lean-review
Skill1 starsChanged 16 days agoMITView on GitHub
Review a diff or a whole repo for unnecessary complexity only — delete-list of reinvented stdlib, unneeded deps, speculative abstractions. Use when the user asks what to delete, whether this is over-engineered, a simplify review, or a bloat audit. Complements review-change. Do not edit product code.
5 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- rpraharaj/ai-sdlcedited, first seen Nov 1, 2026
- FareedKhan-dev/lean-agenttheir own version, first seen Oct 13, 2026
- dRafaleD/cybersec-skillstheir own version, first seen Sep 18, 2026
- utk2103/Prompt-Studioedited, first seen Aug 22, 2026
- MaGe1993/Claude-Code-Base-Harnesstheir own version, first seen Jun 14, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- utk2103/Prompt-Studio★ 812% same
- rpraharaj/ai-sdlc★ 028% same
Wrote their own version · 3
- dRafaleD/cybersec-skills★ 2same name
- FareedKhan-dev/lean-agent★ 1same name
- MaGe1993/Claude-Code-Base-Harness★ 1same 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 repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- open-prSkill
- performanceSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- resolve-conflictsSkill
- revert-changeSkill
- review-changeSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- start-projectSkill
- upgrade-depsSkill
- verify-uiSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-prdSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
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
Read-only hunt for complexity that does not need to exist.
- Distinctive: line 21
If the target is empty, say so and stop.
- Very specific: line 47
Do not apply the cuts unless the user asked — that is refactor-safely or implement-change.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lean review
Read-only hunt for complexity that does not need to exist. Not a correctness, security, or performance review — those are review-change, security-pass, and performance.
Load engineering-bar (paths in that skill) and apply Minimum path + Never cut.
Target
- User said "whole repo", "audit", or "what can we delete from this tree" → scan the tree (skip
node_modules,.git, vendored/build output). - Otherwise follow
engineering-barShared procedures for scope and evidence, including branch commits and relevant untracked files.
If the target is empty, say so and stop.
Tags
One line per finding:
<file>:<line>: <tag> <what to cut>. <what replaces it>.
| Tag | Means |
delete | Dead code, unused flexibility, speculative feature. Replacement: nothing. |
stdlib | Hand-rolled thing the language/runtime already ships. Name the function. |
native | Code or dependency doing what the platform already does. Name the feature. |
yagni | Abstraction with one implementation, config nobody sets, layer with one caller. |
shrink | Same logic, fewer lines. Show the shorter form. |
Do not flag:
- Trust-boundary validation, data-loss error handling, authz, secrets, or accessibility
- The one focused test
write-testsadded for new logic - Correctness/security/perf bugs — name
review-change/security-pass/performanceand leave them out of this list
Output
Rank biggest cut first. End with net: -<N> lines (and -<M> deps if a dependency can go). Nothing to cut: Lean already. and stop.
Do not apply the cuts unless the user asked — that is refactor-safely or implement-change.
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.