AI Code Review
mohitagw15856/pm-claude-skills
Review AI-authored code for its characteristic failure modes — plausible-but-wrong logic, hallucinated APIs, over-engineering, dead scaffolding, and silent security shortcuts.
On-demand minimalism intensifier — find the smallest sufficient, verified implementation for the requested outcome.
Install Lean Code
$ npx skills add AnastasiyaW/codex-claude-code-config --skill lean-code -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config lean-code --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lean-code .claude/skills/lean-code && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "lean-code" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/lean-code into .claude/skills/lean-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lean-code", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/lean-codeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AnastasiyaW/codex-claude-code-config --skill lean-code -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config lean-code --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/lean-code .agents/skills/lean-code && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "lean-code" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/lean-code into .agents/skills/lean-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lean-code", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AnastasiyaW/codex-claude-code-config --skill lean-code -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config lean-code --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/lean-code .cursor/skills/lean-code && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "lean-code" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/lean-code into .cursor/skills/lean-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lean-code", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AnastasiyaW/codex-claude-code-config.git --path skills/lean-code--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AnastasiyaW/codex-claude-code-config --skill lean-code -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config lean-code --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/lean-code .gemini/skills/lean-code && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "lean-code" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/lean-code into .gemini/skills/lean-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lean-code", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AnastasiyaW/codex-claude-code-config lean-codeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AnastasiyaW/codex-claude-code-config --skill lean-code -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/lean-code .github/skills/lean-code && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "lean-code" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/lean-code into .github/skills/lean-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lean-code", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AnastasiyaW/codex-claude-code-config --skill lean-code -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config lean-code --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/lean-code .opencode/skills/lean-code && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "lean-code" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/lean-code into .opencode/skills/lean-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lean-code", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
lean-code- GitHub stars
- 154
- Token cost
- ~1.3k tokens
- SKILL.md length
- 653 words
- Files
- 1
- Skills in repo
- 52
- Repo updated
- First seen
- Licence
- MIT
At a glance
On-demand minimalism intensifier — find the smallest sufficient, verified implementation for the requested outcome.
- Works in 6 steps: Does this need to exist at all?… → Stdlib does it? Use it. → Native platform feature covers it? (… → …
- The user says be lazy / yagni / simplest / minimal / shortest / dont over-engineer
- SKILL.md covers The ladder — stop at the first…, Intensity, When NOT to be lean… and Hard boundary — lean targets…, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Lean Code is an agent skill from AnastasiyaW/codex-claude-code-config. On-demand minimalism intensifier — find the smallest sufficient, verified implementation for the requested outcome. Use when the user says "be lazy / yagni / simplest / minimal / shortest / don't over-engineer", complains about bloat / boilerplate / unnecessary dependencies / abstraction, or before writing a substantial chunk of new code. Supports intensity: lite / full / ultra. Pairs with the always-on quality-code rule and the over-engineering-advisor hook. Do NOT use as a general code-review or bug-hunting…
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Code simplification, Project scaffolding and Code review. The repository describes itself as: Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development. The licence is MIT.
When your agent uses it
- The user says be lazy / yagni / simplest / minimal / shortest / dont over-engineer
- Complains about bloat / boilerplate / unnecessary dependencies / abstraction
- Before writing a substantial chunk of new code
Example prompts
- “be lazy / yagni / simplest / minimal / shortest / don”
- “/lean-code”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Does this need to exist at all? Speculative need → skip it, say so in one line. (YAGNI)
- Stdlib does it? Use it.
- Native platform feature covers it? ( over a picker lib, CSS over JS, a DB constraint over app code.)
- An already-installed dependency solves it? Use it. Never add a new dependency for what a few lines do.
- Can the accepted behavior safely be one line? Prefer it; do not contort control flow, validation, or errors merely to make it fit.
- Only then — the minimum code that works.
What it can do on your machine
Read from SKILL.md and the folder at commit cdcb11d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
gitclear-public.s3.us-west-2.amazonaws.comfaros.aiarxiv.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Lean Code loads about 1.3k tokens when it runs. Until then it costs about 162 tokens; SKILL.md has 653 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from AnastasiyaW/codex-claude-code-config at commit cdcb11d, republished under its MIT licence (© AnastasiyaW). 653 words, ~1,339 tokens.
Download SKILL.mdSave it as
.claude/skills/lean-code/SKILL.md (or your agent's skills folder).- name
- lean-code
- description
- On-demand minimalism intensifier — find the smallest sufficient, verified implementation for the requested outcome. Use when the user says "be lazy / yagni / simplest / minimal / shortest / don't over-engineer", complains about bloat / boilerplate / unnecessary dependencies / abstraction, or before writing a substantial chunk of new code. Supports intensity: lite / full / ultra. Pairs with the always-on quality-code rule and the over-engineering-advisor hook. Do NOT use as a general code-review or bug-hunting pass — it only removes over-building and will not find unrelated correctness defects; use /code-review or /review for those.
Lean Code
Aggressive YAGNI mode, on demand. The always-on baseline is rules/quality-code.md; this skill is the intensifier you invoke when minimalism matters most. The win is the smallest solution that fully satisfies the accepted task outcome, not the fewest lines or the shortest explanation.
The ladder — stop at the first rung that holds
Choose a rung only when it preserves the accepted architecture, contracts, and non-functional requirements; installed/native status alone does not justify crossing an established project boundary.
- Does this need to exist at all? Speculative need → skip it, say so in one line. (YAGNI)
- Stdlib does it? Use it.
- Native platform feature covers it? (
<input type="date">over a picker lib, CSS over JS, a DB constraint over app code.) - An already-installed dependency solves it? Use it. Never add a new dependency for what a few lines do.
- Can the accepted behavior safely be one line? Prefer it; do not contort control flow, validation, or errors merely to make it fit.
- Only then — the minimum code that works.
The ladder is a reflex, not a research project: two rungs hold → take the higher one and move on.
Intensity
- lite — build what the user asked; mention one leaner alternative only when it materially helps. Do not pause accepted implementation for an optional choice. Ask only when an unresolved decision materially changes the requested outcome or authority.
- full — enforce the ladder; prefer stdlib/native and the smallest sufficient, verified diff. (Default.)
- ultra — challenge a requested mechanism, scope assumption, or speculative extension against the required outcome; do not challenge an explicit user decision merely to reduce code. Once retained, implement it without re-arguing.
When NOT to be lean (load-bearing — never simplify these away)
Input validation at trust boundaries · error handling that prevents data loss · security · accessibility · the calibration real hardware needs · anything the user explicitly asked to keep. Lean ≠ incomplete: non-trivial logic leaves one runnable check behind (assert-demo or one small test). User insists on the full version → build it, no re-arguing.
Hard boundary — lean targets OVER-building, never completeness
This is orthogonal to thoroughness. "Minimal" means less unnecessary complexity while delivering every accepted branch, not fewer branches done, a lower line count, or a shortcut. It must never excuse under-delivery, skipped verification, or a hack — see rules/finish-the-task.md (its completeness + quality pillars win) and rules/quality-code.md (the no-monkey-patch pole). Mark a deliberate shortcut with a simplification: comment naming the ceiling + upgrade path.
Show full SKILL.md (251 more words)Show less
Output
Complete and verify the requested result first. Then use at most three short lines for what was deliberately skipped and the trigger to add it. Do not suppress an explanation needed to document a safety boundary, user decision, or upgrade path. Read the surrounding code and requirements before pruning — prune to the task, not to a blanket rule.
Why this works (evidence, not marketing)
GitClear's 2025 report observed rising copy/paste and falling moved-line rates across 211M changed lines; Faros observed higher team task/PR throughput alongside slower review and no demonstrated organization-wide gain. Those are ecosystem signals, not proof that a particular agent or diff is bloated. A "do I even need this?" check is therefore useful, but not a line-count target. GitClear · Faros
Generic prompt additions can trade one measured behavior for another in small local experiments; they do not establish a universal minimalism rule. Keep this on-demand and advisory, then evaluate its instructions on representative held-out tasks. arXiv:2601.22025
Gotchas
- A one-liner is worse when it hides a required failure path, access need, or future-maintenance boundary.
ultracan question how to achieve an outcome; it cannot silently remove an outcome or override the user's retained choice.
Troubleshooting
- The diff is short but a required behavior vanished. Restore the behavior, then remove only the unnecessary mechanism around it and run the smallest relevant check.
- A simplification has an explicit scale or correctness ceiling. Keep the simple version only with its
simplification:ceiling and upgrade trigger; otherwise implement the proper architecture now.
© AnastasiyaW, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/lean-code of AnastasiyaW/codex-claude-code-config.
Open the folder on GitHubat commit cdcb11d
Compare with similar skills
Lean Code next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Lean Code this skillAnastasiyaW/codex-claude-code-config | 154 | — | ~1.3k | Automated safety check: Pass | MIT | |
| AI Code Reviewmohitagw15856/pm-claude-skills | 1.4k | — | ~1.5k | Automated safety check: Pass | MIT | |
| PonytailDavidObando/gsharp | 564 | 8 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Unslop CodeJCarterJohnson/vibecoded-design-tells | 508 | — | ~2.5k | Automated safety check: Pass | Custom licence | |
| Chisle ReviewJayPokale/Chisle | 628 | — | ~362 | Automated safety check: Pass | MIT | |
| Pragmatic Reviewheyitsnoah/claudesidian | 2.6k | — | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Ponytail
DavidObando/gsharp
Forces the laziest solution that actually works, simplest, shortest, most minimal.
Unslop Code
JCarterJohnson/vibecoded-design-tells
Strips the tells that make source code read as AI-generated and forces code that fits the project instead of the model's default average.
Chisle Review
JayPokale/Chisle
Review a diff or file through the Chisle lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink.
Pragmatic Review
heyitsnoah/claudesidian
Interactive pragmatic code review focusing on YAGNI and KISS principles.
Dry Code Review
espennilsen/pi
Perform a comprehensive DRY (Don't Repeat Yourself) code review on a codebase.
More from AnastasiyaW/codex-claude-code-config
All 52 skills in this repoBug Reproducer
AnastasiyaW/codex-claude-code-config
Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix.
Motion Framer
AnastasiyaW/codex-claude-code-config
A skill your agent uses when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation.
Proof Verify
AnastasiyaW/codex-claude-code-config
Plan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify their own work).
Workflow Orchestration
AnastasiyaW/codex-claude-code-config
Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов).
Notebooklm Grounded Research
AnastasiyaW/codex-claude-code-config
A skill your agent uses when: NotebookLM, notebooklm MCP, large documentation sets, courses, books, papers, or citation-backed research are mentioned.
Deepseek Provider Contract
AnastasiyaW/codex-claude-code-config
Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries.
Related
Categories
Questions about Lean Code
What does Lean Code do?
On-demand minimalism intensifier — find the smallest sufficient, verified implementation for the requested outcome. Lean Code is an agent skill from AnastasiyaW/codex-claude-code-config. On-demand minimalism intensifier — find the smallest sufficient, verified implementation for the requested outcome.
When should I use Lean Code?
Lean Code fits situations like: the user says be lazy / yagni / simplest / minimal / shortest / dont over-engineer; complains about bloat / boilerplate / unnecessary dependencies / abstraction; before writing a substantial chunk of new code.
How do I install Lean Code in Claude Code?
Run `npx skills add AnastasiyaW/codex-claude-code-config --skill lean-code -a claude-code`. Or copy the skill folder (skills/lean-code in AnastasiyaW/codex-claude-code-config) into .claude/skills/lean-code in your project. Claude Code loads it when a task matches its description.
How do I install Lean Code in Codex?
Run `npx skills add AnastasiyaW/codex-claude-code-config --skill lean-code -a codex`. Or copy the skill folder (skills/lean-code in AnastasiyaW/codex-claude-code-config) into .agents/skills/lean-code in your project. Codex loads it when a task matches its description.
Can I use Lean Code in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AnastasiyaW/codex-claude-code-config --skill lean-code -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lean-code, .gemini/skills/lean-code, .github/skills/lean-code and .opencode/skills/lean-code in your project.
What does Lean Code need to run?
SKILL.md names no scripts, command-line tools or credentials: Lean Code is instructions for the agent only.
Does Lean Code access the network?
SKILL.md names 3 domains. As links in the text: gitclear-public.s3.us-west-2.amazonaws.com, faros.ai and arxiv.org. This is read from the text; nothing was executed.
Is Lean Code safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Lean Code use?
Lean Code is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Lean Code use?
About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Lean Code?
Skills that share tags, products or a category with Lean Code: AI Code Review (mohitagw15856/pm-claude-skills, 1.4k stars), Ponytail (DavidObando/gsharp, 564 stars), Unslop Code (JCarterJohnson/vibecoded-design-tells, 508 stars) and Chisle Review (JayPokale/Chisle, 628 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Lean Code?
AnastasiyaW (a GitHub user) maintains it in AnastasiyaW/codex-claude-code-config, which has 154 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on October 2, 2026.
Source: AnastasiyaW/codex-claude-code-config on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.