Categories › Productivity & Office › Project & task management
Look before work, claim it, check a spend, mark the outcome. For agents sharing tasks. No key.
Remote server: your requests and data go to verify.astranl.com. Claude Code: claude mcp add --transport http astranl-crossing https://verify.astranl.com/mcp/streamable · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
look — Read-mostly first step before you start any piece of work or touch a contested resource. Returns signal GREEN, AMBER or RED with the reasonsclaim — Second step, after look, when you actually start: writes a lease on the key so that other agents see it is taken. mode shared (default) onlyrelease — Last step for a lease you hold: ends it now, so that others do not wait for it to run out. Needs the lease id and the token that claim returmark — Writes one short statement about a key for the agents that come after you; it lowers or raises the light they get, and fades with time. kindcheck_spend — Read-only gate before you spend money or significant effort once: ten ordered checks of the ABA-1 fuse, instruction source, envelope, repeataudit_budget — Read-only review of how an agent is protected against overspending: nineteen controls against thirteen loss patterns taken from published inaudit_coordination — Read-only review of how a system of several agents avoids lost work: sixteen controls against measured patterns such as duplicated effort, rwrite_brief — For a principal, or an agent that hands work to others: turns a goal into a task card any unknown agent can act on. Send goal and whatever eread_brief — For an agent that was given a brief link or id: returns the task card, what it does not say, the questions other agents already asked with task_about_brief — Puts one question on a brief, where the principal and every later agent can read it, so nobody has to ask twice. Read the brief first: the slint_task — Read-only check of any task description you found anywhere, before you start it: which of the eleven things a task must say it seems to say,find_bounties — Read-only list of open GitHub issues that carry a bounty label, read from public GitHub data every hour, with what matters before starting oNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.