Get card
Download
goal-setter@1.0.0.yamlClone
npx -y darkprint clone goal-setter@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.
Take the objective from the person who owns it, in their words, and put it into the run.
used in 1 blueprint
Specification
137 words · handed to the agentAsk the owner what they want to be true at the end of this run, and record their answer. Press for a single objective rather than a list: where they give several, ask which one the run is for and record that one. Record what they said, not a tidied version of it, and do not add scope they did not ask for. Do not ask them how success will be measured, that is a separate question asked at a separate node on purpose, and an objective written alongside its measure tends to be written to fit it. Emit the objective on objective with whatever context the owner gave about why it matters and what is out of scope. Nothing downstream can ask the owner a follow-up, so an objective that is still ambiguous here stays ambiguous.
Interfaces
0 in · 1 outInputs
0No inputs declared, nothing upstream feeds this node.
Outputs
1| Name | Data type | Description |
|---|---|---|
| objective | plan | The objective in the owner's own terms, with its scope and its exclusions. |
Dependencies
0None declared, no edge has to arrive for this node to run.
Card values
13 declaredWho the node is. The id is the key the DOT pins.
- id
- goal-setter
- name
- Goal Setter
- type
- human-input
- phases
- Planning
What it does, and the prose the agent is handed when the graph runs.
- action18 words
- Take the objective from the person who owns it, in their words, and put it into the run.
- spec137 words
- Ask the owner what they want to be true at the end of this run, and record their answer. Press for a single objective rather than a list: where they give several, ask which one the run is for and record that one. Record what they said, not a tidied version of it, and do not add scope they did not ask for. Do not ask them how success will be measured, that is a separate question asked at a separate node on purpose, and an objective written alongside its measure tends to be written to fit it. Emit the objective on
objectivewith whatever context the owner gave about why it matters and what is out of scope. Nothing downstream can ask the owner a follow-up, so an objective that is still ambiguous here stays ambiguous.in full above - model
- whatever the graph supplies
- agent
- not named
- skill
- not named
- tools
- Human review
- mcp
- none
- params
- none
What arrives, what leaves, which nodes it expects to hear from, and what may not.
- inputs
- none
- outputs
- objective : plan
- dependencies
- none
- cannot
- acceptance-criteria
- will_not
- ask the owner how the objective will be measured, add scope the owner did not state
The keys the static analysis reads. Nothing here instructs the agent.
- risk_markers
- none
- notes26 words
human-inputrather thanhuman-gate: there is nothing upstream for a person to approve here, and this node is where the objective enters the graph at all.
The card's own version, and who wrote it.
- version
- 1.0.0
- author
- autogen
- provenance
- not stated
Version history
1 version published- goal-setter@1.0.0currentsha256:ae2b71dfd379ba3ee1c2fe042f97934dee0fb855de11b2160da9c5a84da0a070
pinned byObjective Tracker
autogen/objective-tracker
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.