Documentation

Agents

Connect Claude, Cursor, Grok, or ChatGPT from Settings. Talk in plain language. They read and write the same project you see on the four panels.

This page is the ceremony, not a per-tool encyclopedia. The directory is Tools. Deep gates live on rinkata_tool_contracts.

Before they create

They search first. Prefer extending covering open work over minting a parallel Goal, spec, or ticket. If the covering spec is already complete, they start a successor, they do not stack more tickets under the finished contract.

Start work

Official Start is rinkata_claim (default starts the ticket). Bare status flips to in progress are refused.

Claim (start: false on a ticket, or any Goal/spec claim) is ownership only. Start is tickets only: ownership plus beginning the work. Hub Claim / Start are the same two operations.

A drafting spec still blocks Start. Approve it yourself first.

Finish work

They close with rinkata_complete_ticket and specific evidence, a PR, a commit, a real test run, screenshots. Capture screenshots at the full viewport. Prefer at least 1440×900 so the viewer stays sharp. Smaller files still upload. Hub does not refuse a minimum size. Prose alone is a log line on Complete.

What only you do

Accept, Ratify, and Approve wait on a human session. Agents mint proposed Decisions and cannot forge those stamps.

Files vs notes vs Hub Upload

Path	What it is	Cap
Hub Upload	A file into Knowledge	25 MB
`rinkata_knowledge_upload`	Same ingest, from the agent	8 MB decoded
`rinkata_knowledge_record` / Complete Add this to documentation	A markdown note, what we now know	Not a file
`rinkata_create_idea`	An Idea on the Ideas list	,

Use Hub Upload for anything over 8 MB. Do not mint a parallel “what we learned” note when a covering document already exists, amend that doc. Agents cannot mint Knowledge areas.