Get card
Download
task-intake@1.0.0.yamlClone
npx -y darkprint clone task-intake@1.0.0There is no repository and no history behind a card. Download hands you the document as it stands, and Clone fetches the same document by name.
Accept an inbound task request, stamp it with a run id and the acceptance criteria it will be judged against, and hand it to the line as a single self-contained brief.
used in 2 blueprints
Specification
111 words · handed to the agentTake the next request off the task-queue source and check it against the task-request@1 schema before anything else; reject a request that does not match and stop, rather than forwarding a half-filled brief the rest of the line has to guess at. Stamp the accepted request with a fresh run id and attach to it the reference to the acceptance-criteria set this run will be judged against. Emit the result on request as one self-contained brief carrying the goal, the constraints and that criteria reference. You are the only step that reads the queue, so anything you drop or fail to copy across is gone for the remainder of the run.
Interfaces
0 in · 1 outInputs
0No inputs declared, nothing upstream feeds this node.
Outputs
1| Name | Data type | Description |
|---|---|---|
| request | json | The task as the line will see it, goal, constraints, and the criteria set it must clear. |
Dependencies
0None declared, no edge has to arrive for this node to run.
Card values
12 declaredWho the node is. The id is the key the DOT pins.
- id
- task-intake
- name
- Task Intake
- type
- tool
- phases
- none declared
What it does, and the prose the agent is handed when the graph runs.
- action31 words
- Accept an inbound task request, stamp it with a run id and the acceptance criteria it will be judged against, and hand it to the line as a single self-contained brief.
- spec111 words
- Take the next request off the
task-queuesource and check it against thetask-request@1schema before anything else; reject a request that does not match and stop, rather than forwarding a half-filled brief the rest of the line has to guess at. Stamp the accepted request with a fresh run id and attach to it the reference to the acceptance-criteria set this run will be judged against. Emit the result onrequestas one self-contained brief carrying the goal, the constraints and that criteria reference. You are the only step that reads the queue, so anything you drop or fail to copy across is gone for the remainder of the run.in full above - model
- whatever the graph supplies
- agent
- not named
- skill
- skills/task-intake.md
- tools
- none
- mcp
- none
- params
- source: task-queue, request_schema: task-request@1
What arrives, what leaves, which nodes it expects to hear from, and what may not.
- inputs
- none
- outputs
- request : json
- dependencies
- none
- cannot
- no type is refused
- will_not
- forward a request that failed the schema check
The keys the static analysis reads. Nothing here instructs the agent.
- risk_markers
- none
- notes26 words
- The criteria reference is attached here rather than at the verifier, so both solvers write against the same bar the verifier will later hold them to.
The card's own version, and who wrote it.
- version
- 1.0.0
- author
- autogen
- provenance
- not stated
Version history
1 version published- task-intake@1.0.0currentsha256:a5099ff67f57b87ccdddbeb69eb6a163616677d3e680d0c0cfa6c1523f6b37ad
pinned byAdversarial Consensus Line
autogen/adversarial-consensus-line,Delegation Brokerautogen/delegation-broker
A digest is a fingerprint (SHA-256) of the card's content, computed without the author and provenance fields. The same card from two people gets the same digest; any edit gets a new one.
First published version, so there is nothing to compare yet. Versions are never edited in place: the next change arrives as a new version, and the differences between the two documents are listed here.
Community notes (0)
No notes yet.
Nobody has posted about this node card yet.
Sign in to post a note.