new-agent
Skill0 starsChanged 5 months agoMITView on GitHub
Scaffold a new agent under agents/<name>/ following this repo's run.sh + (launchd | CLI) pattern. Use when the user says "新加一个 agent" or "/new-agent <name>".
7 other projects use a version of this.
Adopted by
Most recently taken up by
- Sagargupta16/foremantheir own version, first seen Nov 16, 2026
- AcKeskin/contexturetheir own version, first seen Nov 1, 2026
- jnotsknab/mux-swarmtheir own version, first seen Oct 11, 2026
- iDiagoValeta/claude-code-agentstheir own version, first seen Oct 8, 2026
- hcussi/claude-code-toolkittheir own version, first seen Jul 2, 2026
- InfiniteRoomLabs/agent-opstheir own version, first seen Jun 23, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- jnotsknab/mux-swarm★ 9same name
- AcKeskin/contexture★ 2same name
- hcussi/claude-code-toolkit★ 1same name
- iDiagoValeta/claude-code-agents★ 1same name
- InfiniteRoomLabs/agent-ops★ 1same name
- Sagargupta16/foreman★ 1same name
- TheLatentSpaceLab/Qubito★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-statusSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 55
After scaffolding, print the next steps to the user:
- Very specific: line 57
Add dependencies to requirements.txt
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
new-agent
Scaffold a new agent directory matching this repo's conventions.
Usage
/new-agent <name> [--type=scheduled|cli]scheduled(default): launchd-driven with.stamps/<slot>dedupe and one-shot retry. Pattern fromagents/financial_news/.cli: manual CLI invocation, run.sh passes"$@"through. Pattern fromagents/paper_reader/.
Procedure
- Validate
<name>is snake_case andagents/<name>/does not exist. If exists, abort with error. - Resolve
--type(defaultscheduled). - Create
agents/<name>/and inside it:CLAUDE.md— agent-local instructions. Use templatetemplates/agent.CLAUDE.md, replace<NAME>with<name>.requirements.txt— empty by default; add deps if user specified them in the request.<name>.py— main script fromtemplates/skeleton.py, replace<NAME>token.run.sh— copy fromtemplates/scheduled.run.shortemplates/cli.run.sh, replace<NAME>and<AGENT_DIR>. Thenchmod +x.
- For
scheduledonly: emit (do NOT write) a~/Library/LaunchAgents/com.<name>.<slot>.plisttemplate snippet inline in the chat. Ask the user for the slot name and schedule first; do not pre-fill. Tell the user the reload commands after they write the plist. - Update root
CLAUDE.mdagents table — append a new row. Use the same column structure as existing rows. - Do NOT auto-load any launchd job — that's the user's call.
Conventions to respect
- Python interpreter:
/Library/Frameworks/Python.framework/Versions/3.14/bin/python3(overridable via$PYTHON) - All
run.share self-locating (no hardcoded absolute paths) and inject only the keys they need:SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)" eval "$("$REPO_ROOT/tools/load_env.sh" KEY1 KEY2 ...)" - Logs:
agents/<name>/<name>.log.run.shis responsible for tail-truncating to 500 lines (scheduled template does this). - Stamps:
.stamps/<slot>at repo root (NOT~/.stamps/). - Scheduled
run.shfirst arg is the slot name, written to.stamps/only on success. - CLI
run.shtakes no slot — pure passthrough.
Templates
See .claude/skills/new-agent/templates/:
scheduled.run.shcli.run.shskeleton.pyagent.CLAUDE.md
After scaffolding, print the next steps to the user:
- Fill in business logic in
<name>.py - Add dependencies to
requirements.txt - (scheduled) Write the plist, then
launchctl load - (scheduled) Test manually:
agents/<name>/run.sh <slot>
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

