docs: refresh counts for protect-mcp + qa-orchestra; add CI validation · codehornets/agents-claude-code@6625d1e · GitHub
Skip to content

Commit 6625d1e

Browse files
wshobsonwshobson
committed
docs: refresh counts for protect-mcp + qa-orchestra; add CI validation
- Counts now reflect 79 plugins (77 local + 2 external via git-subdir), 184 agents, 150 skills, 98 commands across 25 categories - README/docs: add Governance category (protect-mcp), bump Testing to 2 (adds qa-orchestra), expand Security table to include reverse-engineering and block-no-verify, add Protect MCP skills section, surface pensyve in AI & ML - marketplace.json: bump metadata to 1.6.0, bump pensyve to 1.2.0 - Add .github/workflows/validate.yml to gate PRs on: - marketplace.json + every plugin.json + hooks.json parse as JSON - every ./plugins/<name> source resolves on disk with a plugin.json - plugin-eval pytest suite (would have caught the wshobson#482 sdk.stream bug class)
1 parent 2e04a96 commit 6625d1e

9 files changed

Lines changed: 152 additions & 45 deletions

File tree

‎.claude-plugin/marketplace.json‎

Lines changed: 3 additions & 3 deletions

‎.github/workflows/validate.yml‎

Lines changed: 92 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,92 @@
1+
name: Validate
2+
3+
on:
4+
pull_request:
5+
branches: [main]
6+
push:
7+
branches: [main]
8+
workflow_dispatch:
9+
10+
jobs:
11+
validate-json:
12+
name: Validate JSON files
13+
runs-on: ubuntu-latest
14+
steps:
15+
- uses: actions/checkout@v4
16+
17+
- name: Validate marketplace.json
18+
run: python3 -m json.tool .claude-plugin/marketplace.json > /dev/null
19+
20+
- name: Validate every plugin.json
21+
run: |
22+
set -e
23+
shopt -s globstar nullglob
24+
failed=0
25+
for f in plugins/*/.claude-plugin/plugin.json; do
26+
if ! python3 -m json.tool "$f" > /dev/null 2>&1; then
27+
echo "::error file=$f::invalid JSON"
28+
failed=1
29+
fi
30+
done
31+
exit $failed
32+
33+
- name: Validate hooks.json files
34+
run: |
35+
set -e
36+
shopt -s globstar nullglob
37+
failed=0
38+
for f in plugins/*/hooks/*.json; do
39+
if ! python3 -m json.tool "$f" > /dev/null 2>&1; then
40+
echo "::error file=$f::invalid JSON"
41+
failed=1
42+
fi
43+
done
44+
exit $failed
45+
46+
- name: Validate marketplace entries resolve to plugin dirs
47+
run: |
48+
python3 - <<'PY'
49+
import json, os, sys
50+
with open('.claude-plugin/marketplace.json') as f:
51+
mp = json.load(f)
52+
errors = []
53+
for p in mp.get('plugins', []):
54+
src = p.get('source')
55+
if isinstance(src, str) and src.startswith('./plugins/'):
56+
path = src.lstrip('./')
57+
if not os.path.isdir(path):
58+
errors.append(f"{p['name']}: source {src} does not exist")
59+
elif not os.path.isfile(os.path.join(path, '.claude-plugin', 'plugin.json')):
60+
errors.append(f"{p['name']}: missing .claude-plugin/plugin.json in {src}")
61+
elif isinstance(src, dict) and src.get('source') == 'git-subdir':
62+
if not src.get('url'):
63+
errors.append(f"{p['name']}: git-subdir entry missing url")
64+
if errors:
65+
for e in errors:
66+
print(f"::error::{e}")
67+
sys.exit(1)
68+
print(f"OK: {len(mp.get('plugins', []))} marketplace entries validated")
69+
PY
70+
71+
plugin-eval-tests:
72+
name: plugin-eval pytest
73+
runs-on: ubuntu-latest
74+
defaults:
75+
run:
76+
working-directory: plugins/plugin-eval
77+
steps:
78+
- uses: actions/checkout@v4
79+
80+
- name: Install uv
81+
uses: astral-sh/setup-uv@v5
82+
with:
83+
enable-cache: true
84+
85+
- name: Set up Python
86+
run: uv python install
87+
88+
- name: Sync dependencies
89+
run: uv sync --all-extras
90+
91+
- name: Run tests
92+
run: uv run pytest

‎CLAUDE.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,13 +1,13 @@
11
# Project: claude-agents
22

3-
Claude Code plugin marketplace — 75 focused plugins, 182 agents, 147 skills, 95 commands.
3+
Claude Code plugin marketplace — 79 plugins (77 local + 2 external via git-subdir), 184 agents, 150 skills, 98 commands.
44

55
## Repository Structure
66

77
```
88
claude-agents/
99
├── .claude-plugin/marketplace.json # Registry of all plugins
10-
├── plugins/ # All 72 plugins
10+
├── plugins/ # All 77 local plugins (2 more installed via git-subdir from external repos)
1111
│ ├── <plugin-name>/
1212
│ │ ├── .claude-plugin/plugin.json
1313
│ │ ├── agents/*.md

‎README.md‎

Lines changed: 20 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -4,27 +4,27 @@
44
55
[![Run in Smithery](https://smithery.ai/badge/skills/wshobson)](https://smithery.ai/skills?ns=wshobson&utm_source=github&utm_medium=badge)
66

7-
> **🎯 Agent Skills Enabled** — 149 specialized skills extend Claude's capabilities across plugins with progressive disclosure
7+
> **🎯 Agent Skills Enabled** — 150 specialized skills extend Claude's capabilities across plugins with progressive disclosure
88
9-
A comprehensive production-ready system combining **182 specialized AI agents**, **16 multi-agent workflow orchestrators**, **149 agent skills**, and **96 commands** organized into **77 focused, single-purpose plugins** for [Claude Code](https://docs.claude.com/en/docs/claude-code/overview).
9+
A comprehensive production-ready system combining **184 specialized AI agents**, **16 multi-agent workflow orchestrators**, **150 agent skills**, and **98 commands** organized into **79 focused, single-purpose plugins** for [Claude Code](https://docs.claude.com/en/docs/claude-code/overview).
1010

1111
## Overview
1212

1313
This unified repository provides everything needed for intelligent automation and multi-agent orchestration across modern software development:
1414

15-
- **77 Focused Plugins** - Granular, single-purpose plugins optimized for minimal token usage and composability
16-
- **182 Specialized Agents** - Domain experts with deep knowledge across architecture, languages, infrastructure, quality, data/AI, documentation, business operations, and SEO
17-
- **149 Agent Skills** - Modular knowledge packages with progressive disclosure for specialized expertise
15+
- **79 Focused Plugins** - Granular, single-purpose plugins optimized for minimal token usage and composability
16+
- **184 Specialized Agents** - Domain experts with deep knowledge across architecture, languages, infrastructure, quality, data/AI, documentation, business operations, and SEO
17+
- **150 Agent Skills** - Modular knowledge packages with progressive disclosure for specialized expertise
1818
- **16 Workflow Orchestrators** - Multi-agent coordination systems for complex operations like full-stack development, security hardening, ML pipelines, and incident response
19-
- **96 Commands** - Optimized utilities including project scaffolding, security scanning, test automation, and infrastructure setup
19+
- **98 Commands** - Optimized utilities including project scaffolding, security scanning, test automation, and infrastructure setup
2020

2121
### Key Features
2222

23-
- **Granular Plugin Architecture**: 77 focused plugins optimized for minimal token usage
24-
- **Comprehensive Tooling**: 96 commands including test generation, scaffolding, and security scanning
23+
- **Granular Plugin Architecture**: 79 focused plugins optimized for minimal token usage
24+
- **Comprehensive Tooling**: 98 commands including test generation, scaffolding, and security scanning
2525
- **100% Agent Coverage**: All plugins include specialized agents
26-
- **Agent Skills**: 149 specialized skills following for progressive disclosure and token efficiency
27-
- **Clear Organization**: 24 categories with 1-10 plugins each for easy discovery
26+
- **Agent Skills**: 150 specialized skills following for progressive disclosure and token efficiency
27+
- **Clear Organization**: 25 categories with 1-10 plugins each for easy discovery
2828
- **Efficient Design**: Average 3.6 components per plugin (follows Anthropic's 2-8 pattern)
2929

3030
### How It Works
@@ -49,7 +49,7 @@ Add this marketplace to Claude Code:
4949
/plugin marketplace add wshobson/agents
5050
```
5151

52-
This makes all 77 plugins available for installation, but **does not load any agents or tools** into your context.
52+
This makes all 79 plugins available for installation, but **does not load any agents or tools** into your context.
5353

5454
### Step 2: Install Plugins
5555

@@ -114,9 +114,9 @@ rm -rf ~/.claude/plugins/cache/claude-code-workflows && rm ~/.claude/plugins/ins
114114

115115
### Core Guides
116116

117-
- **[Plugin Reference](docs/plugins.md)** - Complete catalog of all 77 plugins
118-
- **[Agent Reference](docs/agents.md)** - All 182 agents organized by category
119-
- **[Agent Skills](docs/agent-skills.md)** - 149 specialized skills with progressive disclosure
117+
- **[Plugin Reference](docs/plugins.md)** - Complete catalog of all 79 plugins
118+
- **[Agent Reference](docs/agents.md)** - All 184 agents organized by category
119+
- **[Agent Skills](docs/agent-skills.md)** - 150 specialized skills with progressive disclosure
120120
- **[Usage Guide](docs/usage.md)** - Commands, workflows, and best practices
121121
- **[Architecture](docs/architecture.md)** - Design principles and patterns
122122
- **[PluginEval](docs/plugin-eval.md)** - Quality evaluation framework (layers, dimensions, scoring)
@@ -197,7 +197,7 @@ Transforms Claude Code into a project management tool with a structured **Contex
197197

198198
[→ View Conductor documentation](plugins/conductor/README.md)
199199

200-
### Agent Skills (149 skills across 36 plugins)
200+
### Agent Skills (150 skills across 37 plugins)
201201

202202
Specialized knowledge packages following Anthropic's progressive disclosure architecture:
203203

@@ -313,20 +313,21 @@ Uses kubernetes-architect agent with 4 specialized skills for production-grade c
313313

314314
## Plugin Categories
315315

316-
**24 categories, 77 plugins:**
316+
**25 categories, 79 plugins:**
317317

318318
- 🎨 **Development** (6) - debugging, backend, frontend, multi-platform
319319
- 📚 **Documentation** (4) - code docs, API specs, diagrams, C4 architecture, **HADS** (Human-AI Document Standard)
320320
- 🔄 **Workflows** (5) - git, full-stack, TDD, **Conductor** (context-driven development), **Agent Teams** (multi-agent orchestration)
321-
- ✅ **Testing** (1) - unit testing
321+
- ✅ **Testing** (2) - unit testing, **qa-orchestra** (multi-agent QA toolkit with Chrome MCP validation)
322322
- 🔍 **Quality** (3) - comprehensive review, performance
323-
- 🤖 **AI & ML** (5) - LLM apps, agent orchestration, context, MLOps
323+
- 🤖 **AI & ML** (5) - LLM apps, agent orchestration, context, MLOps, **pensyve** (intelligent memory capture)
324324
- 📊 **Data** (2) - data engineering, data validation
325325
- 🗄️ **Database** (2) - database design, migrations
326326
- 🚨 **Operations** (4) - incident response, diagnostics, distributed debugging, observability
327327
- ⚡ **Performance** (2) - application performance, database/cloud optimization
328328
- ☁️ **Infrastructure** (5) - deployment, validation, Kubernetes, cloud, CI/CD
329329
- 🔒 **Security** (6) - scanning, compliance, backend/API, frontend/mobile, **block-no-verify** (git hook bypass guard)
330+
- 🛡️ **Governance** (1) - **protect-mcp** (Cedar policy enforcement + Ed25519 signed receipts)
330331
- 💻 **Languages** (10) - Python, JS/TS, systems, JVM, scripting, functional, embedded
331332
- 🔗 **Blockchain** (1) - smart contracts, DeFi, Web3
332333
- 💰 **Finance** (1) - quantitative trading, risk management
@@ -349,7 +350,7 @@ Uses kubernetes-architect agent with 4 specialized skills for production-grade c
349350
- **Single responsibility** - Each plugin does one thing well
350351
- **Minimal token usage** - Average 3.6 components per plugin
351352
- **Composable** - Mix and match for complex workflows
352-
- **100% coverage** - All 182 agents accessible across plugins
353+
- **100% coverage** - All 184 agents accessible across plugins
353354

354355
### Progressive Disclosure (Skills)
355356

‎docs/agent-skills.md‎

Lines changed: 8 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Agent Skills
22

3-
Agent Skills are modular packages that extend Claude's capabilities with specialized domain knowledge, following Anthropic's [Agent Skills Specification](https://github.com/anthropics/skills/blob/main/agent_skills_spec.md). This plugin ecosystem includes **149 specialized skills** across 36 plugins, enabling progressive disclosure and efficient token usage.
3+
Agent Skills are modular packages that extend Claude's capabilities with specialized domain knowledge, following Anthropic's [Agent Skills Specification](https://github.com/anthropics/skills/blob/main/agent_skills_spec.md). This plugin ecosystem includes **150 specialized skills** across 37 plugins, enabling progressive disclosure and efficient token usage.
44

55
## Overview
66

@@ -330,6 +330,12 @@ Skills provide Claude with deep expertise in specific domains without loading ev
330330
| -------------------------- | ------------------------------------------------------------------------------------------------ |
331331
| **block-no-verify-hook** | PreToolUse hook preventing AI agents from skipping git pre-commit hooks via bypass flags |
332332

333+
### Protect MCP (1 skill)
334+
335+
| Skill | Description |
336+
| ---------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
337+
| **protect-mcp-setup** | Configure Cedar policy enforcement and Ed25519 signed receipts for tool calls; example policies for research/dev/production |
338+
333339
## How Skills Work
334340

335341
### Activation
@@ -374,7 +380,7 @@ fastapi-templates skill → Supplies production-ready templates
374380

375381
## Specification Compliance
376382

377-
All 149 skills follow the [Agent Skills Specification](https://agentskills.io/specification):
383+
All 150 skills follow the [Agent Skills Specification](https://agentskills.io/specification):
378384

379385
- ✓ Required `name` field (hyphen-case)
380386
- ✓ Required `description` field with "Use when" clause

‎docs/agents.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Agent Reference
22

3-
Complete reference for all **182 specialized AI agents** organized by category with model assignments.
3+
Complete reference for all **184 specialized AI agents** organized by category with model assignments.
44

55
## Agent Categories
66

‎docs/architecture.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -36,8 +36,8 @@ This marketplace follows industry best practices with a focus on granularity, co
3636

3737
### Plugin Distribution
3838

39-
- **77 focused plugins** optimized for specific use cases
40-
- **24 clear categories** with 1-10 plugins each for easy discovery
39+
- **79 focused plugins** (77 local + 2 external via git-subdir) optimized for specific use cases
40+
- **25 clear categories** with 1-10 plugins each for easy discovery
4141
- Organized by domain:
4242
- **Development**: 4 plugins (debugging, backend, frontend, multi-platform)
4343
- **Security**: 4 plugins (scanning, compliance, backend-api, frontend-mobile)
@@ -194,7 +194,7 @@ description: What the skill does. Use when [trigger]. # Required: < 1024 chars
194194
- **Composability**: Mix and match skills across workflows
195195
- **Maintainability**: Isolated updates don't affect other skills
196196

197-
See [Agent Skills](./agent-skills.md) for complete details on the 149 skills.
197+
See [Agent Skills](./agent-skills.md) for complete details on the 150 skills.
198198

199199
## Model Configuration Strategy
200200

‎docs/plugins.md‎

Lines changed: 21 additions & 13 deletions

0 commit comments

Comments
 (0)