GAAG;;;AAI9C,SAAS,eAAe,YAAoB,WAA+B,SAAyB;CAClG,MAAM,MAAMA,UAAK,QAAQ,WAAW;AACpC,SAAG,UAAU,KAAK,EAAE,WAAW,MAAM,CAAC;CAEtC,MAAM,eAAe,YAAY,KAAK,UAAU,MAAM,GAAG,EAAE,CAAC,KAAK;CACjE,MAAM,cACJ,QAAQ,SAAS,IACb,QAAQ,KAAK,MAAM,aAAa,IAAI,CAAC,KAAK,KAAK,GAC/C;CAEN,MAAM,QAAQ;EACZ,cAAc,OAAO,GAAG;EACxB,KAAK,QAAQ,OAAO;EACpB;EACA;EACD,CAAC,KAAK,KAAK;AAEZ,SAAG,eAAe,YAAY,KAAK,SAAS,OAAO;;AAGrD,eAA0B,UAAU;AAClC,KAAI;EACF,MAAM,aAAa,MAAM,OAAO,QAAQ,KAAK;AAE7C,MAAI,CAAC,gBAAgB,WAAW,CAC9B,SAAQ,KAAK,EAAE;EAGjB,MAAM,aAAaA,UAAK,KACtB,YACA,YACA,gBACA,kBACA,YACD;EAED,MAAM,UAAU,cAAc,YAAY,EAAE;AAC5C,iBAAe,YAAY,MAAM,YAAY,QAAQ;SAC/C;AAIR,SAAQ,KAAK,EAAE;EACf"}