hub-safety
Skill710 starsChanged 8 months agoMITView on GitHub
Safety checks and procedures when modifying hub files (files imported by 3+ others). Activated when editing files with high importer counts.
In this repository7 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- codemapSkill
- config-setupSkill
- exploreSkill
- handoffSkill
- refactorSkill
- test-firstSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Run codemap --importers <file> to see all dependents
- Distinctive: line 14
Check if tests exist for dependents, not just the hub itself
- Distinctive: line 18
Prefer additive changes over breaking changes
- Distinctive: line 19
If renaming or removing a public symbol, update all importers in the same commit
- Distinctive: line 20
If changing a function signature, check all call sites
- Distinctive: line 24
Run the full test suite, not just the hub's tests
- Very specific: line 25
Run codemap --deps . to verify the dependency graph is intact
- Distinctive: line 26
If the hub has 8+ importers, consider a staged rollout (change hub, test, update callers separately)
≈ “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
Hub Safety Protocol
Hub files are imported by 3+ other files. Changes here ripple across the codebase.
Before editing a hub file
- Run
codemap --importers <file>to see all dependents - Understand the public API surface: which functions/types are used externally
- Check if tests exist for dependents, not just the hub itself
While editing
- Prefer additive changes over breaking changes
- If renaming or removing a public symbol, update all importers in the same commit
- If changing a function signature, check all call sites
After editing
- Run the full test suite, not just the hub's tests
- Run
codemap --deps .to verify the dependency graph is intact - If the hub has 8+ importers, consider a staged rollout (change hub, test, update callers separately)
Risk escalation
| Importers | Risk | Action |
| 3-5 | Medium | Run package tests + direct importer tests |
| 6-10 | High | Run full test suite, review all importers |
| 10+ | Critical | Consider splitting the hub or using an interface |
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.

