Get card
Download
work-planner@1.0.0.yamlClone
npx -y darkprint clone work-planner@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.
Turn the objective into an ordered set of steps, without knowing how the result will be measured.
used in 1 blueprint
Specification
129 words · handed to the agentRead the objective and write the steps that would achieve it, in the order they have to happen. Each step names one action and what it needs from the steps before it. Do not order a step before one it depends on, and do not write a step whose completion nobody could check. Where the objective is ambiguous, choose the reading that does least and say in the step which reading you took, rather than planning for both. Do not write any of the work itself. You do not have the conditions this run will be judged against and must not guess at them: a plan written toward a guessed measure is worse than one written toward the objective, because it looks like it was written toward the objective.
Interfaces
1 in · 1 outInputs
1| Name | Data type | Required | Description |
|---|---|---|---|
| objective | plan | required | The objective in the owner's terms, with its scope and exclusions. |
Outputs
1| Name | Data type | Description |
|---|---|---|
| steps | plan | The ordered steps, each naming its action and what it depends on. |
Dependencies
1The upstream nodes this card expects to receive from. Whenever a blueprint pins this card, each name is checked against a real edge in that graph. A name without a link is not a published card; it refers to a node inside some graph.
Card values
14 declaredWho the node is. The id is the key the DOT pins.
- id
- work-planner
- name
- Work Planner
- type
- agent
- phases
- Planning
What it does, and the prose the agent is handed when the graph runs.
- action17 words
- Turn the objective into an ordered set of steps, without knowing how the result will be measured.
- spec129 words
- Read the objective and write the steps that would achieve it, in the order they have to happen. Each step names one action and what it needs from the steps before it. Do not order a step before one it depends on, and do not write a step whose completion nobody could check. Where the objective is ambiguous, choose the reading that does least and say in the step which reading you took, rather than planning for both. Do not write any of the work itself. You do not have the conditions this run will be judged against and must not guess at them: a plan written toward a guessed measure is worse than one written toward the objective, because it looks like it was written toward the objective.in full above
- model
- whatever the graph supplies
- agent
- Planner
- skill
- not named
- tools
- none
- mcp
- none
- params
- none
What arrives, what leaves, which nodes it expects to hear from, and what may not.
- inputs
- objective : plan
- outputs
- steps : plan
- dependencies
- goal-setter
- cannot
- acceptance-criteria
- will_not
- write any of the work it plans, guess at the conditions the run will be judged against
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
Version history
1 version published- work-planner@1.0.0currentsha256:cf8bc0f0160b9f6077a0b6e5a1adb6accad15ae62b480ff8ad82074ff44e1c08
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.