Observed since 20 Oct, 23:31 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
agent-synchronizer
Synchronize agent files across providers
CLI tool for syncing skills, subagents, AGENTS/CLAUDE.md and provider-specific files.
uv add agent-synchronizer
uv run agent-synchronizer <repo_root>
<repo_root>/
├── common/
│ ├── skills/
│ ├── agents/
│ └── AGENTS.md
├── claude/
│ ├── skills/
│ ├── CLAUDE.md
│ ├── settings.json
│ └── hooks/
├── codex/
│ ├── skills/
│ └── config.toml
├── cursor/
│ ├── skills/
│ └── .cursorrules
└── opencode/
├── skills/
└── opencode.jsonc
common/ holds skills, subagents, and rules shared across harnesses. Each
harness's own directory holds files specific to it (config, and for Claude
and Cursor, rules), plus an optional skills/ folder for skills specific to
that harness.
Skills may be grouped into subfolders anywhere under a skills/ directory,
at any depth — every synced harness sees them flattened, one directory per
skill. A skill in <harness>/skills/ overrides a same-named skill in
common/skills/.
We use the $HOME-based config directories for each harness.
Download counts and popularity will appear here as the collector receives them.
Declarations describe requirements; they are not a resolved dependency graph.
bdist_wheel · 6.09 KB · Python py3
sdist · 3.89 KB · Python source
Shared repository data · GitHub
Observed since 20 Oct, 23:31 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package_version:e1089ce77e68114f6fc9c4eea7dd10283d9e572d39b273bad1d08cdfc0d7cea4