Bootstrap a project init.md (cached project context for autonomous yaver runs). Drastically cuts the per-kick token + wall-clock cost of autoideas because runners read init.md instead of re-grepping the project on every kick. Idempotent — re-runs replace only the AI-generated section, preserving ...
AI agents invoke autoinit_start to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
force | boolean | — | regenerate even if init.md already has a generated section |
engine | string | — | |
output | string | — | default init.md |
prompt | string | — | extra context to bias the description |
project | string | — | |
work_dir | string | Yes |
Parameters from the server's own tool schema.
autoinit_start triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Bootstrap a project init.md (cached project context for autonomous yaver runs). Drastically cuts the per-kick token + wall-clock cost of autoideas because runners read init.md instead of re-grepping the project on every kick. Idempotent — re-runs replace only the AI-generated section, preserving any human-edited prose between markers. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
autoinit_start accepts 6 parameters: force, engine, output, prompt, project, work_dir. Required: work_dir. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for autoinit_start: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.
autoinit_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the autoinit_start rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for autoinit_start. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
autoinit_start is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.