Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/anastasiyaw/codex-claude-code-config/lean-codenpx skills add AnastasiyaW/codex-claude-code-config --skill lean-codegit clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-configWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00134 | $0.00848 |
| Opus 5 | $0.00067 | $0.00424 |
| Sonnet 5 | $0.00027 | $0.00170 |
| Haiku 4.5 | $0.00013 | $0.00085 |
Grade A, and why
lean-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 measured ("smallest solution that FULLY satisfies the task"), not a slogan.
The ladder — stop at the first rung that holds
- 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 it be one line? Make it one line.
- 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's asked, but name the leaner alternative in one line; user picks.
- full — the ladder enforced; stdlib/native first; shortest working diff. (Default.)
- ultra — YAGNI extremist: ship the one-liner and challenge the rest of the requirement in the same breath.
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 code per branch, NOT fewer branches done or cutting corners with a hack. It must never be an excuse to under-deliver, skip verification, or leave a required branch — 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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 36 lines · 0 tokens per session scan A a520a4ce3d4c
lean-code is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (147 stars, last pushed 8d ago), licensed MIT. It adds 134 tokens to every session and 848 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
swarms
Build agents and multi-agent systems with the Swarms framework — the Agent class, tools, autonomous loops, memory, and the 15+ multi-agent architectures (SequentialWorkflow, ConcurrentWorkflow, GraphWorkflow, HierarchicalSwarm, SwarmRouter, and more). Use whenever writing, reviewing, or debugging code that imports…
code-review
Perform comprehensive code reviews focusing on best practices, security vulnerabilities, performance optimization, and maintainability.
data-visualization
Create effective data visualizations using best practices for clarity, accuracy, and visual communication of insights.
financial-analysis
Perform comprehensive financial analysis including DCF modeling, ratio analysis, and financial statement evaluation for companies and investment opportunities.
ai-content-filter
Professional Ai Content Filter Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
ai-engineer
Professional Ai Engineer skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.