You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
docs: rebrand theme from "workflow automation toolkit" to "agent runtime & orchestration system"
Update all user-facing messaging to reflect AgentSys identity:
- README hero: "A modular runtime and orchestration system for AI agents"
- What This Is: rewritten from "collection of tools" to system description
- Site meta, OG tags, hero, footer tagline
- docs/README.md intro
- UX spec, CSS tokens, OG image template
Copy file name to clipboardExpand all lines: README.md
+9-11Lines changed: 9 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,7 +5,7 @@
5
5
<h1align="center">AgentSys</h1>
6
6
7
7
<palign="center">
8
-
<strong>Automate the entire dev workflow. Not just the coding.</strong>
8
+
<strong>A modular runtime and orchestration system for AI agents.</strong>
9
9
</p>
10
10
11
11
<palign="center">
@@ -36,20 +36,18 @@
36
36
37
37
---
38
38
39
-
AI models can write code. That's not the hard part anymore. The hard part is everything else—picking what to work on, managing branches, reviewing output, cleaning up artifacts, handling CI, addressing comments, deploying. **AgentSys automates the entire workflow**, not just the coding.
39
+
AI models can write code. That's not the hard part anymore. The hard part is everything around it — task selection, branch management, code review, artifact cleanup, CI, PR comments, deployment. **AgentSys is the runtime that orchestrates agents to handle all of it** — structured pipelines, gated phases, specialized agents, and persistent state that survives session boundaries.
40
40
41
41
---
42
42
> Building custom skills, agents, hooks, or MCP tools? [agnix](https://github.com/avifenesh/agnix) is the CLI + LSP linter that catches config errors before they fail silently - real-time IDE validation, auto suggestions, auto-fix, and 155 rules for Cursor, Claude Code, Cline, Copilot, Codex, Windsurf, and more.
43
43
44
44
## What This Is
45
45
46
-
Production-ready skills, agents, and commands for Claude Code, OpenCode, and Codex CLI.
46
+
An agent orchestration system — 12 plugins, 41 agents, and 27 skills that compose into structured pipelines for software development.
47
47
48
-
Install the plugins → get the skills → your agents become more capable. Each piece was built to work with the others. The whole system is E2E tested.
48
+
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.
49
49
50
-
From messy project to clean codebase. From drifted plan to focused execution. From task to merged PR.
51
-
52
-
**Works with:** Claude Code · OpenCode · Codex CLI
50
+
The system runs on Claude Code, OpenCode, and Codex CLI. Install the plugins, get the runtime.
53
51
54
52
---
55
53
@@ -92,7 +90,7 @@ This came from testing on 1,000+ repositories.
92
90
|[`/consult`](#consult)| Consult another AI CLI tool for a second opinion. Use when you want to cross-check ideas, get alternative approaches, or validate decisions with Gemini, Codex, Claude, OpenCode, or Copilot. |
93
91
<!-- GEN:END:readme-commands -->
94
92
95
-
Each command works standalone. Together, they form complete workflows.
93
+
Each command works standalone. Together, they compose into end-to-end pipelines.
96
94
97
95
---
98
96
@@ -113,7 +111,7 @@ Each command works standalone. Together, they form complete workflows.
113
111
|**Linting**|`agnix:agnix`|
114
112
<!-- GEN:END:readme-skills -->
115
113
116
-
Skills give your agents specialized capabilities. When you install a plugin, its skills become available to all agents in that session.
114
+
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.
117
115
118
116
---
119
117
@@ -706,7 +704,7 @@ The workflow tracks state so you can resume from any point.
706
704
## Design Philosophy
707
705
708
706
<details>
709
-
<summary><strong>Why build this? What's the thinking?</strong> (click to expand)</summary>
707
+
<summary><strong>Architecture decisions and trade-offs</strong> (click to expand)</summary>
Copy file name to clipboardExpand all lines: docs/README.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
# Documentation
2
2
3
-
AI models can write code. The bottleneck is everything else—picking tasks, managing branches, reviewing output, handling CI, addressing comments, deploying. These docs show how AgentSys automates the full workflow, not just the coding part.
3
+
AgentSys is a modular runtime and orchestration system for AI agents. These docs cover the architecture, commands, and workflows — how agents compose into pipelines, how phases gate execution, and how state persists across sessions.
4
4
5
5
**New here?** Start with [USAGE.md](./USAGE.md) to see commands in action.
Copy file name to clipboardExpand all lines: site/content.json
+3-3Lines changed: 3 additions & 3 deletions
Original file line number
Diff line number
Diff line change
@@ -1,7 +1,7 @@
1
1
{
2
2
"meta": {
3
3
"title": "agentsys",
4
-
"description": "Production-ready skills, agents, and commands for Claude Code, OpenCode, and Codex CLI. 12 plugins that automate the entire AI development workflow, not just the coding.",
4
+
"description": "A modular runtime and orchestration system for AI agents. 12 plugins, 41 agents, 27 skills — structured pipelines for Claude Code, OpenCode, and Codex CLI.",
5
5
"url": "https://avifenesh.github.io/agentsys",
6
6
"repo": "https://github.com/avifenesh/agentsys",
7
7
"npm": "https://www.npmjs.com/package/agentsys",
@@ -10,8 +10,8 @@
10
10
"author_url": "https://github.com/avifenesh"
11
11
},
12
12
"hero": {
13
-
"title": "Automate the entire workflow, not just the coding",
14
-
"subtitle": "AI models can write code. That's not the hard part anymore. The hard part is everything else -- picking tasks, managing branches, reviewing output, handling CI, addressing comments, deploying. AgentSys automates all of it.",
13
+
"title": "A modular runtime and orchestration system for AI agents",
14
+
"subtitle": "AI models can write code. That's not the hard part anymore. The hard part is everything around it -- task selection, branch management, code review, artifact cleanup, CI, deployment. AgentSys is the runtime that orchestrates agents to handle all of it.",
<title>AgentSys - AI Workflow Automation Toolkit</title>
7
-
<metaname="description" content="11 plugins, 40 agents, 26 skills. Automate the entire dev workflow from task selection to merged PR. Works with Claude Code, OpenCode, and Codex CLI.">
6
+
<title>AgentSys - Agent Runtime & Orchestration System</title>
7
+
<metaname="description" content="A modular runtime and orchestration system for AI agents. 12 plugins, 41 agents, 27 skills — structured pipelines for Claude Code, OpenCode, and Codex CLI.">
- "MIT License" in 13px, `rgba(255, 255, 255, 0.3)`
450
450
451
451
**Column 2 (center):** Links
@@ -649,8 +649,8 @@ This disables:
649
649
650
650
### Head Content
651
651
```html
652
-
<title>AgentSys - AI Workflow Automation Toolkit</title>
653
-
<metaname="description"content="11 plugins, 40 agents, 26 skills. Automate the entire dev workflow from task selection to merged PR. Works with Claude Code, OpenCode, and Codex CLI.">
652
+
<title>AgentSys - Agent Runtime & Orchestration System</title>
653
+
<metaname="description"content="A modular runtime and orchestration system for AI agents. 12 plugins, 41 agents, 27 skills — structured pipelines for Claude Code, OpenCode, and Codex CLI.">
0 commit comments