leanlane

leanlane is a skill for Claude Code, Codex from talocode/leanlane. It costs 25 tokens per session (585 once invoked), scanned A, original, MIT.

A set of working rules that tells an AI coding agent to keep changes minimal and avoid unnecessary implementation.

In plain words
What is it for?
Use it while planning or reviewing coding tasks, especially when deciding whether to add code, reuse an existing helper, or introduce a dependency.
Why use it?
AI agents can add speculative features, abstractions, or dependencies that the task does not need. These rules encourage checking existing code and stopping at the smallest suitable solution.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/talocode/leanlane/leanlane
Any agent
npx skills add talocode/leanlane --skill leanlane
Clone the repo
git clone --depth 1 https://github.com/talocode/leanlane

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for leanlane

README.md
[![agentmods](https://agentmods.dev/badge/skills/talocode/leanlane/leanlane.svg)](https://agentmods.dev/skills/talocode/leanlane/leanlane)
Your own site
<a href="https://agentmods.dev/skills/talocode/leanlane/leanlane"><img src="https://agentmods.dev/badge/skills/talocode/leanlane/leanlane.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00585
Opus 5 $0.00013 $0.00293
Sonnet 5 $0.00005 $0.00117
Haiku 4.5 $0.00003 $0.00059

Measured 2d ago against content hash 1c5f89b77e13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

leanlane 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.

skills/leanlane/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LeanLane — lean senior mode (full)

You write only what the task needs. Lazy means efficient, not careless. The best code is code you never wrote.

Full intensity: stop at the first ladder rung that holds. Shortest correct diff wins.

Decision ladder (after you understand the problem)

Read the task and the code it touches. Trace the real flow. Then stop at the first rung that holds:

  1. Does this need to exist? → If the task is speculative or already covered by behavior, do not build it (YAGNI).
  2. Already in this codebase? → Search helpers, utilities, patterns, and similar features. Reuse before rewrite.
  3. Standard library? → Prefer language/runtime standard library over custom or third-party code.
  4. Native platform feature? → Prefer browser/OS/runtime native APIs (e.g. input type=date) over wrappers.
  5. Already-installed dependency? → Use an already-installed package. Do not add a new dependency unless required.
  6. Can this be one line? → If a single clear expression or call solves it, stop there.
  7. Minimum that works → Write the smallest correct change. No speculative abstractions.

Rules

  • No abstractions that were not explicitly requested.
  • No new dependency if it can be avoided.
  • No boilerplate nobody asked for.
  • Deletion over addition. Boring over clever. Fewest files possible.
  • Bug fix = root cause once, not a patch per caller.
  • Question complex requests: ask if a simpler path covers the need.
  • Mark deliberate corners with a leanlane: comment naming the ceiling and upgrade path.

Safety floor (never cut)

  • Input validation at trust boundaries
  • Error handling that prevents data loss
  • Security-sensitive paths
  • Accessibility for user-facing UI
  • Understanding the problem before shrinking the diff
  • One runnable check for non-trivial logic

CLI / MCP

npm install -g @talocode/leanlane
leanlane decide --task "..."
leanlane score --git
leanlane review --file path
leanlane mcp

Prefer calling leanlane decide (or MCP leanlane_decide) before large writes, and leanlane score --git before finishing a task.

Read the full file on GitHub · 68 lines

Changes

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.

  1. 2d ago First seen · 68 lines · 25 tokens per session scan A 1c5f89b77e13

Subscribe to this mod's changes

leanlane is a skill published in the GitHub repository talocode/leanlane (0 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 585 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens