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
Copy file name to clipboardExpand all lines: README.md
+16-4Lines changed: 16 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,11 +1,13 @@
1
1
# sync-agents
2
2
3
-
One set of agent rules to rule them all. `sync-agents` keeps your AI coding agent configurations in a single `.agents/` directory and syncs them to agent-specific directories (`.claude/`, `.windsurf/`) via symlinks. This ensures all agents follow the same rules, skills, and workflows without duplicating files.
3
+
One set of agent rules to rule them all. `sync-agents` keeps your AI coding agent configurations in a single `.agents/` directory and syncs them to agent-specific directories (`.claude/`, `.windsurf/`, `.cursor/`, `.github/copilot/`) via symlinks. This ensures all agents follow the same rules, skills, and workflows without duplicating files.
4
4
5
5
AGENTS.md serves as an auto-generated index of everything in `.agents/` and is symlinked to CLAUDE.md for Claude compatibility.
Running `sync-agents sync` creates symlinks from `.agents/` subdirectories into `.claude/`and `.windsurf/`. Any changes to `.agents/` are automatically reflected in the target directories because they are symlinks, not copies.
49
+
Running `sync-agents sync` creates symlinks from `.agents/` subdirectories into `.claude/`, `.windsurf/`, `.cursor/`, and `.github/copilot/`. Any changes to `.agents/` are automatically reflected in the target directories because they are symlinks, not copies.
41
50
42
51
AGENTS.md is also symlinked to CLAUDE.md so that Claude reads the index natively.
43
52
@@ -50,7 +59,10 @@ AGENTS.md is also symlinked to CLAUDE.md so that Claude reads the index natively
50
59
| Command | Description |
51
60
|---|---|
52
61
|`init`| Initialize the `.agents/` directory structure with `rules/`, `skills/`, `workflows/`, `STATE.md`, and generate `AGENTS.md`|
53
-
|`sync`| Create symlinks from `.agents/` into `.claude/` and `.windsurf/`, and symlink `AGENTS.md` to `CLAUDE.md`|
62
+
|`sync`| Create symlinks from `.agents/` into all target directories, and symlink `AGENTS.md` to `CLAUDE.md`|
63
+
|`watch`| Watch `.agents/` for changes and auto-regenerate `AGENTS.md`|
64
+
|`import <url>`| Import a rule/skill/workflow from a URL |
65
+
|`hook`| Install a pre-commit git hook for auto-sync |
54
66
|`status`| Show the current sync status of all targets and symlinks |
55
67
|`add <type> <name>`| Add a new rule, skill, or workflow from a template (type is `rule`, `skill`, or `workflow`) |
56
68
|`index`| Regenerate `AGENTS.md` by scanning the contents of `.agents/`|
@@ -63,7 +75,7 @@ AGENTS.md is also symlinked to CLAUDE.md so that Claude reads the index natively
63
75
|`-h`, `--help`| Show help message |
64
76
|`-v`, `--version`| Show version |
65
77
|`-d`, `--dir <path>`| Set project root directory (default: current directory) |
66
-
|`--targets <list>`| Comma-separated list of sync targets (default: `claude,windsurf`) |
78
+
|`--targets <list>`| Comma-separated list of sync targets (default: `claude,windsurf,cursor,copilot`) |
67
79
|`--dry-run`| Show what would be done without making changes |
68
80
|`--force`| Overwrite existing files and symlinks |
This is the state template for sync-agents. It is used to define the state of the agent and its environment. The state markdown file itself is a human readble source for the agent to read and understand its current situation. It can be used to track the progress of the agent, identify any issues or challenges it may be facing, and provide a clear overview of its goals and objectives. The state is an important tool for the agent to use in order to make informed decisions and take appropriate actions to achieve its goals. By maintaining an up-to-date state, the agent can continuously learn and evolve, becoming more effective and efficient in its tasks.
9
-
10
-
The goal is to improve the performance of the agent by providing it with a clear and structured representation of its current situation. This allows the agent to make informed decisions and take appropriate actions to achieve its goals. The state is also used to track the progress of the agent and identify any issues or areas for improvement. By maintaining an up-to-date state, the agent can continuously learn and evolve, becoming more effective and efficient in its xtasks.
11
-
12
-
## TRACKING Agent State
13
-
14
-
Every state tracking will begin with a header of `### YYYYMMDDHHMMSS STATE: <STATE_NAME or OBJECTIVE` followed by a description of the state, any relevant information about the agent's performance, issues, or updates, and any actions taken or planned to address the current state. This format allows for easy tracking and monitoring of the agent's progress over time, as well as providing a clear record of the agent's history and development. By maintaining a detailed and organized state history, the agent can learn from past experiences and make informed decisions to improve its performance in the future.>
15
-
16
-
The format above will be written below the `## STATE HISTORY BELOW` header in the STATE.md file. This allows for easy tracking and monitoring of the agent's progress over time, as well as providing a clear record of the agent's history and development. By maintaining a detailed and organized state history, the agent can learn from past experiences and make informed decisions to improve its performance in the future.
17
-
18
-
## Formatted Agent State
7
+
Track project progress, current objectives, and resumption context.
8
+
Update this file regularly so agents can pick up where they left off.
19
9
20
-
The formatted agent state will be a structured representation of the agent's current situation, including its goals, objectives, performance metrics, and any relevant information about its environment. This formatted state will be used by the agent to make informed decisions and take appropriate actions to achieve its goals. By maintaining an up-to-date and well-structured formatted state, the agent can continuously learn and evolve, becoming more effective and efficient in its tasks. The formatted state will also be used to track the progress of the agent and identify any issues or areas for improvement, allowing for continuous optimization of the agent's performance.
10
+
## Format
21
11
22
-
Example:
12
+
### YYYYMMDDHHMMSS STATE: <objective>
23
13
24
-
The state is structured as follows:
25
-
26
-
```json
27
-
{
28
-
"agent_name": "string",
29
-
"goals": ["string"],
30
-
"skills": ["string"],
31
-
"workflows": ["string"],
32
-
"issues": ["string"],
33
-
"last_updated": "timestamp"
34
-
}
35
-
```
36
-
to `.agents/state.json`
14
+
Description of current state, progress, blockers, and next steps.
0 commit comments