Skip to content

Commit f9870eb

Browse files
avifeneshavifenesh
authored
docs: update README counts and add new plugin sections (#304)
* docs: update README with 18 plugins, 38 agents, 36 skills and add git-map, onboard, can-i-help sections * fix: add git-map, onboard, can-i-help to gen-docs static data Update COMMAND_ORDER, COMMAND_SUMMARIES, STATIC_SKILLS, CATEGORY_MAP, and PURPOSE_MAP so gen-docs generates the correct 19-command and 36-skill tables. Rename compact -> skillers-compact.
1 parent 6039d8c commit f9870eb

3 files changed

Lines changed: 145 additions & 21 deletions

File tree

‎.claude-plugin/marketplace.json‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"name": "agentsys",
3-
"description": "17 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, git intelligence, perf investigations, topic research, agent config linting, cross-tool AI consultation, structured AI debate, workflow pattern learning, and codebase onboarding",
3+
"description": "18 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, git intelligence, perf investigations, topic research, agent config linting, cross-tool AI consultation, structured AI debate, workflow pattern learning, codebase onboarding, and contributor guidance",
44
"version": "5.4.1",
55
"owner": {
66
"name": "Avi Fenesh",
@@ -138,7 +138,7 @@
138138
"source": "url",
139139
"url": "https://github.com/agent-sh/agnix.git"
140140
},
141-
"description": "Lint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 155 rules across 10+ AI tools",
141+
"description": "Lint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 342 rules across 10+ AI tools",
142142
"version": "1.0.0",
143143
"category": "development",
144144
"homepage": "https://github.com/agent-sh/agnix"

‎README.md‎

Lines changed: 118 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -8,8 +8,6 @@
88
<strong>A modular runtime and orchestration system for AI agents.</strong>
99
</p>
1010

11-
> **Renamed from `awesome-slash`** — The `awesome-` prefix implies a curated list of links, but this project is a functional software suite and runtime. Please update your installs: `npm install -g agentsys`
12-
1311
<p align="center">
1412
<a href="https://www.npmjs.com/package/agentsys"><img src="https://img.shields.io/npm/v/agentsys.svg" alt="npm version"></a>
1513
<a href="https://www.npmjs.com/package/agentsys"><img src="https://img.shields.io/npm/dm/agentsys.svg" alt="npm downloads"></a>
@@ -21,7 +19,7 @@
2119
</p>
2220

2321
<p align="center">
24-
<b>15 plugins · 35 agents · 32 skills (across all repos) · 30k lines of lib code · 3,751 tests · 5 platforms</b><br>
22+
<b>18 plugins · 38 agents · 36 skills (across all repos) · 30k lines of lib code · 3,575 tests · 5 platforms</b><br>
2523
<em>Plugins distributed as standalone repos under <a href="https://github.com/agent-sh">agent-sh</a> org — agentsys is the marketplace &amp; installer</em>
2624
</p>
2725

@@ -47,7 +45,7 @@ AI models can write code. That's not the hard part anymore. The hard part is eve
4745
4846
## What This Is
4947

50-
An agent orchestration system — 15 plugins, 35 agents, and 32 skills that compose into structured pipelines for software development. Each plugin lives in its own standalone repo under the [agent-sh](https://github.com/agent-sh) org. agentsys is the marketplace and installer that ties them together.
48+
An agent orchestration system — 18 plugins, 38 agents, and 36 skills that compose into structured pipelines for software development. Each plugin lives in its own standalone repo under the [agent-sh](https://github.com/agent-sh) org. agentsys is the marketplace and installer that ties them together.
5149

5250
Each agent has a single responsibility, a specific model assignment, and defined inputs/outputs. Pipelines enforce phase gates so agents can't skip steps. State persists across sessions so work survives interruptions.
5351

@@ -96,6 +94,9 @@ This came from testing on 1,000+ repositories.
9694
| [`/web-ctl`](#web-ctl) | Browser automation for AI agents |
9795
| [`/release`](#release) | Versioned release with ecosystem detection |
9896
| [`/skillers`](#skillers) | Workflow pattern learning and automation |
97+
| [`/git-map`](#git-map) | Git history analysis: hotspots, coupling, ownership, bus factor |
98+
| [`/onboard`](#onboard) | Codebase orientation for newcomers |
99+
| [`/can-i-help`](#can-i-help) | Match contributor skills to project needs |
99100
<!-- GEN:END:readme-commands -->
100101

101102
Each command works standalone. Together, they compose into end-to-end pipelines.
@@ -105,18 +106,20 @@ Each command works standalone. Together, they compose into end-to-end pipelines.
105106
## Skills
106107

107108
<!-- GEN:START:readme-skills -->
108-
32 skills included across the plugins:
109+
36 skills included across the plugins:
109110

110111
| Category | Skills |
111112
|----------|--------|
112113
| **Workflow** | `discover-tasks`, `orchestrate-review`, `validate-delivery` |
113114
| **Enhancement** | `enhance-agent-prompts`, `enhance-claude-memory`, `enhance-cross-file`, `enhance-docs`, `enhance-hooks`, `enhance-orchestrator`, `enhance-plugins`, `enhance-prompts`, `enhance-skills` |
114115
| **Performance** | `baseline`, `benchmark`, `code-paths`, `investigation-logger`, `perf-analyzer`, `profile`, `theory-gatherer`, `theory-tester` |
115116
| **Cleanup** | `deslop`, `sync-docs` |
116-
| **AI Collaboration** | `compact`, `consult`, `debate`, `learn`, `recommend` |
117+
| **Code Review** | `audit-project` |
118+
| **AI Collaboration** | `consult`, `debate`, `learn`, `recommend`, `skillers-compact` |
119+
| **Onboarding** | `can-i-help`, `onboard` |
117120
| **Web** | `web-auth`, `web-browse` |
118121
| **Release** | `release` |
119-
| **Analysis** | `drift-analysis`, `repo-mapping` |
122+
| **Analysis** | `drift-analysis`, `git-mapping`, `repo-mapping` |
120123
<!-- GEN:END:readme-skills -->
121124

122125
Skills are the reusable implementation units. Agents invoke skills; commands orchestrate agents. When you install a plugin, its skills become available to all agents in that session.
@@ -128,8 +131,8 @@ Skills are the reusable implementation units. Agents invoke skills; commands orc
128131
| Section | What's there |
129132
|---------|--------------|
130133
| [The Approach](#the-approach) | Why it's built this way |
131-
| [Commands](#commands) | All 16 commands overview |
132-
| [Skills](#skills) | 32 skills across plugins |
134+
| [Commands](#commands) | All 19 commands overview |
135+
| [Skills](#skills) | 36 skills across plugins |
133136
| [Command Details](#command-details) | Deep dive into each command |
134137
| [How Commands Work Together](#how-commands-work-together) | Standalone vs integrated |
135138
| [Design Philosophy](#design-philosophy) | The thinking behind the architecture |
@@ -834,7 +837,111 @@ No per-turn overhead - it reads transcripts that Claude Code already saves.
834837

835838
**Agents:** skillers-compactor (sonnet), skillers-recommender (opus)
836839

837-
**Skills:** compact, recommend
840+
**Skills:** skillers-compact, recommend
841+
842+
---
843+
844+
### /git-map
845+
846+
**Purpose:** Analyze git history to surface hotspots, coupling, ownership, bus factor, bugspots, area health, and AI attribution.
847+
848+
**How it works:**
849+
850+
The plugin wraps the [agent-analyzer](https://github.com/agent-sh/agent-analyzer) Rust binary. Run `init` once to scan git history and cache the result as `repo-intel.json`. Then run queries instantly.
851+
852+
**21 query types:**
853+
854+
| Category | Queries |
855+
|----------|---------|
856+
| Activity | `hotspots`, `coldspots`, `file-history` |
857+
| Quality | `bugspots`, `test-gaps`, `diff-risk` |
858+
| People | `ownership`, `contributors`, `bus-factor` |
859+
| Coupling | `coupling` |
860+
| Standards | `norms`, `conventions` |
861+
| Health | `areas`, `health`, `release-info` |
862+
| AI | `ai-ratio`, `recent-ai` |
863+
| Guidance | `onboard`, `can-i-help` |
864+
| Docs | `doc-drift` |
865+
866+
**9 plugins consume git-map data automatically** - deslop, sync-docs, drift-detect, audit-project, next-task, enhance, ship, onboard, can-i-help.
867+
868+
**Usage:**
869+
870+
```bash
871+
/git-map init # First-time scan
872+
/git-map update # Add new commits
873+
/git-map query hotspots # Most active files
874+
/git-map query ownership src/ # Who owns a path
875+
/git-map query bus-factor # Knowledge risk
876+
```
877+
878+
[Full query reference ->](https://github.com/agent-sh/git-map)
879+
880+
---
881+
882+
### /onboard
883+
884+
**Purpose:** Get oriented in any codebase in under 3 minutes.
885+
886+
**What happens when you run it:**
887+
888+
1. **Collect** - Pure JavaScript scans manifest, structure, README, CI, git, repo-intel, repo-map (no LLM tokens)
889+
2. **Synthesize** - Opus agent produces a structured overview: tech stack, key files, active areas, conventions
890+
3. **Guide** - Interactive Q&A: ask about specific files, areas, or patterns
891+
892+
**Depth levels:**
893+
894+
| Level | Time | Data |
895+
|-------|------|------|
896+
| quick | ~2s | Manifest + README + structure |
897+
| normal | ~5s | + CLAUDE.md + CI + repo-intel |
898+
| deep | ~15s | + repo-map AST symbols |
899+
900+
**Usage:**
901+
902+
```bash
903+
/onboard # Current repo
904+
/onboard /path/to/repo # Specific repo
905+
/onboard --depth=deep # Include AST data
906+
```
907+
908+
**Agent:** onboard-agent (opus model)
909+
910+
[Full documentation ->](https://github.com/agent-sh/onboard)
911+
912+
---
913+
914+
### /can-i-help
915+
916+
**Purpose:** Match a contributor's skills to specific areas where they can help.
917+
918+
**What happens when you run it:**
919+
920+
1. **Collect** - Gathers project data + contributor signals (test gaps, doc drift, bugspots, good-first areas, open issues)
921+
2. **Match** - Opus agent asks about developer background and matches skills to project needs
922+
3. **Guide** - For each recommendation: reads code, explains what needs doing, gives a concrete first step
923+
924+
**Matching:**
925+
926+
| Developer profile | Gets recommended |
927+
|-------------------|------------------|
928+
| New to stack | Good-first areas with clear patterns |
929+
| Experienced | Hard problems in pain-point areas |
930+
| Test-focused | Test gaps in frequently-changed files |
931+
| Bug-focused | Bugspot files + relevant open issues |
932+
| Docs-focused | Stale documentation with code examples |
933+
934+
**Usage:**
935+
936+
```bash
937+
/can-i-help # Current repo
938+
/can-i-help /path/to/repo # Specific repo
939+
/can-i-help --depth=deep # Include AST data
940+
```
941+
942+
**Agent:** can-i-help-agent (opus model)
943+
944+
[Full documentation ->](https://github.com/agent-sh/can-i-help)
838945

839946
---
840947

@@ -1041,7 +1148,7 @@ The system is built on research, not guesswork.
10411148
- Instruction following reliability
10421149

10431150
**Testing:**
1044-
- 3,751 tests passing
1151+
- 3,575 tests passing
10451152
- Drift-detect validated on 1,000+ repositories
10461153
- E2E workflow testing across all commands
10471154
- Cross-platform validation (Claude Code, OpenCode, Codex CLI, Cursor, Kiro)

‎scripts/generate-docs.js‎

Lines changed: 25 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -59,7 +59,11 @@ const CATEGORY_MAP = {
5959
'debate': 'AI Collaboration',
6060
'skillers': 'AI Collaboration',
6161
'web-ctl': 'Web',
62-
'ship': 'Release'
62+
'ship': 'Release',
63+
'git-map': 'Analysis',
64+
'onboard': 'Onboarding',
65+
'can-i-help': 'Onboarding',
66+
'audit-project': 'Code Review'
6367
};
6468

6569
// Static skill definitions for cross-repo plugins (not discoverable locally)
@@ -94,8 +98,12 @@ const STATIC_SKILLS = [
9498
{ plugin: 'web-ctl', name: 'web-auth' },
9599
{ plugin: 'web-ctl', name: 'web-browse' },
96100
{ plugin: 'ship', name: 'release' },
97-
{ plugin: 'skillers', name: 'compact' },
98-
{ plugin: 'skillers', name: 'recommend' }
101+
{ plugin: 'skillers', name: 'skillers-compact' },
102+
{ plugin: 'skillers', name: 'recommend' },
103+
{ plugin: 'git-map', name: 'git-mapping' },
104+
{ plugin: 'onboard', name: 'onboard' },
105+
{ plugin: 'can-i-help', name: 'can-i-help' },
106+
{ plugin: 'audit-project', name: 'audit-project' }
99107
];
100108

101109
// Purpose mapping for architecture table
@@ -112,7 +120,12 @@ const PURPOSE_MAP = {
112120
'learn': 'Topic research and learning guides',
113121
'agnix': 'Agent config linting',
114122
'consult': 'Cross-tool AI consultation',
115-
'debate': 'Multi-perspective debate analysis'
123+
'debate': 'Multi-perspective debate analysis',
124+
'web-ctl': 'Browser automation for AI agents',
125+
'skillers': 'Workflow pattern learning',
126+
'git-map': 'Git history analysis',
127+
'onboard': 'Codebase onboarding',
128+
'can-i-help': 'Contributor guidance'
116129
};
117130

118131
// ---------------------------------------------------------------------------
@@ -162,7 +175,8 @@ function generateCommandsTable(commands) {
162175
'next-task', 'agnix', 'ship', 'deslop', 'perf',
163176
'drift-detect', 'audit-project', 'enhance',
164177
'repo-map', 'sync-docs', 'learn', 'consult',
165-
'debate', 'web-ctl', 'release', 'skillers'
178+
'debate', 'web-ctl', 'release', 'skillers',
179+
'git-map', 'onboard', 'can-i-help'
166180
];
167181

168182
// Command descriptions for the table (short, human-written summaries)
@@ -182,7 +196,10 @@ function generateCommandsTable(commands) {
182196
'debate': 'Structured debate between AI tools',
183197
'web-ctl': 'Browser automation for AI agents',
184198
'release': 'Versioned release with ecosystem detection',
185-
'skillers': 'Workflow pattern learning and automation'
199+
'skillers': 'Workflow pattern learning and automation',
200+
'git-map': 'Git history analysis: hotspots, coupling, ownership, bus factor',
201+
'onboard': 'Codebase orientation for newcomers',
202+
'can-i-help': 'Match contributor skills to project needs'
186203
};
187204

188205
// Build lookup of discovered commands
@@ -239,8 +256,8 @@ function generateSkillsTable(skills) {
239256
// Defined category order
240257
const categoryOrder = [
241258
'Workflow', 'Enhancement', 'Performance', 'Cleanup',
242-
'AI Collaboration', 'Web', 'Release', 'Analysis',
243-
'Linting', 'Other'
259+
'Code Review', 'AI Collaboration', 'Onboarding',
260+
'Web', 'Release', 'Analysis', 'Linting', 'Other'
244261
];
245262

246263
const lines = [

0 commit comments

Comments
 (0)