Skip to content

Commit 8f142c9

Browse files
avifeneshavifenesh
committed
chore: release v5.2.0
1 parent b12b395 commit 8f142c9

File tree

8 files changed

+110
-134
lines changed

8 files changed

+110
-134
lines changed

‎.claude-plugin/marketplace.json‎

Lines changed: 57 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
{
22
"name": "agentsys",
33
"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",
4-
"version": "5.1.0",
4+
"version": "5.2.0",
55
"owner": {
66
"name": "Avi Fenesh",
77
"url": "https://github.com/avifenesh"
@@ -24,111 +24,153 @@
2424
"plugins": [
2525
{
2626
"name": "next-task",
27-
"source": {"source": "url", "url": "https://github.com/agent-sh/next-task.git"},
27+
"source": {
28+
"source": "url",
29+
"url": "https://github.com/agent-sh/next-task.git"
30+
},
2831
"description": "Master workflow orchestrator: autonomous workflow with model optimization (opus/sonnet/haiku), two-file state management, workflow enforcement gates, 14 specialist agents",
2932
"version": "1.0.0",
3033
"category": "productivity",
3134
"homepage": "https://github.com/agent-sh/next-task"
3235
},
3336
{
3437
"name": "ship",
35-
"source": {"source": "url", "url": "https://github.com/agent-sh/ship.git"},
38+
"source": {
39+
"source": "url",
40+
"url": "https://github.com/agent-sh/ship.git"
41+
},
3642
"description": "Complete PR workflow: commit to production, skips review when called from next-task, removes task from registry on cleanup, automatic rollback",
3743
"version": "1.0.0",
3844
"category": "deployment",
3945
"homepage": "https://github.com/agent-sh/ship"
4046
},
4147
{
4248
"name": "deslop",
43-
"source": {"source": "url", "url": "https://github.com/agent-sh/deslop.git"},
49+
"source": {
50+
"source": "url",
51+
"url": "https://github.com/agent-sh/deslop.git"
52+
},
4453
"description": "3-phase AI slop detection: regex patterns (HIGH), multi-pass analyzers (MEDIUM), CLI tools (LOW)",
4554
"version": "1.0.0",
4655
"category": "development",
4756
"homepage": "https://github.com/agent-sh/deslop"
4857
},
4958
{
5059
"name": "audit-project",
51-
"source": {"source": "url", "url": "https://github.com/agent-sh/audit-project.git"},
60+
"source": {
61+
"source": "url",
62+
"url": "https://github.com/agent-sh/audit-project.git"
63+
},
5264
"description": "Multi-agent iterative code review until zero issues remain",
5365
"version": "1.0.0",
5466
"category": "development",
5567
"homepage": "https://github.com/agent-sh/audit-project"
5668
},
5769
{
5870
"name": "drift-detect",
59-
"source": {"source": "url", "url": "https://github.com/agent-sh/drift-detect.git"},
71+
"source": {
72+
"source": "url",
73+
"url": "https://github.com/agent-sh/drift-detect.git"
74+
},
6075
"description": "Deep repository analysis to realign project plans with code reality - detects drift, gaps, and creates prioritized reconstruction plans",
6176
"version": "1.0.0",
6277
"category": "productivity",
6378
"homepage": "https://github.com/agent-sh/drift-detect"
6479
},
6580
{
6681
"name": "enhance",
67-
"source": {"source": "url", "url": "https://github.com/agent-sh/enhance.git"},
82+
"source": {
83+
"source": "url",
84+
"url": "https://github.com/agent-sh/enhance.git"
85+
},
6886
"description": "Master enhancement orchestrator: parallel analyzer execution for plugins, agents, docs, CLAUDE.md, and prompts with unified reporting",
6987
"version": "1.0.0",
7088
"category": "development",
7189
"homepage": "https://github.com/agent-sh/enhance"
7290
},
7391
{
7492
"name": "sync-docs",
75-
"source": {"source": "url", "url": "https://github.com/agent-sh/sync-docs.git"},
93+
"source": {
94+
"source": "url",
95+
"url": "https://github.com/agent-sh/sync-docs.git"
96+
},
7697
"description": "Standalone documentation sync: find outdated refs, update CHANGELOG, flag stale examples based on code changes",
7798
"version": "1.0.0",
7899
"category": "development",
79100
"homepage": "https://github.com/agent-sh/sync-docs"
80101
},
81102
{
82103
"name": "repo-map",
83-
"source": {"source": "url", "url": "https://github.com/agent-sh/repo-map.git"},
104+
"source": {
105+
"source": "url",
106+
"url": "https://github.com/agent-sh/repo-map.git"
107+
},
84108
"description": "AST-based repository map generation using ast-grep with incremental updates for faster drift analysis",
85109
"version": "1.0.0",
86110
"category": "development",
87111
"homepage": "https://github.com/agent-sh/repo-map"
88112
},
89113
{
90114
"name": "perf",
91-
"source": {"source": "url", "url": "https://github.com/agent-sh/perf.git"},
115+
"source": {
116+
"source": "url",
117+
"url": "https://github.com/agent-sh/perf.git"
118+
},
92119
"description": "Rigorous performance investigation workflow with baselines, profiling, hypotheses, and evidence-backed decisions",
93120
"version": "1.0.0",
94121
"category": "development",
95122
"homepage": "https://github.com/agent-sh/perf"
96123
},
97124
{
98125
"name": "learn",
99-
"source": {"source": "url", "url": "https://github.com/agent-sh/learn.git"},
126+
"source": {
127+
"source": "url",
128+
"url": "https://github.com/agent-sh/learn.git"
129+
},
100130
"description": "Research topics online and create comprehensive learning guides with RAG-optimized indexes",
101131
"version": "1.0.0",
102132
"category": "productivity",
103133
"homepage": "https://github.com/agent-sh/learn"
104134
},
105135
{
106136
"name": "agnix",
107-
"source": {"source": "url", "url": "https://github.com/agent-sh/agnix.git"},
137+
"source": {
138+
"source": "url",
139+
"url": "https://github.com/agent-sh/agnix.git"
140+
},
108141
"description": "Lint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 155 rules across 10+ AI tools",
109142
"version": "1.0.0",
110143
"category": "development",
111144
"homepage": "https://github.com/agent-sh/agnix"
112145
},
113146
{
114147
"name": "consult",
115-
"source": {"source": "url", "url": "https://github.com/agent-sh/consult.git"},
148+
"source": {
149+
"source": "url",
150+
"url": "https://github.com/agent-sh/consult.git"
151+
},
116152
"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",
117153
"version": "1.0.0",
118154
"category": "productivity",
119155
"homepage": "https://github.com/agent-sh/consult"
120156
},
121157
{
122158
"name": "debate",
123-
"source": {"source": "url", "url": "https://github.com/agent-sh/debate.git"},
159+
"source": {
160+
"source": "url",
161+
"url": "https://github.com/agent-sh/debate.git"
162+
},
124163
"description": "Structured multi-round debate between AI tools with proposer/challenger roles and verdict",
125164
"version": "1.0.0",
126165
"category": "productivity",
127166
"homepage": "https://github.com/agent-sh/debate"
128167
},
129168
{
130169
"name": "web-ctl",
131-
"source": {"source": "url", "url": "https://github.com/agent-sh/web-ctl.git"},
170+
"source": {
171+
"source": "url",
172+
"url": "https://github.com/agent-sh/web-ctl.git"
173+
},
132174
"description": "Browser automation and web testing toolkit for AI agents - headless browser control, persistent sessions, auth handoff, and prompt injection defense",
133175
"version": "1.0.0",
134176
"category": "automation",

‎.claude-plugin/plugin.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"name": "agentsys",
3-
"version": "5.1.0",
3+
"version": "5.2.0",
44
"description": "Professional-grade slash commands for Claude Code with cross-platform support",
55
"keywords": [
66
"workflow",

‎CHANGELOG.md‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
99

1010
## [Unreleased]
1111

12+
## [5.2.0] - 2026-02-27
13+
1214
### Added
1315

1416
- **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.
@@ -27,6 +29,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
2729

2830
### Fixed
2931

32+
- **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.
33+
34+
- **CLAUDE.md merge conflict markers** - Resolved broken merge conflict markers (HEAD/ancestor markers without closer) that were committed to main.
35+
3036
- **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.
3137

3238
- **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.

‎CLAUDE.md‎

Lines changed: 7 additions & 104 deletions
Original file line numberDiff line numberDiff line change
@@ -54,105 +54,13 @@ npm run validate # All validators
5454

5555
## References
5656

57-
<<<<<<< HEAD
58-
40 agents across 11 plugins. Key agents by model:
59-
60-
| Model | Agents | Use Case |
61-
|-------|--------|----------|
62-
| **opus** | planning, implementation, perf-orchestrator, debate-orchestrator | Complex reasoning, judgment |
63-
| **sonnet** | exploration, learn, task-discoverer, delivery-validator, ci-fixer, deslop-agent, reporters | Validation, pattern matching |
64-
| **haiku** | worktree-manager, ci-monitor, simple-fixer | Mechanical execution |
65-
66-
See [README.md](./README.md#command-details) and [docs/reference/AGENTS.md](./docs/reference/AGENTS.md) for full agent list.
67-
</agents>
68-
69-
<skills>
70-
## Skills
71-
72-
26 skills across plugins. Agents invoke skills for reusable implementation.
73-
74-
| Category | Key Skills |
75-
|----------|------------|
76-
| Workflow | `orchestrate-review`, `discover-tasks`, `validate-delivery` |
77-
| Enhancement | `enhance-*` (9 skills for plugins, agents, docs, prompts, hooks) |
78-
| Performance | `baseline`, `benchmark`, `profile`, `theory-tester` |
79-
| Cleanup | `deslop`, `sync-docs`, `drift-analysis`, `repo-mapping` |
80-
81-
See [README.md](./README.md#skills) for full skill list.
82-
</skills>
83-
84-
<state-files>
85-
## State Files
86-
87-
| File | Location | Purpose |
88-
|------|----------|---------|
89-
| `tasks.json` | `{stateDir}/` | Active task registry |
90-
| `flow.json` | `{stateDir}/` (worktree) | Workflow progress |
91-
| `preference.json` | `{stateDir}/sources/` | Cached task source |
92-
| `suppressions.json` | `~/.<claude\|opencode\|codex>/enhance/` | Auto-learned suppressions |
93-
94-
Platform-aware state directory:
95-
- Claude Code: `.claude/`
96-
- OpenCode: `config/.opencode/`
97-
- Codex: `.codex/`
98-
</state-files>
99-
100-
<workflow-agents>
101-
## Workflow Agents (MUST-CALL)
102-
103-
Cannot skip in /next-task:
104-
- `exploration-agent` → before planning
105-
- `planning-agent` → before implementation
106-
- **Phase 9 review loop** → MUST use orchestrate-review skill
107-
- `delivery-validator` → before sync-docs:sync-docs-agent
108-
- `sync-docs:sync-docs-agent` → before /ship
109-
</workflow-agents>
110-
111-
<pr-auto-review>
112-
## PR Auto-Review
113-
114-
4 reviewers: Copilot, Claude, Gemini, Codex
115-
116-
1. Wait 3 min after PR creation (initial auto-reviews)
117-
2. Claude-review may take 10+ min - wait for it
118-
3. Read ALL comments
119-
4. Address EVERY comment
120-
5. Iterate until zero unresolved
121-
</pr-auto-review>
122-
123-
<model-selection>
124-
## Model Selection
125-
126-
| Model | When to Use |
127-
|-------|-------------|
128-
| **Opus** | Complex reasoning, analysis where imperfection compounds |
129-
| **Sonnet** | Validation, pattern matching, most agents |
130-
| **Haiku** | Mechanical execution, no judgment needed |
131-
</model-selection>
132-
133-
<priorities>
134-
## Core Priorities
57+
- Part of the [agentsys](https://github.com/agent-sh/agentsys) ecosystem
58+
- https://agentskills.io
13559

136-
1. User DX (plugin users)
137-
2. Worry-free automation
138-
3. Token efficiency
139-
4. Quality output
140-
5. Simplicity
141-
</priorities>
60+
<project-memory>
14261

143-
<end-reminder>
144-
**REMEMBER**:
145-
- Use CHANGELOG.md for completion tracking (not summary files)
146-
- BEFORE starting → Read the relevant checklist (`checklists/*.md`)
147-
- BEFORE delivering any work, especially releases → Go through that checklist item by item
148-
- 4 platforms: Claude Code + OpenCode + Codex + Cursor - ALL must work
149-
- Agent/Skill pattern: Agents invoke skills, skills have implementation
150-
- Create PRs for non-trivial changes
151-
</end-reminder>
152-
153-
</project-memory>
154-
||||||| ddd8211
155-
40 agents across 11 plugins. Key agents by model:
62+
<agents>
63+
43 agents across 14 plugins. Key agents by model:
15664

15765
| Model | Agents | Use Case |
15866
|-------|--------|----------|
@@ -166,7 +74,7 @@ See [README.md](./README.md#command-details) and [docs/reference/AGENTS.md](./do
16674
<skills>
16775
## Skills
16876

169-
26 skills across plugins. Agents invoke skills for reusable implementation.
77+
30 skills across plugins. Agents invoke skills for reusable implementation.
17078

17179
| Category | Key Skills |
17280
|----------|------------|
@@ -242,14 +150,9 @@ Cannot skip in /next-task:
242150
- Use CHANGELOG.md for completion tracking (not summary files)
243151
- BEFORE starting → Read the relevant checklist (`checklists/*.md`)
244152
- BEFORE delivering any work, especially releases → Go through that checklist item by item
245-
- 3 platforms: Claude Code + OpenCode + Codex - ALL must work
153+
- 4 platforms: Claude Code + OpenCode + Codex + Cursor - ALL must work
246154
- Agent/Skill pattern: Agents invoke skills, skills have implementation
247155
- Create PRs for non-trivial changes
248156
</end-reminder>
249157

250158
</project-memory>
251-
252-
## References
253-
254-
- Part of the [agentsys](https://github.com/agent-sh/agentsys) ecosystem
255-
- https://agentskills.io

0 commit comments

Comments
 (0)