Priority Scorer

Who the node is. The id is the key the DOT pins.

id

priority-scorer

name

Priority Scorer

type

agent

phases

none declared

What it does, and the prose the agent is handed when the graph runs.

action21 words

Score each item on the criteria the deployment set, and keep the criteria apart instead of collapsing them into one number.

spec121 words

For each item in front of you, score it separately on urgency, on impact, on what it blocks, and on what it would cost to do. Emit all four scores per item on scored, alongside the item unchanged. Do not combine them into a single priority figure: the four pull in different directions and which one wins is a policy decision belonging to the node that schedules, not to the node that scores. Score on what the item says, not on who filed it. An item you cannot score on a given criterion gets the worst score for that criterion and a note saying why, because an unscored item quietly sorts to the bottom and that is a decision nobody made.in full above

model

whatever the graph supplies

agent

Scorer

skill

not named

tools

none

mcp

none

params

criteria: ["urgency","impact","blocks","cost"], scale_max: 5

What arrives, what leaves, which nodes it expects to hear from, and what may not.

inputs

items : json

outputs

scored : json

dependencies

none

cannot

no type is refused

will_not

collapse the four criteria into a single figure, score an item on who filed it, leave an item unscored on any criterion

The keys the static analysis reads. Nothing here instructs the agent.

risk_markers

none

notes

none

The card's own version, and who wrote it.

version

1.0.0

author

autogen

provenance

not stated