scope-and-plan
Skill0 starsChanged 2 months agoMITView on GitHub
Locates where a change will live by tracing the relevant slice of the codebase, then interrogates the plan relentlessly, one question at a time, resolving each branch of the decision tree, until you and the user reach a shared, code-grounded understanding. Use before building a feature or refactor, to stress-test a plan, or when the user says "scope this" or "plan this out".
In this repository7 other files it gives its agents.
- audit-with-subagentsSkill
- cleanupSkill
- complainSkill
- grade-fileSkill
- harden-codeSkill
- simplify-codeSkill
- structurizeSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Before planning, scope the codebase.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Before planning, scope the codebase. Trace the import graph around where the change will live (the files it'll touch and, one hop out, their neighbors) to pin down roughly where it belongs and what it connects to. Flag anything that should reshape the plan.
Then plan relentlessly until you and the user reach a shared understanding. Walk each branch of the decision tree, resolving dependencies between decisions one at a time. Ask one question at a time, each with your recommended answer. If a question can be answered by exploring the codebase, explore instead of asking.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.