more-with-less

more-with-less is a skill for Claude Code, Codex from gustavo-meilus/aiboarding. It costs 85 tokens per session (1,769 once invoked), scanned A, original, MIT.

An engineering approach based on building the smallest system that fully meets the requirements. It applies this idea to coding, design, debugging, architecture, dependencies, automation, and verification.

In plain words
What is it for?
Use it when making a non-trivial project decision or change. It helps choose simpler designs, reuse existing parts, limit moving pieces, and remove complexity that evidence shows is no longer needed.
Why use it?
It helps prevent unnecessary complexity, extra tools, and unused code while keeping important correctness and security guarantees. It also encourages checking the existing project before adding something new.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; mentions Codex.

Part of the aiboarding plugin — 17 skills, 11 commands, 4 hooks shipped together

Good fit Use it when making a non-trivial project decision or change. It helps choose simpler designs, reuse existing parts, limit moving pieces, and remove complexity that evidence shows is no longer needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gustavo-meilus/aiboarding/more-with-less
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.

Any agent
npx skills add gustavo-meilus/aiboarding --skill more-with-less
Clone the repo
git clone --depth 1 https://github.com/gustavo-meilus/aiboarding

Made for: Claude Code, Codex.

Or install aiboarding, the plugin that ships this one along with the rest of its 17 skills, 11 commands, 4 hooks.

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 more-with-less

README.md
[![agentmods](https://agentmods.dev/badge/skills/gustavo-meilus/aiboarding/more-with-less/github.svg)](https://agentmods.dev/skills/gustavo-meilus/aiboarding/more-with-less)
Your own site
<a href="https://agentmods.dev/skills/gustavo-meilus/aiboarding/more-with-less"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/aiboarding/more-with-less/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for more-with-less

Your own site · 80×15
<a href="https://agentmods.dev/skills/gustavo-meilus/aiboarding/more-with-less"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/aiboarding/more-with-less.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,769 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00085 $0.01769
Opus 5 $0.00043 $0.00885
Sonnet 5 $0.00017 $0.00354
Haiku 4.5 $0.00009 $0.00177

Measured 9d ago against content hash 4e5b74309008, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

more-with-less 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 9d 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.

.agents/skills/more-with-less/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

More With Less Engineering

Use this Skill as the default design and implementation lens for non-trivial project work.

The objective is not minimum code, files, tokens, tools, agents, or tests independently. The objective is the minimum sufficient system that reliably satisfies the real requirements and preserves required guarantees.

Core doctrine

Do the least that fully solves the real problem. Use the least powerful sufficient mechanism. Keep active context, authority, tools, state, agents, handoffs, and orchestration as small as practical. Preserve the guarantees that matter. Hide unavoidable complexity behind stable interfaces. Add complexity only when evidence shows the simpler system is insufficient, and remove it when that evidence no longer holds.

Mandatory operating rules

  1. Understand before simplifying. Inspect the relevant code, docs, behavior, callers, constraints, and existing guarantees before choosing the smaller solution.
  2. Solve the real requirement. Prefer outcome and acceptance criteria over user-prescribed implementation choreography unless the implementation method is itself a requirement.
  3. Delete or reuse before adding. Prefer existing project capability, language/runtime facilities, native platform behavior, installed dependencies, and deterministic scripts before new machinery.
  4. Use the least powerful sufficient mechanism. Prefer deterministic code, schemas, tests, linters, type systems, DB constraints, and scripts before model judgment or orchestration when they can decide the property reliably.
  5. Keep context progressive. Load only the information required for the current decision. Do not dump the whole repository, spec corpus, or this full playbook into context without need.
  6. One agent by default. Add a reviewer/specialist only for independent judgment, context isolation, different authority, specialized expertise, or useful parallelism.
  7. Minimize the tool and permission surface. Give the current task only the capabilities needed to understand, act, observe, and verify.
  8. Make specification proportional. Spec depth grows with uncertainty, consequence, and coordination. Do not force proposal/design/task ceremony onto trivial work.
  9. Make verification proportional. Use the minimum evidence sufficiently strong for the consequence of failure. Keep the oracle stronger than the generator.
  10. Never simplify away critical guarantees. Preserve trust-boundary validation, security, authorization, data integrity, accessibility, irreversible-operation safeguards, required architecture invariants, acceptance criteria, rollback/recovery, necessary observability, and explicit requirements.
  11. Prefer root-cause fixes. For bugs, reproduce when feasible, trace the real path, and fix the shared cause rather than patching symptoms repeatedly.
  12. Design for deletion. For non-trivial new harness or architecture mechanisms, know why they exist, what would prove them insufficient, and what would allow them to be removed.

Read the full file on GitHub · 193 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 193 lines · 85 tokens per session scan A 4e5b74309008

Subscribe to this mod's changes

more-with-less is a skill published in the GitHub repository gustavo-meilus/aiboarding (2 stars, last pushed 12d ago), licensed MIT. It adds 85 tokens to every session and 1,769 once invoked, about $0.0004 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.