mirror of
https://github.com/wshobson/agents.git
synced 2026-09-14 18:04:20 +08:00
* docs: synchronize plugin/agent/skill counts (closes #517)
Live counts are 80 local plugins (81 incl. external git-subdir),
185 agents, 153 skills, 100 commands. Six docs were stale:
- marketplace.json metadata.description: 79/184/150 -> 80/185/153
- docs/plugins.md: 78 plugins (77 local) -> 81 plugins (80 local)
- docs/agents.md: 184 agents -> 185
- docs/agent-skills.md: 150 skills / 37 plugins -> 153 skills / 40 plugins
- docs/architecture.md: 79 plugins, 99 agents, 150 skills -> 81/185/153
- docs/usage.md: 150 skills, 79 plugins -> 153 skills, 80 plugins
Companion to 159ce68 which fixed README.md and CLAUDE.md.
* docs: fix model distribution sums + plugins.md framing
CodeRabbit follow-up on PR #522:
- docs/agents.md model distribution table summed to 99 (42+39+18) but
the header now says 185 agents. Recounted from frontmatter:
opus 54, sonnet 62, haiku 20, inherit 49 = 185. Added the missing
Inherit row.
- docs/architecture.md model distribution table had the same stale
42/39/18 sum; updated to 54/62/20/49 and renamed "Two-Tier" to
"Four-Tier" since Inherit is now load-bearing.
- docs/architecture.md "average plugin size: 3.4 components" → 5.5,
matching (185 + 153 + 100) / 80.
- docs/plugins.md headline reframed from "81 ... 80 local + 1 external"
to "80 ... plus 1 externally-hosted" to match the GEMINI.md
path-based rule (catalog headline counts local plugins).
This commit is contained in:
@@ -6,7 +6,7 @@
|
||||
"url": "https://github.com/wshobson"
|
||||
},
|
||||
"metadata": {
|
||||
"description": "Production-ready workflow orchestration with 79 focused plugins, 184 specialized agents, and 150 skills - optimized for granular installation and minimal token usage",
|
||||
"description": "Production-ready workflow orchestration with 80 focused plugins, 185 specialized agents, and 153 skills - optimized for granular installation and minimal token usage",
|
||||
"version": "1.6.0"
|
||||
},
|
||||
"plugins": [
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Agent Skills
|
||||
|
||||
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.
|
||||
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 **153 specialized skills** across 40 plugins, enabling progressive disclosure and efficient token usage.
|
||||
|
||||
## Overview
|
||||
|
||||
@@ -380,7 +380,7 @@ fastapi-templates skill → Supplies production-ready templates
|
||||
|
||||
## Specification Compliance
|
||||
|
||||
All 150 skills follow the [Agent Skills Specification](https://agentskills.io/specification):
|
||||
All 153 skills follow the [Agent Skills Specification](https://agentskills.io/specification):
|
||||
|
||||
- ✓ Required `name` field (hyphen-case)
|
||||
- ✓ Required `description` field with "Use when" clause
|
||||
|
||||
+7
-6
@@ -1,6 +1,6 @@
|
||||
# Agent Reference
|
||||
|
||||
Complete reference for all **184 specialized AI agents** organized by category with model assignments.
|
||||
Complete reference for all **185 specialized AI agents** organized by category with model assignments.
|
||||
|
||||
## Agent Categories
|
||||
|
||||
@@ -227,11 +227,12 @@ Agents are assigned to specific Claude models based on task complexity and compu
|
||||
|
||||
### Model Distribution Summary
|
||||
|
||||
| Model | Agent Count | Use Case |
|
||||
| ------ | ----------- | --------------------------------------------------------------- |
|
||||
| Opus | 42 | Critical architecture, security, code review, production coding |
|
||||
| Sonnet | 39 | Complex tasks, support with intelligence |
|
||||
| Haiku | 18 | Fast operational tasks |
|
||||
| Model | Agent Count | Use Case |
|
||||
| ------- | ----------- | --------------------------------------------------------------- |
|
||||
| Opus | 54 | Critical architecture, security, code review, production coding |
|
||||
| Sonnet | 62 | Complex tasks, support with intelligence |
|
||||
| Haiku | 20 | Fast operational tasks |
|
||||
| Inherit | 49 | Complex tasks where the user chooses the model at runtime |
|
||||
|
||||
### Model Selection Criteria
|
||||
|
||||
|
||||
+14
-13
@@ -8,7 +8,7 @@ This marketplace follows industry best practices with a focus on granularity, co
|
||||
|
||||
- Each plugin does **one thing well** (Unix philosophy)
|
||||
- Clear, focused purposes (describable in 5-10 words)
|
||||
- Average plugin size: **3.4 components** (follows Anthropic's 2-8 pattern)
|
||||
- Average plugin size: **5.5 components** (follows Anthropic's 2-8 pattern)
|
||||
- **Zero bloated plugins** - all plugins focused and purposeful
|
||||
|
||||
### Composability Over Bundling
|
||||
@@ -36,7 +36,7 @@ This marketplace follows industry best practices with a focus on granularity, co
|
||||
|
||||
### Plugin Distribution
|
||||
|
||||
- **79 focused plugins** (77 local + 2 external via git-subdir) optimized for specific use cases
|
||||
- **81 focused plugins** (80 local + 1 external via git-subdir) optimized for specific use cases
|
||||
- **25 clear categories** with 1-10 plugins each for easy discovery
|
||||
- Organized by domain:
|
||||
- **Development**: 4 plugins (debugging, backend, frontend, multi-platform)
|
||||
@@ -48,7 +48,7 @@ This marketplace follows industry best practices with a focus on granularity, co
|
||||
|
||||
### Component Breakdown
|
||||
|
||||
**99 Specialized Agents**
|
||||
**185 Specialized Agents**
|
||||
|
||||
- Domain experts with deep knowledge
|
||||
- Organized across architecture, languages, infrastructure, quality, data/AI, documentation, business, and SEO
|
||||
@@ -194,19 +194,20 @@ description: What the skill does. Use when [trigger]. # Required: < 1024 chars
|
||||
- **Composability**: Mix and match skills across workflows
|
||||
- **Maintainability**: Isolated updates don't affect other skills
|
||||
|
||||
See [Agent Skills](./agent-skills.md) for complete details on the 150 skills.
|
||||
See [Agent Skills](./agent-skills.md) for complete details on the 153 skills.
|
||||
|
||||
## Model Configuration Strategy
|
||||
|
||||
### Two-Tier Architecture
|
||||
### Four-Tier Architecture
|
||||
|
||||
The system uses Claude Opus and Sonnet models strategically:
|
||||
The system uses Claude Opus, Sonnet, Haiku, and Inherit assignments strategically:
|
||||
|
||||
| Model | Count | Use Case |
|
||||
| ------ | --------- | -------------------------------------------- |
|
||||
| Opus | 42 agents | Critical architecture, security, code review |
|
||||
| Sonnet | 39 agents | Complex tasks, support with intelligence |
|
||||
| Haiku | 18 agents | Fast operational tasks |
|
||||
| Model | Count | Use Case |
|
||||
| ------- | --------- | -------------------------------------------- |
|
||||
| Opus | 54 agents | Critical architecture, security, code review |
|
||||
| Sonnet | 62 agents | Complex tasks, support with intelligence |
|
||||
| Haiku | 20 agents | Fast operational tasks |
|
||||
| Inherit | 49 agents | Defers model choice to the user at runtime |
|
||||
|
||||
### Selection Criteria
|
||||
|
||||
@@ -261,8 +262,8 @@ code-reviewer (Sonnet) validates architecture
|
||||
### Component Coverage
|
||||
|
||||
- **100% agent coverage** - all plugins include at least one agent
|
||||
- **100% component availability** - all 99 agents accessible across plugins
|
||||
- **Efficient distribution** - 3.4 components per plugin average
|
||||
- **100% component availability** - all 185 agents accessible across plugins
|
||||
- **Efficient distribution** - 5.5 components per plugin average
|
||||
|
||||
### Discoverability
|
||||
|
||||
|
||||
+2
-2
@@ -1,6 +1,6 @@
|
||||
# Complete Plugin Reference
|
||||
|
||||
Browse all **78 focused, single-purpose plugins** organized by category. 77 plugins ship from this repo; 1 additional plugin (`qa-orchestra`) is hosted in an external repository and distributed via a `git-subdir` marketplace entry.
|
||||
Browse all **80 focused, single-purpose plugins** organized by category, plus 1 externally-hosted plugin (`qa-orchestra`) distributed via a `git-subdir` marketplace entry — 81 plugins total.
|
||||
|
||||
> 💡 **Also recommended:** [Pensyve](https://github.com/major7apps/pensyve) — universal memory runtime for Claude Code. Distributed from its own marketplace (`major7apps/pensyve`) so updates ship directly from the source. Install with `/plugin marketplace add major7apps/pensyve` then `/plugin install pensyve@major7apps-pensyve`.
|
||||
|
||||
@@ -382,7 +382,7 @@ Each installed plugin loads **only its specific agents and commands** into Claud
|
||||
|
||||
## See Also
|
||||
|
||||
- [Agent Skills](./agent-skills.md) - 150 specialized skills across plugins
|
||||
- [Agent Skills](./agent-skills.md) - 153 specialized skills across plugins
|
||||
- [Agent Reference](./agents.md) - Complete agent catalog
|
||||
- [Usage Guide](./usage.md) - Commands and workflows
|
||||
- [Architecture](./architecture.md) - Design principles
|
||||
|
||||
+2
-2
@@ -385,11 +385,11 @@ User: "Implement Kubernetes deployment with Helm"
|
||||
→ Result: Production-grade K8s manifests with Helm charts
|
||||
```
|
||||
|
||||
See [Agent Skills](./agent-skills.md) for details on the 150 specialized skills.
|
||||
See [Agent Skills](./agent-skills.md) for details on the 153 specialized skills.
|
||||
|
||||
## See Also
|
||||
|
||||
- [Agent Skills](./agent-skills.md) - Specialized knowledge packages
|
||||
- [Agent Reference](./agents.md) - Complete agent catalog
|
||||
- [Plugin Reference](./plugins.md) - All 79 plugins
|
||||
- [Plugin Reference](./plugins.md) - All 80 plugins
|
||||
- [Architecture](./architecture.md) - Design principles
|
||||
|
||||
Reference in New Issue
Block a user