From butterbase-skills
Builds agents from a plan: registers MCP servers, validates graph specs, creates agents, and runs smoke tests. Skips if no agents are listed.
How this skill is triggered — by the user, by Claude, or both
Slash command
/butterbase-skills:journey-agentsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Build the agents described in `02-plan.md`. Order: MCP servers first (probe must pass before any agent references them) → agents → smoke runs.
Build the agents described in 02-plan.md. Order: MCP servers first (probe must pass before any agent references them) → agents → smoke runs.
journey when current_stage: agents./butterbase-skills:journey-agents.(n/a)) if the plan lists no agents.If docs/butterbase/03-preflight.md is missing, older than 24 hours, or 00-state.md has app_id: null, invoke butterbase-skills:journey-preflight first. Wait for it to return successfully before proceeding.
docs/butterbase/02-plan.md — the Agents section (names, purpose, tool list, visibility, MCP servers needed).docs/butterbase/00-state.md — for app_id.agents/ in the project (preferred — version-controlled and survives clones).Refresh docs. Call butterbase_docs with topic: "agents". If the cache (docs/butterbase/03b-docs-cache.md) already covers agents, skip.
Register MCP servers first. For each MCP server in the plan:
"Registering MCP server '<label>' at <url> (transport=<sse|http|streamable_http>). Proceed?". Wait for yes.butterbase_docs topic agents for the current preferred path).status: unhealthy, surface the error and ask the user to fix (URL, auth header, transport mismatch) before continuing. Do not create agents that reference an unhealthy server.Build each agent. For each agent in the plan, in order:
a. Print: "About to build agent: <name> (visibility=<v>, tools=<n builtin / m mcp / k function>). Proceed?". Wait for yes.
b. Invoke butterbase-skills:agents via the Skill tool with: agent name, intended behaviour, plan-derived tool list, model preference, visibility/limits. The wrapped skill drafts the graph_spec, writes it to agents/<name>.json in the project repo, and calls validate_agent_spec.
c. If validation fails, surface the Zod issues and loop the agents skill to fix.
d. Safety gate. If visibility != 'private' AND any node can reach a write tool (insert_row, update_row, delete_row, write_storage, or any read_write-mode MCP/function tool), explicitly ask: "This agent is reachable by <visibility> callers and can write data. Set safety_acknowledged=true? (yes / change to private / reduce tools)". Do not proceed silently.
e. create_agent with the validated spec.
f. Smoke: invoke_agent with a representative input. Poll get_agent_run until terminal. If the run errors, debug per the agents skill's debugging procedure; otherwise show the user the final output.
g. Append one line per agent to docs/butterbase/04-build-log.md:
<ISO timestamp> agents create_agent <agent-name> ok (run smoke=<run_id>)
Persist specs to the repo. Confirm agents/<name>.json files are tracked locally. They will be carried by butterbase repo push (run by the templates stage if the user is publishing, or any time the user pushes a snapshot). This is the only way a clone recipient can recreate the agents — the agents table is not part of clone replay.
Tick state. Mark - [x] agents in 00-state.md, set current_stage to the next unchecked stage.
Return to journey orchestrator (or ask "Continue to the next stage? (yes/no)").
agents/<name>.json spec files in the project repo.docs/butterbase/04-build-log.md.validate_agent_spec. Bad specs surface as opaque runtime errors after the agent is live.public write-capable agent without rate limits or a daily_budget_usd. The runtime requires safety_acknowledged, but you should also pick hourly per-IP and per-app caps.system_prompt or args_template. Read them from ctx.env inside a function tool.agents table is not replayed on clone. Always commit the spec JSON and document re-import (butterbase agents create -f agents/<name>.json) in the README.visibility: 'private' and calling it good for a public agent. After the smoke, change visibility and re-test with an unauthenticated curl to confirm the public path works.npx claudepluginhub butterbase-ai/butterbase-skills --plugin butterbase-skillsDesigns, deploys, and debugs Butterbase Agents — declarative LLM/tool graphs with MCP integration, access controls, and rate limits.
Provides the full agent development lifecycle (scaffold, build, evaluate, deploy, publish, observe) using ADK and google-agents-cli, with code preservation rules and troubleshooting.
Creates and validates production-grade agent .md files for Anthropic 2026 16-field spec. Use for custom subagents, agent quality review, or orchestrator architectures. Triggers: /agent-creator, 'create an agent'.