scope-lock
Skill0 starsChanged 3 months agoMITView on GitHub
Produces a short context manifest of which files and directories are in-bounds for the current task on a medium or large existing codebase. Keeps subsequent reading inside that boundary unless explicitly widened. Prevents context bloat.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- kartykk/agent-readytheir own version, first seen Sep 21, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- kartykk/agent-ready★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- document-directorySkill
- domain-modelingSkill
- grillingSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- prototypeSkill
- researchSkill
- resolving-merge-conflictsSkill
- setupSkill
- start-sessionSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- wayfinderSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Before researching anything in a codebase big enough that reading all of it would be wasteful, decide what's in bounds and write it down.
- Distinctive: line 13
Start from whatever's already known: If the user or wayfinder already named a specific area ("the payments module", "the login flow"), …
- Very specific: line 30
Hold the boundary: Treat anything outside the manifest as out-of-bounds for Read/Grep/Glob.
- Distinctive: line 40
Never read an entire large repository before scoping.
- Distinctive: line 41
Never lock scope without at least one confirmation from the user.
- Distinctive: line 42
Never treat the manifest as permanent across unrelated tasks.
≈ “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
Scope-lock
Before researching anything in a codebase big enough that reading all of it would be wasteful, decide what's in bounds and write it down.
Process
- Start from whatever's already known. If the user or wayfinder already named a specific area ("the payments module", "the login flow"), that's the starting point.
- If nothing specific has been named, do a cheap structural pass:
top-level directory listing,
README/rootCLAUDE.mdif present,git log --stat -20for recently-active areas, and any subdirectoryCLAUDE.mdfiles near likely locations. Do not read full file contents broadly — structure and names are enough. - Propose a boundary. State it back to the user: "This looks like
it lives mostly in
src/checkout/and touchessrc/payments/— I'll focus there." One confirmation is enough. - Write the manifest. Record the in-bounds paths in
.agent/state.json(add acontext_manifestfield if needed). - Hold the boundary. Treat anything outside the manifest as
out-of-bounds for Read/Grep/Glob. If the boundary proves too narrow,
say so and widen explicitly. If the research pass was substantial
and
handoffis detected, use it to compact before continuing. - Re-scope per task, not per project. A manifest set for one feature doesn't carry to an unrelated task in the same repo.
What this skill must never do
- Never read an entire large repository before scoping.
- Never lock scope without at least one confirmation from the user.
- Never treat the manifest as permanent across unrelated tasks.
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.