awesome-slash 3.9.0 → 4.0.0

package/.agnix.toml

@@ -0,0 +1,42 @@
+severity = "Warning"
+exclude = [
+    "node_modules/**",
+    ".git/**",
+    "target/**",
+    # Research/reference docs - external content, not our code
+    "agent-docs/**",
+    # Meta skills - reference/example content
+    "meta/**",
+    # Lib copies in plugins (source is lib/, avoid duplicate warnings)
+    "plugins/*/lib/**",
+]
+target = "ClaudeCode"
+tools = []
+
+[rules]
+skills = true
+hooks = true
+agents = true
+memory = true
+plugins = true
+xml = true
+mcp = true
+imports = true
+cross_platform = false  # Intentional - we document all 3 platform paths
+agents_md = true
+copilot = false  # Not targeting Copilot
+cursor = false   # Not targeting Cursor
+prompt_engineering = true
+generic_instructions = true
+frontmatter_validation = true
+xml_balance = true
+import_references = true
+disabled_rules = [
+    "hardcoded-claude-path",   # Intentional - we document platform paths
+    "hardcoded-opencode-path", # Intentional - we document platform paths
+    "windows-path-separator",  # False positives on regex escape sequences (\n, \s, \d)
+]
+
+[tool_versions]
+
+[spec_revisions]

package/.claude-plugin/marketplace.json

@@ -1,7 +1,7 @@
 {
   "name": "awesome-slash",
-  "description": "9 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, and perf investigations",
-  "version": "3.9.0",
+  "description": "10 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, perf investigations, and topic research",
+  "version": "4.0.0",
   "owner": {
     "name": "Avi Fenesh",
     "url": "https://github.com/avifenesh"
@@ -26,64 +26,71 @@
       "name": "next-task",
       "source": "./plugins/next-task",
       "description": "Master workflow orchestrator: autonomous workflow with model optimization (opus/sonnet/haiku), two-file state management, workflow enforcement gates, 14 specialist agents",
-      "version": "3.9.0",
+      "version": "4.0.0",
       "category": "productivity"
     },
     {
       "name": "ship",
       "source": "./plugins/ship",
       "description": "Complete PR workflow: commit to production, skips review when called from next-task, removes task from registry on cleanup, automatic rollback",
-      "version": "3.9.0",
+      "version": "4.0.0",
       "category": "deployment"
     },
     {
       "name": "deslop",
       "source": "./plugins/deslop",
       "description": "3-phase AI slop detection: regex patterns (HIGH), multi-pass analyzers (MEDIUM), CLI tools (LOW)",
-      "version": "3.9.0",
+      "version": "4.0.0",
       "category": "development"
     },
     {
       "name": "audit-project",
       "source": "./plugins/audit-project",
       "description": "Multi-agent iterative code review until zero issues remain",
-      "version": "3.9.0",
+      "version": "4.0.0",
       "category": "development"
     },
     {
       "name": "drift-detect",
       "source": "./plugins/drift-detect",
       "description": "Deep repository analysis to realign project plans with code reality - detects drift, gaps, and creates prioritized reconstruction plans",
-      "version": "3.9.0",
+      "version": "4.0.0",
       "category": "productivity"
     },
     {
       "name": "enhance",
       "source": "./plugins/enhance",
       "description": "Master enhancement orchestrator: parallel analyzer execution for plugins, agents, docs, CLAUDE.md, and prompts with unified reporting",
-      "version": "3.9.0",
+      "version": "4.0.0",
       "category": "development"
     },
     {
       "name": "sync-docs",
       "source": "./plugins/sync-docs",
       "description": "Standalone documentation sync: find outdated refs, update CHANGELOG, flag stale examples based on code changes",
-      "version": "3.9.0",
+      "version": "4.0.0",
       "category": "development"
     },
     {
       "name": "repo-map",
       "source": "./plugins/repo-map",
       "description": "AST-based repository map generation using ast-grep with incremental updates for faster drift analysis",
-      "version": "3.9.0",
+      "version": "4.0.0",
       "category": "development"
     },
     {
       "name": "perf",
       "source": "./plugins/perf",
       "description": "Rigorous performance investigation workflow with baselines, profiling, hypotheses, and evidence-backed decisions",
-      "version": "3.9.0",
+      "version": "4.0.0",
       "category": "development"
+    },
+    {
+      "name": "learn",
+      "source": "./plugins/learn",
+      "description": "Research topics online and create comprehensive learning guides with RAG-optimized indexes",
+      "version": "4.0.0",
+      "category": "productivity"
     }
   ]
 }

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "awesome-slash",
-  "version": "3.9.0",
+  "version": "4.0.0",
   "description": "Professional-grade slash commands for Claude Code with cross-platform support",
   "keywords": [
     "workflow",

package/AGENTS.md

@@ -7,13 +7,13 @@
 <critical-rules>
 ## Critical Rules (Priority Order)
 
-1. **Production project** - Real users depend on this. Test thoroughly, don't break things.
+1. **Production project** - Real users depend on this. Test thoroughly and verify all edge cases before committing.
    *WHY: Breaking changes affect all plugin users immediately.*
 
 2. **Plugin for OTHER projects** - Optimize for plugin users, not internal dev convenience.
    *WHY: Every decision should improve the experience for developers using this in their repos.*
 
-3. **No summary files** - No `*_AUDIT.md`, `*_SUMMARY.md`, `*_COMPLETION.md`. Use CHANGELOG.md.
+3. **Use CHANGELOG.md for completion tracking** - MUST use CHANGELOG.md for release notes. NEVER create `*_AUDIT.md`, `*_SUMMARY.md`, `*_COMPLETION.md` files.
    *WHY: Summary files clutter repos and add no value. Report completion verbally.*
 
 4. **Unless** it is a very small change of max few lines, or an urgent hotfix, **MUST create PRs for all changes** - No direct pushes to main.
@@ -27,6 +27,7 @@
    - Release → `checklists/release.md`
    - New command → `checklists/new-command.md`
    - New agent → `checklists/new-agent.md`
+   - New skill → `checklists/new-skill.md`
    - New lib module → `checklists/new-lib-module.md`
    - OpenCode plugin update → `checklists/update-opencode-plugin.md`
    - Repo map changes → `checklists/repo-map.md`
@@ -41,9 +42,8 @@
    - Don't mark complete until ALL checklist items are done
    *WHY: Checklists exist because we kept missing things. They are the definition of "done".*
 
-8. **No emojis or ASCII art** - No emojis or decorative ASCII boxes in any files.
-   - Save tokens - conciseness and clarity over decorations.
-   - Use plain text: `[OK]`, `[ERROR]`, `[WARN]`, `[CRITICAL]`
+8. **Use plain text markers** - MUST use `[OK]`, `[ERROR]`, `[WARN]`, `[CRITICAL]` for status. NEVER use emojis or ASCII art boxes.
+   - Save tokens - conciseness and clarity over decorations
    - Use markdown formatting instead of decorative borders
    *WHY: Emojis and ASCII art waste tokens. AI models parse plain text better.*
 
@@ -52,79 +52,38 @@
    - Single quotes unreliable - use double quotes with escaped inner quotes
    *WHY: Windows shell interprets $ and ! differently. These cause silent failures.*
 
-10. **NEVER use --no-verify** - Never skip git hooks with `--no-verify` or `ENHANCE_CONFIRMED=1`.
-   - If pre-push hook blocks, fix the issue it reports
-   - Hooks exist to catch problems before they reach the repo
-   *WHY: Skipping hooks defeats their purpose. Fix the root cause instead.*
+10. **Always run git hooks** - Run all pre-commit and pre-push hooks. If a hook blocks, fix the reported issue.
+   - Hooks catch problems before they reach the repo
+   - Fix the root cause, then retry
+   *WHY: Hooks are safety nets. Bypassing them defeats their purpose.*
 </critical-rules>
 
 <architecture>
 ## Architecture
 
 ```
-lib/                        # Shared library (canonical source)
-├── config/                 # Configuration utilities
-├── cross-platform/         # Platform detection, MCP helpers
-├── enhance/                # Enhancement analyzers and patterns
-├── patterns/               # Slop detection pipeline
-├── perf/                   # Performance investigation tools
-├── platform/               # Platform detection, state directory
-├── repo-map/               # AST-based repo mapping
-├── schemas/                # JSON schema validation
-├── sources/                # Task source handlers
-├── state/                  # Workflow state management
-├── utils/                  # Utilities (cache, shell-escape)
-└── index.js                # Main exports
-
-plugins/                    # 9 plugins, 39 agents (29 file-based + 10 role-based), 24 skills
-├── next-task/              # Master workflow (10 agents, 3 skills)
-├── enhance/                # Enhancement analyzers (9 agents, 9 skills)
-├── ship/                   # PR workflow (4 commands)
-├── perf/                   # Performance investigation (6 agents, 8 skills)
-├── audit-project/          # Multi-agent review (10 role-based agents, 3 commands)
-├── deslop/                 # AI slop cleanup (1 agent, 1 skill)
-├── drift-detect/           # Plan drift detection (1 agent, 1 skill)
-├── repo-map/               # AST repo mapping (1 agent, 1 skill)
-└── sync-docs/              # Documentation sync (1 agent, 1 skill)
-
-adapters/                   # Platform-specific adapters
-├── opencode-plugin/        # Native OpenCode plugin
-├── opencode/               # OpenCode install script
-└── codex/                  # Codex install script
-
-bin/cli.js                  # npm CLI installer
-checklists/                 # Action checklists (8 files)
-agent-docs/                 # Knowledge base
-docs/                       # User documentation
+lib/          → Shared library (canonical source)
+plugins/      → 9 plugins, 39 agents (29 file-based + 10 role-based), 25 skills
+adapters/     → Platform adapters (opencode-plugin/, opencode/, codex/)
+checklists/   → Action checklists (9 files)
+bin/cli.js    → npm CLI installer
 ```
 
-### Agent/Skill Pattern
-
-```
-Command (orchestration) → Agent (thin wrapper) → Skill (implementation)
-```
-
-- **Commands**: Orchestration, argument parsing, phase coordination
-- **Agents**: Invoke skills, handle output, manage state
-- **Skills**: Reusable implementation, patterns, detection logic, auto-fixes
+| Plugin | Agents | Skills | Purpose |
+|--------|--------|--------|---------|
+| next-task | 10 | 3 | Master workflow orchestration |
+| enhance | 9 | 9 | Code quality analyzers |
+| ship | 0 | 0 | PR creation and deployment |
+| perf | 6 | 8 | Performance investigation |
+| audit-project | 10 | 0 | Multi-agent code review |
+| deslop | 1 | 1 | AI slop cleanup |
+| drift-detect | 1 | 1 | Plan drift detection |
+| repo-map | 1 | 1 | AST repo mapping |
+| sync-docs | 1 | 1 | Documentation sync |
+
+**Pattern**: `Command → Agent → Skill` (orchestration → invocation → implementation)
 </architecture>
 
-<plugins>
-## Plugins Overview
-
-| Plugin | Commands | Agents | Skills | Purpose |
-|--------|----------|--------|--------|---------|
-| next-task | 3 | 10 | 3 | Master workflow orchestration |
-| enhance | 1 | 9 | 9 | Code quality analyzers |
-| ship | 4 | 0 | 0 | PR creation and deployment |
-| perf | 1 | 6 | 8 | Performance investigation |
-| audit-project | 3 | 0 | 0 | Multi-agent code review |
-| deslop | 1 | 1 | 1 | AI slop cleanup |
-| drift-detect | 1 | 1 | 1 | Plan drift detection |
-| repo-map | 1 | 1 | 1 | AST-based repo mapping |
-| sync-docs | 1 | 1 | 1 | Documentation sync |
-</plugins>
-
 <commands>
 ## Commands
 
@@ -154,84 +113,32 @@ awesome-slash                # Run installer
 </commands>
 
 <agents>
-## Key Agents
-
-### next-task (10 agents)
-| Agent | Model | Purpose |
-|-------|-------|---------|
-| task-discoverer | sonnet | Find and rank tasks from sources |
-| worktree-manager | haiku | Create isolated git worktrees |
-| exploration-agent | opus | Deep codebase analysis |
-| planning-agent | opus | Design implementation plans |
-| implementation-agent | opus | Execute approved plans |
-| test-coverage-checker | sonnet | Validate test coverage |
-| delivery-validator | sonnet | Autonomous completion validation |
-| ci-monitor | haiku | Monitor CI and PR comments |
-| ci-fixer | sonnet | Fix CI failures |
-| simple-fixer | haiku | Execute mechanical fixes |
-
-### deslop (1 agent)
-| Agent | Model | Purpose |
-|-------|-------|---------|
-| deslop-agent | sonnet | Clean AI slop patterns from code |
-
-### enhance (9 agents)
-| Agent | Model | Purpose |
-|-------|-------|---------|
-| enhancement-orchestrator | opus | Coordinate all enhancers |
-| enhancement-reporter | sonnet | Generate unified reports |
-| plugin-enhancer | sonnet | Analyze plugin structures |
-| agent-enhancer | opus | Analyze agent prompts |
-| docs-enhancer | sonnet | Analyze documentation |
-| claudemd-enhancer | sonnet | Analyze CLAUDE.md files |
-| prompt-enhancer | opus | Analyze prompt quality |
-| hooks-enhancer | opus | Analyze hook safety |
-| skills-enhancer | opus | Analyze skill triggers |
-
-### perf (6 agents)
-| Agent | Model | Purpose |
-|-------|-------|---------|
-| perf-orchestrator | opus | Coordinate perf investigation |
-| perf-analyzer | opus | Synthesize findings |
-| perf-code-paths | sonnet | Map likely hot paths |
-| perf-theory-gatherer | opus | Generate hypotheses |
-| perf-theory-tester | opus | Run controlled experiments |
-| perf-investigation-logger | sonnet | Log evidence |
+## Agents
+
+39 agents across 9 plugins. Key agents by model:
+
+| Model | Agents | Use Case |
+|-------|--------|----------|
+| **opus** | exploration, planning, implementation, perf-orchestrator | Complex reasoning, analysis |
+| **sonnet** | task-discoverer, delivery-validator, ci-fixer, deslop-agent, reporters | Validation, pattern matching |
+| **haiku** | worktree-manager, ci-monitor, simple-fixer | Mechanical execution |
+
+See [README.md](./README.md#command-details) and [docs/reference/AGENTS.md](./docs/reference/AGENTS.md) for full agent list.
 </agents>
 
 <skills>
 ## Skills
 
-Skills contain reusable implementation. Agents invoke skills to perform work.
-
-### next-task Skills
-- `orchestrate-review` - Phase 9 review loop logic
-- `discover-tasks` - Task discovery and scoring
-- `validate-delivery` - Completion validation checks
-
-### enhance Skills
-- `enhance-orchestrator` - Enhancer coordination
-- `enhance-reporter` - Report generation
-- `enhance-plugins` - Plugin analysis patterns
-- `enhance-agent-prompts` - Agent analysis patterns
-- `enhance-docs` - Documentation patterns
-- `enhance-claude-memory` - CLAUDE.md patterns
-- `enhance-prompts` - Prompt quality patterns
-- `enhance-hooks` - Hook safety patterns
-- `enhance-skills` - Skill trigger patterns
-
-### perf Skills
-- `baseline`, `benchmark`, `profile` - Measurement
-- `analyzer`, `code-paths`, `theory` - Analysis
-- `theory-tester`, `investigation-logger` - Testing
-
-### deslop Skills
-- `deslop` - AI slop detection and cleanup
-
-### Other Skills
-- `drift-analysis` - Plan drift detection
-- `repo-mapping` - AST repo map generation
-- `sync-docs` - Documentation sync with code
+25 skills across plugins. Agents invoke skills for reusable implementation.
+
+| Category | Key Skills |
+|----------|------------|
+| Workflow | `orchestrate-review`, `discover-tasks`, `validate-delivery` |
+| Enhancement | `enhance-*` (9 skills for plugins, agents, docs, prompts, hooks) |
+| Performance | `baseline`, `benchmark`, `profile`, `theory-tester` |
+| Cleanup | `deslop`, `sync-docs`, `drift-analysis`, `repo-mapping` |
+
+See [README.md](./README.md#skills) for full skill list.
 </skills>
 
 <state-files>
@@ -242,11 +149,11 @@ Skills contain reusable implementation. Agents invoke skills to perform work.
 | `tasks.json` | `{stateDir}/` | Active task registry |
 | `flow.json` | `{stateDir}/` (worktree) | Workflow progress |
 | `preference.json` | `{stateDir}/sources/` | Cached task source |
-| `suppressions.json` | `~/.claude/enhance/` | Auto-learned suppressions |
+| `suppressions.json` | `~/.<claude\|opencode\|codex>/enhance/` | Auto-learned suppressions |
 
 Platform-aware state directory:
 - Claude Code: `.claude/`
-- OpenCode: `.opencode/`
+- OpenCode: `config/.opencode/`
 - Codex: `.codex/`
 </state-files>
 
@@ -274,19 +181,13 @@ Cannot skip in /next-task:
 </pr-auto-review>
 
 <model-selection>
-## Model Selection Guidelines
+## Model Selection
 
 | Model | When to Use |
 |-------|-------------|
-| **Opus** | Complex reasoning, enhancers, analyzers where imperfection compounds |
-| **Sonnet** | Most agents, validation, pattern matching |
-| **Haiku** | Mechanical execution, simple operations, no judgment needed |
-
-**Examples**:
-- `exploration-agent` uses opus - codebase analysis requires deep reasoning
-- `delivery-validator` uses sonnet - validation is structured
-- `simple-fixer` uses haiku - mechanically applies pre-defined fixes
-- `worktree-manager` uses haiku - scripted git commands
+| **Opus** | Complex reasoning, analysis where imperfection compounds |
+| **Sonnet** | Validation, pattern matching, most agents |
+| **Haiku** | Mechanical execution, no judgment needed |
 </model-selection>
 
 <priorities>
@@ -301,7 +202,7 @@ Cannot skip in /next-task:
 
 <end-reminder>
 **REMEMBER**:
-- No summary files (`*_AUDIT.md`, `*_SUMMARY.md`) - use CHANGELOG.md
+- Use CHANGELOG.md for completion tracking (not summary files)
 - BEFORE starting → Read the relevant checklist (`checklists/*.md`)
 - BEFORE delivering any work, especially releases → Go through that checklist item by item
 - 3 platforms: Claude Code + OpenCode + Codex - ALL must work

package/CHANGELOG.md

@@ -7,6 +7,54 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [4.0.0] - 2026-02-05
+
+### Added
+- **New /learn Plugin** - Research any topic online and create comprehensive learning guides
+  - Gathers 10-40 online sources based on depth level (brief/medium/deep)
+  - Uses progressive query architecture (funnel approach: broad → specific → deep)
+  - Implements source quality scoring (authority, recency, depth, examples, uniqueness)
+  - Just-in-time retrieval to avoid context rot
+  - Creates topic-specific guides in `agent-knowledge/` directory
+  - Maintains CLAUDE.md/AGENTS.md as master RAG indexes
+  - Self-evaluation step for output quality assessment
+  - Integrates with enhance:enhance-docs and enhance:enhance-prompts
+  - Opus model for high-quality research synthesis
+
+### Changed
+- **Agent Frontmatter Format** - Converted all 29 agents to YAML array format for tools field (Claude Code spec compliance)
+- **Argument Hints** - Aligned all argument-hint fields to official `[placeholder]` format
+- **Plugin Count** - Now 10 plugins total (added learn)
+
+### Fixed
+- **Semver Sorting** - Fixed version comparison so "1.10.0" correctly > "1.9.9"
+- **CodeQL Security** - Escape backslashes in glob pattern matching
+- **Path Traversal** - Use `path.relative()` instead of `startsWith()` for Windows compatibility
+
+## [4.0.0-rc.1] - 2026-02-05
+
+### Added
+- **New /learn Plugin** - Research any topic online and create comprehensive learning guides
+  - Gathers 10-40 online sources based on depth level (brief/medium/deep)
+  - Uses progressive query architecture (funnel approach: broad → specific → deep)
+  - Implements source quality scoring (authority, recency, depth, examples, uniqueness)
+  - Just-in-time retrieval to avoid context rot
+  - Creates topic-specific guides in `agent-knowledge/` directory
+  - Maintains CLAUDE.md/AGENTS.md as master RAG indexes
+  - Self-evaluation step for output quality assessment
+  - Integrates with enhance:enhance-docs and enhance:enhance-prompts
+  - Opus model for high-quality research synthesis
+
+### Changed
+- **Agent Frontmatter Format** - Converted all 29 agents to YAML array format for tools field (Claude Code spec compliance)
+- **Argument Hints** - Aligned all argument-hint fields to official `[placeholder]` format
+- **Plugin Count** - Now 10 plugins total (added learn)
+
+### Fixed
+- **Semver Sorting** - Fixed version comparison so "1.10.0" correctly > "1.9.9"
+- **CodeQL Security** - Escape backslashes in glob pattern matching
+- **Path Traversal** - Use `path.relative()` instead of `startsWith()` for Windows compatibility
+
 ## [3.9.0] - 2026-02-04
 
 ### Fixed

package/README.md

@@ -8,7 +8,7 @@
 
 AI models can write code. That's not the hard part anymore. The hard part is everything else—picking what to work on, managing branches, reviewing output, cleaning up artifacts, handling CI, addressing comments, deploying. **awesome-slash automates the entire workflow**, not just the coding.
 
-**9 plugins · 39 agents · 25 skills · 26k lines of lib code · 3,357 tests · 3 platforms**
+**10 plugins · 39 agents · 25 skills · 26k lines of lib code · 3,357 tests · 3 platforms**
 
 If you find this useful: [⭐ Star the repo](https://github.com/avifenesh/awesome-slash)
 
@@ -59,6 +59,7 @@ This came from testing on 1,000+ repositories.
 | [`/enhance`](#enhance) | Analyzes prompts, agents, plugins, docs, hooks, skills |
 | [`/repo-map`](#repo-map) | AST symbol and import mapping via ast-grep |
 | [`/sync-docs`](#sync-docs) | Finds outdated references, stale examples, missing CHANGELOG entries |
+| [`/learn`](#learn) | Research any topic, gather online sources, create learning guide with RAG index |
 
 Each command works standalone. Together, they form complete workflows.
 
@@ -71,10 +72,11 @@ Each command works standalone. Together, they form complete workflows.
 | Category | Skills |
 |----------|--------|
 | **Performance** | `perf:analyzer`, `perf:baseline`, `perf:benchmark`, `perf:code-paths`, `perf:investigation-logger`, `perf:profile`, `perf:theory`, `perf:theory-tester` |
-| **Enhancement** | `enhance:agent-prompts`, `enhance:claude-memory`, `enhance:cross-file`, `enhance:docs`, `enhance:hooks`, `enhance:orchestrator`, `enhance:plugins`, `enhance:prompts`, `enhance:reporter`, `enhance:skills` |
+| **Enhancement** | `enhance:agent-prompts`, `enhance:claude-memory`, `enhance:cross-file`, `enhance:docs`, `enhance:hooks`, `enhance:orchestrator`, `enhance:plugins`, `enhance:prompts`, `enhance:skills` |
 | **Workflow** | `next-task:orchestrate-review`, `next-task:discover-tasks`, `next-task:validate-delivery` |
 | **Cleanup** | `deslop:deslop`, `sync-docs:sync-docs` |
 | **Analysis** | `drift-detect:drift-analysis`, `repo-map:repo-mapping` |
+| **Learning** | `learn:learn` |
 
 Skills give your agents specialized capabilities. When you install a plugin, its skills become available to all agents in that session.
 
@@ -468,6 +470,51 @@ You refactor `auth.js` into `auth/index.js`. Your README still says `import from
 
 ---
 
+### /learn
+
+**Purpose:** Research any topic online and create a comprehensive learning guide with RAG-optimized indexes.
+
+**What it does:**
+
+1. **Progressive Discovery** - Uses funnel approach (broad → specific → deep) to find quality sources
+2. **Quality Scoring** - Scores sources by authority, recency, depth, examples, uniqueness
+3. **Just-In-Time Extraction** - Fetches only high-scoring sources to save tokens
+4. **Synthesis** - Creates structured learning guide with examples and best practices
+5. **RAG Index** - Updates CLAUDE.md/AGENTS.md master index for future lookups
+6. **Enhancement** - Runs enhance:enhance-docs and enhance:enhance-prompts
+
+**Depth levels:**
+
+| Depth | Sources | Use Case |
+|-------|---------|----------|
+| brief | 10 | Quick overview |
+| medium | 20 | Default, balanced |
+| deep | 40 | Comprehensive |
+
+**Output structure:**
+
+```
+agent-knowledge/
+  CLAUDE.md                    # Master index (updated each run)
+  AGENTS.md                    # Index for OpenCode/Codex
+  recursion.md                 # Topic-specific guide
+  resources/
+    recursion-sources.json     # Source metadata with quality scores
+```
+
+**Usage:**
+
+```bash
+/learn recursion                    # Default (20 sources)
+/learn react hooks --depth=deep     # Comprehensive (40 sources)
+/learn kubernetes --depth=brief     # Quick overview (10 sources)
+/learn python async --no-enhance    # Skip enhancement pass
+```
+
+**Agent:** learn-agent (opus model for research quality)
+
+---
+
 ## How Commands Work Together
 
 **Standalone use:**

package/adapters/opencode/install.sh

@@ -271,7 +271,7 @@ if [ -d "$LEGACY_AGENTS_DIR" ]; then
   known_agents=(
     'agent-enhancer.md' 'ci-fixer.md' 'ci-monitor.md' 'claudemd-enhancer.md'
     'delivery-validator.md' 'deslop-agent.md' 'docs-enhancer.md' 'enhancement-orchestrator.md'
-    'enhancement-reporter.md' 'exploration-agent.md' 'hooks-enhancer.md' 'implementation-agent.md'
+    'exploration-agent.md' 'hooks-enhancer.md' 'implementation-agent.md' 'learn-agent.md'
     'map-validator.md' 'perf-analyzer.md' 'perf-code-paths.md' 'perf-investigation-logger.md'
     'perf-orchestrator.md' 'perf-theory-gatherer.md' 'perf-theory-tester.md' 'plan-synthesizer.md'
     'planning-agent.md' 'plugin-enhancer.md' 'prompt-enhancer.md' 'simple-fixer.md'

package/bin/cli.js

@@ -220,7 +220,7 @@ function installForClaude() {
     }
 
     // PLUGINS_ARRAY - Install or update plugins
-    const plugins = ['next-task', 'ship', 'deslop', 'audit-project', 'drift-detect', 'enhance', 'sync-docs', 'repo-map', 'perf'];
+    const plugins = ['next-task', 'ship', 'deslop', 'audit-project', 'drift-detect', 'enhance', 'sync-docs', 'repo-map', 'perf', 'learn'];
     for (const plugin of plugins) {
       console.log(`  Installing ${plugin}...`);
       try {
@@ -237,7 +237,7 @@ function installForClaude() {
     }
 
     console.log('\n[OK] Claude Code installation complete!\n');
-    console.log('Commands: /next-task, /ship, /deslop, /audit-project, /drift-detect, /enhance, /perf');
+    console.log('Commands: /next-task, /ship, /deslop, /audit-project, /drift-detect, /enhance, /perf, /learn');
     return true;
   } catch (err) {
     console.log('[ERROR] Auto-install failed. Manual installation:');
@@ -261,7 +261,7 @@ function installForClaudeDevelopment() {
   }
 
   const pluginsDir = getClaudePluginsDir();
-  const plugins = ['next-task', 'ship', 'deslop', 'audit-project', 'drift-detect', 'enhance', 'sync-docs', 'repo-map', 'perf'];
+  const plugins = ['next-task', 'ship', 'deslop', 'audit-project', 'drift-detect', 'enhance', 'sync-docs', 'repo-map', 'perf', 'learn'];
 
   // Remove marketplace plugins first
   console.log('Removing marketplace plugins...');
@@ -310,7 +310,7 @@ function installForClaudeDevelopment() {
 
   console.log('\n[OK] Claude Code development installation complete!');
   console.log('  Plugins installed to: ' + pluginsDir);
-  console.log('  Commands: /next-task, /ship, /deslop, /audit-project, /drift-detect, /enhance, /perf');
+  console.log('  Commands: /next-task, /ship, /deslop, /audit-project, /drift-detect, /enhance, /perf, /learn');
   console.log('\n[NOTE] To revert to marketplace version:');
   console.log('  rm -rf ~/.claude/plugins/*@awesome-slash');
   console.log('  awesome-slash --tool claude');
@@ -370,7 +370,8 @@ function installForOpenCode(installDir, options = {}) {
     ['ship.md', 'ship', 'ship.md'],
     ['drift-detect.md', 'drift-detect', 'drift-detect.md'],
     ['repo-map.md', 'repo-map', 'repo-map.md'],
-    ['perf.md', 'perf', 'perf.md']
+    ['perf.md', 'perf', 'perf.md'],
+    ['learn.md', 'learn', 'learn.md']
   ];
 
   // Helper function to transform content for OpenCode
@@ -574,7 +575,7 @@ After user answers, proceed to Phase 2 with the selected policy.
   fs.mkdirSync(agentsDir, { recursive: true });
 
   console.log('  Installing agents for OpenCode...');
-  const pluginDirs = ['next-task', 'enhance', 'audit-project', 'drift-detect', 'ship', 'deslop', 'repo-map', 'perf', 'sync-docs'];
+  const pluginDirs = ['next-task', 'enhance', 'audit-project', 'drift-detect', 'ship', 'deslop', 'repo-map', 'perf', 'sync-docs', 'learn'];
   let agentCount = 0;
 
   for (const pluginName of pluginDirs) {
@@ -686,7 +687,7 @@ After user answers, proceed to Phase 2 with the selected policy.
   console.log(`   Commands: ${commandsDir}`);
   console.log(`   Agents: ${agentsDir}`);
   console.log(`   Plugin: ${pluginDir}`);
-  console.log('   Access via: /next-task, /ship, /deslop, /audit-project, /drift-detect, /enhance, /sync-docs, /perf');
+  console.log('   Access via: /next-task, /ship, /deslop, /audit-project, /drift-detect, /enhance, /sync-docs, /perf, /learn');
   console.log('   Native features: Auto-thinking selection, workflow enforcement, session compaction\n');
   return true;
 }
@@ -749,7 +750,9 @@ function installForCodex(installDir) {
     ['delivery-approval', 'next-task', 'delivery-approval.md',
       'Use when user asks to "validate delivery", "approve for shipping", "check if ready to ship", "verify task completion". Autonomous validation that tests pass, build succeeds, and requirements are met.'],
     ['sync-docs', 'sync-docs', 'sync-docs.md',
-      'Use when user asks to "update docs", "sync documentation", "fix outdated docs", "refresh README". Compares documentation to actual code and fixes discrepancies.']
+      'Use when user asks to "update docs", "sync documentation", "fix outdated docs", "refresh README". Compares documentation to actual code and fixes discrepancies.'],
+    ['learn', 'learn', 'learn.md',
+      'Use when user asks to "learn about topic", "research subject", "create learning guide", "build knowledge base", "study topic". Gathers online sources and synthesizes comprehensive guide with RAG index.']
   ];
 
   for (const [skillName, plugin, sourceFile, description] of skillMappings) {