agentsys 5.0.3 → 5.2.0

package/.claude-plugin/marketplace.json

@@ -1,12 +1,12 @@
 {
   "name": "agentsys",
-  "description": "12 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, perf investigations, topic research, agent config linting, and cross-tool AI consultation",
-  "version": "5.0.3",
+  "description": "14 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, perf investigations, topic research, agent config linting, cross-tool AI consultation, and structured AI debate",
+  "version": "5.2.0",
   "owner": {
     "name": "Avi Fenesh",
     "url": "https://github.com/avifenesh"
   },
-  "repository": "https://github.com/avifenesh/agentsys",
+  "repository": "https://github.com/agent-sh/agentsys",
   "keywords": [
     "ai",
     "llm",
@@ -24,87 +24,157 @@
   "plugins": [
     {
       "name": "next-task",
-      "source": "./plugins/next-task",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/next-task.git"
+      },
       "description": "Master workflow orchestrator: autonomous workflow with model optimization (opus/sonnet/haiku), two-file state management, workflow enforcement gates, 14 specialist agents",
-      "version": "5.0.3",
-      "category": "productivity"
+      "version": "1.0.0",
+      "category": "productivity",
+      "homepage": "https://github.com/agent-sh/next-task"
     },
     {
       "name": "ship",
-      "source": "./plugins/ship",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/ship.git"
+      },
       "description": "Complete PR workflow: commit to production, skips review when called from next-task, removes task from registry on cleanup, automatic rollback",
-      "version": "5.0.3",
-      "category": "deployment"
+      "version": "1.0.0",
+      "category": "deployment",
+      "homepage": "https://github.com/agent-sh/ship"
     },
     {
       "name": "deslop",
-      "source": "./plugins/deslop",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/deslop.git"
+      },
       "description": "3-phase AI slop detection: regex patterns (HIGH), multi-pass analyzers (MEDIUM), CLI tools (LOW)",
-      "version": "5.0.3",
-      "category": "development"
+      "version": "1.0.0",
+      "category": "development",
+      "homepage": "https://github.com/agent-sh/deslop"
     },
     {
       "name": "audit-project",
-      "source": "./plugins/audit-project",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/audit-project.git"
+      },
       "description": "Multi-agent iterative code review until zero issues remain",
-      "version": "5.0.3",
-      "category": "development"
+      "version": "1.0.0",
+      "category": "development",
+      "homepage": "https://github.com/agent-sh/audit-project"
     },
     {
       "name": "drift-detect",
-      "source": "./plugins/drift-detect",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/drift-detect.git"
+      },
       "description": "Deep repository analysis to realign project plans with code reality - detects drift, gaps, and creates prioritized reconstruction plans",
-      "version": "5.0.3",
-      "category": "productivity"
+      "version": "1.0.0",
+      "category": "productivity",
+      "homepage": "https://github.com/agent-sh/drift-detect"
     },
     {
       "name": "enhance",
-      "source": "./plugins/enhance",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/enhance.git"
+      },
       "description": "Master enhancement orchestrator: parallel analyzer execution for plugins, agents, docs, CLAUDE.md, and prompts with unified reporting",
-      "version": "5.0.3",
-      "category": "development"
+      "version": "1.0.0",
+      "category": "development",
+      "homepage": "https://github.com/agent-sh/enhance"
     },
     {
       "name": "sync-docs",
-      "source": "./plugins/sync-docs",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/sync-docs.git"
+      },
       "description": "Standalone documentation sync: find outdated refs, update CHANGELOG, flag stale examples based on code changes",
-      "version": "5.0.3",
-      "category": "development"
+      "version": "1.0.0",
+      "category": "development",
+      "homepage": "https://github.com/agent-sh/sync-docs"
     },
     {
       "name": "repo-map",
-      "source": "./plugins/repo-map",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/repo-map.git"
+      },
       "description": "AST-based repository map generation using ast-grep with incremental updates for faster drift analysis",
-      "version": "5.0.3",
-      "category": "development"
+      "version": "1.0.0",
+      "category": "development",
+      "homepage": "https://github.com/agent-sh/repo-map"
     },
     {
       "name": "perf",
-      "source": "./plugins/perf",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/perf.git"
+      },
       "description": "Rigorous performance investigation workflow with baselines, profiling, hypotheses, and evidence-backed decisions",
-      "version": "5.0.3",
-      "category": "development"
+      "version": "1.0.0",
+      "category": "development",
+      "homepage": "https://github.com/agent-sh/perf"
     },
     {
       "name": "learn",
-      "source": "./plugins/learn",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/learn.git"
+      },
       "description": "Research topics online and create comprehensive learning guides with RAG-optimized indexes",
-      "version": "5.0.3",
-      "category": "productivity"
+      "version": "1.0.0",
+      "category": "productivity",
+      "homepage": "https://github.com/agent-sh/learn"
     },
     {
       "name": "agnix",
-      "source": "./plugins/agnix",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/agnix.git"
+      },
       "description": "Lint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 155 rules across 10+ AI tools",
-      "version": "5.0.3",
-      "category": "development"
+      "version": "1.0.0",
+      "category": "development",
+      "homepage": "https://github.com/agent-sh/agnix"
     },
     {
       "name": "consult",
-      "source": "./plugins/consult",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/consult.git"
+      },
       "description": "Cross-tool AI consultation: get second opinions from Gemini CLI, Codex CLI, Claude Code, OpenCode, or Copilot CLI with model and thinking effort control",
-      "version": "5.0.3",
-      "category": "productivity"
+      "version": "1.0.0",
+      "category": "productivity",
+      "homepage": "https://github.com/agent-sh/consult"
+    },
+    {
+      "name": "debate",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/debate.git"
+      },
+      "description": "Structured multi-round debate between AI tools with proposer/challenger roles and verdict",
+      "version": "1.0.0",
+      "category": "productivity",
+      "homepage": "https://github.com/agent-sh/debate"
+    },
+    {
+      "name": "web-ctl",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/web-ctl.git"
+      },
+      "description": "Browser automation and web testing toolkit for AI agents - headless browser control, persistent sessions, auth handoff, and prompt injection defense",
+      "version": "1.0.0",
+      "category": "automation",
+      "homepage": "https://github.com/agent-sh/web-ctl"
     }
   ]
 }

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agentsys",
-  "version": "5.0.3",
+  "version": "5.2.0",
   "description": "Professional-grade slash commands for Claude Code with cross-platform support",
   "keywords": [
     "workflow",
@@ -15,6 +15,6 @@
     "name": "Avi Fenesh",
     "url": "https://github.com/avifenesh"
   },
-  "repository": "https://github.com/avifenesh/agentsys",
+  "repository": "https://github.com/agent-sh/agentsys",
   "license": "MIT"
 }

package/AGENTS.md

@@ -76,7 +76,7 @@
 <!-- GEN:START:claude-architecture -->
 ```
 lib/          → Shared library (vendored to plugins)
-plugins/      → 12 plugins, 41 agents (31 file-based + 10 role-based), 27 skills
+plugins/      → 0 plugins, 10 agents (0 file-based + 10 role-based), 0 skills
 adapters/     → Platform adapters (opencode-plugin/, opencode/, codex/)
 checklists/   → Action checklists (9 files)
 bin/cli.js    → npm CLI installer
@@ -84,18 +84,6 @@ bin/cli.js    → npm CLI installer
 
 | Plugin | Agents | Skills | Purpose |
 |--------|--------|--------|---------|
-| agnix | 1 | 1 | Agent config linting |
-| audit-project | 10 | 0 | Multi-agent code review |
-| consult | 1 | 1 | Cross-tool AI consultation |
-| deslop | 1 | 1 | AI slop cleanup |
-| drift-detect | 1 | 1 | Plan drift detection |
-| enhance | 8 | 9 | Code quality analyzers |
-| learn | 1 | 1 | Topic research and learning guides |
-| next-task | 10 | 3 | Master workflow orchestration |
-| perf | 6 | 8 | Performance investigation |
-| repo-map | 1 | 1 | AST repo mapping |
-| ship | 0 | 0 | PR creation and deployment |
-| sync-docs | 1 | 1 | Documentation sync |
 <!-- GEN:END:claude-architecture -->
 
 **Pattern**: `Command → Agent → Skill` (orchestration → invocation → implementation)
@@ -252,7 +240,7 @@ Cannot skip in /next-task:
 - 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
+- 4 platforms: Claude Code + OpenCode + Codex + Cursor - ALL must work
 - Agent/Skill pattern: Agents invoke skills, skills have implementation
 - Create PRs for non-trivial changes
 </end-reminder>

package/CHANGELOG.md

@@ -9,6 +9,66 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [5.2.0] - 2026-02-27
+
+### Added
+
+- **Cursor platform support (#261)** — agentsys now installs to Cursor as a 4th platform alongside Claude Code, OpenCode, and Codex CLI. Use `agentsys --tool cursor` or `agentsys install <plugin> --tool cursor` to install. Skills are copied to `.cursor/skills/` (same SKILL.md format - no transform needed), commands to `.cursor/commands/` (light transform), and rules to `.cursor/rules/*.mdc` (MDC frontmatter). All content is project-scoped. Cursor v2.4+ natively supports the Agent Skills standard.
+
+- **`/web-ctl` plugin** — New plugin for browser automation and web testing. Headless browser control via Playwright with persistent encrypted sessions, human-in-the-loop auth handoff (including CAPTCHA detection and checkpoint mode), anti-bot measures (webdriver spoofing, random delays), WSL detection with Windows Chrome fallback, and prompt injection defense via `[PAGE_CONTENT: ...]` delimiters. Includes `web-session` agent, `web-auth` and `web-browse` skills, and the `/web-ctl` command. Available at [agent-sh/web-ctl](https://github.com/agent-sh/web-ctl).
+
+- **Plugin extraction to standalone repos (#250)** — All 13 plugins extracted from `plugins/` into standalone repos under the `agent-sh` org (`agent-sh/next-task`, `agent-sh/ship`, `agent-sh/deslop`, `agent-sh/audit-project`, `agent-sh/enhance`, `agent-sh/perf`, `agent-sh/drift-detect`, `agent-sh/sync-docs`, `agent-sh/repo-map`, `agent-sh/learn`, `agent-sh/consult`, `agent-sh/debate`, `agent-sh/agnix`). The `plugins/` directory has been removed from this repo. agentsys is now a marketplace + installer.
+
+- **External plugin fetching in installer** — `bin/cli.js` now fetches plugins from their standalone GitHub repos at install time rather than bundling them. The installer resolves the correct version for each platform using the marketplace manifest.
+
+- **Graduation script** (`scripts/graduate-plugin.js`) — Automates extraction of a plugin from the monorepo to a new standalone repo: creates repo, copies files, sets up agent-core sync, updates marketplace manifest.
+
+- **Marketplace `requires` field** — `.claude-plugin/marketplace.json` now supports a `requires` field per plugin entry to declare the minimum agentsys installer version required. The installer validates this at install time and warns on incompatibility.
+
+- **`/next-task` GitHub Projects source** — Added `gh-projects` as a supported task source. When selected, the workflow prompts for a project number and owner, then fetches issues from a GitHub Projects v2 board via `gh project item-list`. Includes PR-linked issue exclusion (same as GitHub Issues), input validation for project number and owner, and caching of project preferences. Fixes #247.
+
+### Fixed
+
+- **Installer crash with new marketplace schema** - Fixed `plugin.source.startsWith is not a function` error when installing plugins. The marketplace.json `source` field changed from a string to an object in #266 but the installer was not updated to handle the new format. Added `resolveSourceUrl()` helper that handles both legacy string and new `{ source: "url", url: "..." }` formats. Also fixed `.git` suffix in source URLs causing 404 errors when fetching tarballs from the GitHub API. Added fallback to `main` branch when version tags don't exist yet. Fixed Windows tar extraction failure by converting backslash paths to forward slashes for MSYS2 compatibility.
+
+- **CLAUDE.md merge conflict markers** - Resolved broken merge conflict markers (HEAD/ancestor markers without closer) that were committed to main.
+
+- **Windows jscpd output bug (#270)** - Fixed `runDuplicateDetection` creating a mangled filename on Windows when `--output NUL` was passed to jscpd via `execFileSync` (no shell). Replaced platform-specific null device with a temp directory via `os.tmpdir()` that is cleaned up in a `finally` block. Added 5 regression tests for temp directory lifecycle.
+
+- **task-discoverer**: Exclude issues that already have an open PR from discovery results (GitHub source only). Detection uses branch name suffix, PR body closing keywords (`closes/fixes/resolves #N`), and PR title `(#N)` convention. Fixes #236.
+
+- **`/debate` 240s timeout enforcement** — All tool invocations in the debate workflow now enforce a hard 240-second timeout. Round 1 proposer timeouts abort the debate; round 1 challenger timeouts proceed with an uncontested position; round 2+ timeouts synthesize from completed rounds. Added "all rounds timeout" error path (`[ERROR] Debate failed: all tool invocations timed out.`). Timeout handling is consistent across the Claude Code command, OpenCode adapter, Codex adapter, and the `debate-orchestrator` agent. Restored missing "Round 2+: Challenger Follow-up" template in the OpenCode adapter SKILL.md. Fixes issue #233.
+
+- **`/next-task` review loop exit conditions** — The Phase 9 review loop now continues iterating until all issues are resolved or a stall is detected (MAX_STALLS reduced from 2 to 1: two consecutive identical-hash iterations = stall). The `orchestrate-review` skill now uses `completePhase()` instead of `updateFlow()` to properly advance workflow state. Added `pre-review-gates` and `docs-update` to the `PHASES` array and `RESULT_FIELD_MAP` in `workflow-state.js`, ensuring these phases can be tracked and resumed correctly. Fixes issue #235.
+
+- **`/debate` command inline orchestration** — The `/debate` command now manages the full debate workflow directly (parse → resolve → execute → verdict), following the `/consult` pattern. The `debate-orchestrator` agent is now the programmatic entry point for other agents/workflows that need to spawn a debate via `Task()`. Fixes issue #231.
+
+- **`/debate` External Tool Quick Reference** — Added a "External Tool Quick Reference" section to all copies of the debate skill (`plugins/debate/skills/debate/SKILL.md`, OpenCode and Codex adapters) with safe command patterns, effort-to-model mapping tables, and output parsing expressions. The section includes a canonical-source pointer to `plugins/consult/skills/consult/SKILL.md` so the debate orchestrator doesn't duplicate provider logic. Added pointer notes in `debate-orchestrator` agents. Fixes issue #232.
+
+- **`/consult` and `/debate` model defaults update** — Gemini high/max effort now uses `gemini-3.1-pro-preview`; Gemini low/medium uses `gemini-3-flash-preview`. Codex uses `gpt-5.3-codex` for all effort tiers. Updated across all platforms: Claude Code plugin, OpenCode adapter, and Codex adapter for both consult and debate skills and commands. Fixes issue #234.
+
+- **`/consult` model name updates** — Updated stale model names in the consult skill: Codex models are now `o4-mini` (low/medium) and `o3` (high/max); Gemini models include `gemini-3-flash-preview`, `gemini-3-pro-preview`, and `gemini-3.1-pro-preview`. Synced to OpenCode adapter consult skill. Fixes issue #232.
+
+- **`/next-task` Phase 12 ship invocation** — Phase 12 now invokes `ship:ship` via `await Skill({ name: "ship:ship", args: ... })` instead of `Task({ subagent_type: "ship:ship", ... })`. `ship:ship` is a skill, not an agent; the previous `Task()` call silently failed, leaving the workflow stuck after delivery validation with no PR created. The Codex adapter is updated in parity and regression tests are added. Fixes issue #230.
+
+## [5.1.0] - 2026-02-18
+
+### Added
+
+- **`/debate` plugin** — New plugin for structured multi-round AI dialectic. Pick two tools (e.g. `codex vs gemini`), set 1–5 rounds, and get a proposer/challenger debate with a synthesized verdict. Supports natural language input, effort levels (`--effort=low|high|max`), and context injection (`--context=diff` or `--context=file=PATH`). Available on Claude Code, OpenCode, and Codex CLI.
+- **`/consult` multi-instance support** — Run N parallel consultations with the same tool using `--count=N` (or natural language: "ask 3 gemini about this"). Responses are numbered and a brief synthesis highlights agreements and differences.
+- **`/consult` natural language parsing** — Free-form queries are now parsed automatically without requiring explicit flags. "with codex about my auth approach", "ask gemini thoroughly about this design", or "3 claude opinions on error handling" all work out of the box.
+
+### Changed
+
+- **Agent model optimization** — `exploration-agent` and `learn-agent` switched from opus to sonnet, reducing cost and latency for exploration and research passes with no quality regression.
+
+### Fixed
+
+- **Debate `--context=file` path validation** — Added path containment checks to prevent directory traversal when passing file paths as context.
+- **Debate prompt hardening** — Context passthrough, canonical output redaction, and relaxed disagreement rules applied consistently across all debate rounds.
+- **Consult model/flag issues** — Hardened model flag handling and non-interactive invocation across all four supported tools (Claude, Gemini, Codex, OpenCode).
+
 ## [5.0.3] - 2026-02-17
 
 ### Fixed
@@ -123,7 +183,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - Added CI/CD integration example with GitHub Code Scanning SARIF workflow
   - Added installation instructions (Cargo, Homebrew)
   - Added "Why use agnix" value proposition section
-  - Prominent link to [agnix CLI project](https://github.com/avifenesh/agnix)
+  - Prominent link to [agnix CLI project](https://github.com/agent-sh/agnix)
   - Updated Commands table with more descriptive entry
   - Updated skill count to 26 across all references
 
@@ -143,7 +203,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - Auto-fix support with `--fix` flag
   - SARIF output for GitHub Code Scanning integration
   - Target-specific validation (`--target claude-code|cursor|codex`)
-  - Requires [agnix CLI](https://github.com/avifenesh/agnix) (`cargo install agnix-cli`)
+  - Requires [agnix CLI](https://github.com/agent-sh/agnix) (`cargo install agnix-cli`)
 
 ### Changed
 - **Plugin Count** - Now 11 plugins, 40 agents, 26 skills
@@ -207,6 +267,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## Previous Releases
 
-- [v3.x Changelog](https://github.com/avifenesh/agentsys/blob/main/changelogs/CHANGELOG-v3.md) (v3.0.0 - v3.9.0)
-- [v2.x Changelog](https://github.com/avifenesh/agentsys/blob/main/changelogs/CHANGELOG-v2.md) (v2.0.0 - v2.10.1)
-- [v1.x Changelog](https://github.com/avifenesh/agentsys/blob/main/changelogs/CHANGELOG-v1.md) (v1.0.0 - v1.1.0)
+- [v3.x Changelog](https://github.com/agent-sh/agentsys/blob/main/changelogs/CHANGELOG-v3.md) (v3.0.0 - v3.9.0)
+- [v2.x Changelog](https://github.com/agent-sh/agentsys/blob/main/changelogs/CHANGELOG-v2.md) (v2.0.0 - v2.10.1)
+- [v1.x Changelog](https://github.com/agent-sh/agentsys/blob/main/changelogs/CHANGELOG-v1.md) (v1.0.0 - v1.1.0)