simplification-gate
Skill1 starsChanged 11 days agoMITView on GitHub
Review an implementation or diff for avoidable complexity, unnecessary code, dependencies, abstractions, configuration, and duplication before completion.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adaptive-engineeringSkill
- code-reviewSkill
- existing-system-scanSkill
- memory-groundingSkill
- minimal-planningSkill
- systematic-debuggingSkill
- task-triageSkill
- verificationSkill
- verified-implementationSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 7
Treat complexity as a cost that requires evidence.
- Distinctive: line 12
Look for code that can be deleted without changing required behavior.
- Distinctive: line 13
Look for new code that duplicates repository capabilities.
- Distinctive: line 16
Ensure simplification does not hide real domain boundaries or compromise correctness.
≈ “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
Simplification Gate
Treat complexity as a cost that requires evidence.
Review sequence
- Compare actual scope with the declared complexity budget.
- Look for code that can be deleted without changing required behavior.
- Look for new code that duplicates repository capabilities.
- Challenge each new dependency, abstraction, interface, service, config key, and persistent field.
- Replace clever/general solutions with boring/specific ones when the latter satisfy current requirements.
- Ensure simplification does not hide real domain boundaries or compromise correctness.
Findings
Classify findings:
REMOVE: no value for current requirementsREUSE: existing capability should replace itCOLLAPSE: abstraction is prematureKEEP: complexity is justified by a concrete boundary or requirement
Apply safe simplifications directly when operating in implementation mode. Otherwise report them with the expected impact.
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.

