Fog plan
Seven tiny agent skills that burn down the gap between your prompt and reality — through one shared unknowns ledger
npx -y skills add leoncuhk/defog --skill fog-planAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 13 days oldThe repository was created 13 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Turn a burned-down ledger into a persisted plan ordered by decision volatility — likeliest-to-change first, mechanical work last.
SKILL.md
1.4 KB, as published. Nobody here has run it
Fog Plan
A plan's job is not to prove completeness; it's to put the expensive-to-change decisions in front of the user while changing them is still free.
Before writing: only low-risk residue converts to a labeled [A]. An open decision or taste item blocks the plan — run its listed resolver, record the answer, then plan. Update the ledger first; the plan cites only Resolved and Assumed items.
Order by volatility, sourced from the ledger:
- Decisions you may want to tweak — data model, interfaces, user-facing behavior. Each: the choice, one alternative considered (or "no real alternative" for territory findings), what changing it later costs. (From
Resolved.) - Assumptions standing — the
[A]batch: one line each, veto window, and the pivot signal — what observation during implementation forces revisiting it. - Mechanical work — compressed. The user trusts you here; reviewing it wastes their attention.
Write the plan to PLAN.md beside the ledger (PLAN-<task-slug>.md if the ledger is slugged) — the two files together are the launch packet for a fresh session.
End with the 2–4 items you need a yes or no on before starting. Target under ~400 words — a plan too long to read gets skimmed.