code-plan

Solid

Use only when autopilot-code dispatches the planning and plan-check stage. Not for top-level user requests or primary capability routing.

AI & Automation 7 stars 1 forks Updated today MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
30
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# code-plan Use the deepest eligible planning profile selected by the active adapter when cross-file reasoning or call-site analysis would benefit from it. > **Stage-session entry (`standard+` dispatch, spec/stage-dispatch SD-2)**: Run in-session or as an isolated dispatch-depth-2 stage worker dispatched by the `autopilot-code` conductor. Inputs are the task description and `<artifact-root>/plans/`; never depend on prior-stage conversation. The write class is root `plan.md`, root `checklist.md`, an existing or explicitly requested audience-language companion such as legacy `plan_ko.md`, and `_internal/plan_reviews/`. The stage runs as the `plan/plan-author` unit (the node's unit); independent plan review is the sibling `plan-check` node dispatched by the conductor, not an in-stage delegation. > **Language rule**: Follow the audience and artifact language contract in [arguments-and-decisions.md#language-rule](../autopilot-code/references/arguments-and-decisions.md). Write the canonical plan in the selected artifact language; do not generate a language mirror merely because the skill source is English or the conversation uses a particular language. ## Pre-Check Search `<artifact-root>/plans/` for a similar plan and branch on its frontmatter status: - `active`: Ask whether to continue the active plan or create a new one. Do not proceed until that genuine choice is resolved. - `done` or `failed`: Note it as a reference and create a new plan without pausing. - `partial`: Rea...

Details

Author
dmlguq456
Repository
dmlguq456/hearting
Created
5 months ago
Last Updated
today
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category