orca-multiagent-kit / templates
AGENTS.md0 starsChanged 5 days agoMITView on GitHub
In this repository8 other files it gives its agents.
- core/AGENTS.mdAGENTS.md
- templates/CLAUDE.mdCLAUDE.md
- csr-auditSkill
- csr-gateSkill
- csr-stackSkill
- kit-initSkill
- orcaSkill
- speckit-orca-implementSkill
The file
We found no rules to list in this file: it reads as prose or reference rather than instructions.
Files
<!-- AGENTS:BEGIN project v1.0.0 -->Reglas del proyecto
- Lee
./STACK.mdantes de la primera edición de cada sesión: versiones, comandos y límites. Comandos: solo los deSTACK.md§3; si falta uno, dilo, no lo inventes. - Aplican las reglas globales (
~/.agents/AGENTS.md) y su router (~/.agents/rules/). Lee bajo demanda, no todo. Si tu agente no las tiene cargadas, léelas ahora. - Ningún cambio se da por terminado sin
~/.agents/rules/50-done-gate.mdy la tabla de gates. - Respuestas mínimas: resultado primero, ≤4 líneas de prosa, sin narrar herramientas. Detalle solo si se pide.
- Trabajo multiagente: antes de repartir, lee
./ORCHESTRATION.md. Una unidad = un worktree = una rama; los ficherossharedsolo los toca una unidad por ronda; los workers no editantasks.md,planes/*.md,ORCHESTRATION.md,STACK.mdni lockfiles, no mergean ni hacen push, y entregan informe. Briefs e informes en.work/(ignorado por git).
Overrides de este proyecto
<!-- Solo lo que se desvía de las reglas globales. Si está vacío, mejor. --><!-- AGENTS:END -->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.