eco-max

eco-max is a skill for Claude Code, Codex from sup3x/claude-code-eco. It costs 71 tokens per session (946 once invoked), scanned A, original, MIT.

A maximum-savings session mode for routine coding tasks, with reduced reasoning effort and concise output.

In plain words
What is it for?
Use it for small fixes, renames, quick questions, or boilerplate when minimum token spending matters.
Why use it?
It cuts token use for simple work, while warning you when a task is too difficult or risky for this mode.

Skill for Claude CodeCodex

Part of the claude-eco plugin — 4 skills, 1 agent shipped together

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/sup3x/claude-code-eco/eco-max
Any agent
npx skills add sup3x/claude-code-eco --skill eco-max
Clone the repo
git clone --depth 1 https://github.com/sup3x/claude-code-eco

Made for: Claude Code, Codex.

Or install claude-eco, the plugin that ships this one along with the rest of its 4 skills, 1 agent.

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 eco-max

README.md
[![agentmods](https://agentmods.dev/badge/skills/sup3x/claude-code-eco/eco-max.svg)](https://agentmods.dev/skills/sup3x/claude-code-eco/eco-max)
Your own site
<a href="https://agentmods.dev/skills/sup3x/claude-code-eco/eco-max"><img src="https://agentmods.dev/badge/skills/sup3x/claude-code-eco/eco-max.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 946 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 $0.00071 $0.00946
Opus 5 $0.00036 $0.00473
Sonnet 5 $0.00014 $0.00189
Haiku 4.5 $0.00007 $0.00095

Measured 4d ago against content hash 6a9cfd1d232d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eco-max 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 4d 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/eco-max/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eco-Max — minimum-token execution for this task

The /eco rules at low reasoning effort. If brevity ever conflicts with correctness, correctness wins. Always reply in the user's language.

Two things to know before using it: the effort override is part of the prompt-cache key, so switching to /eco-max deep into a long session makes the next turn re-read the whole conversation uncached — it pays off at session start or in short sessions. And this mode is for routine work: if the task turns out to be genuinely hard or high-stakes, say so in one line and recommend plain /eco rather than guessing.

Quality floor (non-negotiable)

  • Read code before changing it; verify and test when the task calls for it.
  • Never truncate deliverables (code, configs, docs the user asked for). When the deliverable is a list — review findings, bugs, options, affected files — completeness is part of correctness: report every item you found, then compress each to one line. Brevity shortens items, never the list.
  • Create no files nobody asked for — no summary documents, no unrequested smoke tests, no scratch scripts left behind.
  • If you notice a correctness-critical problem (crash, data loss, security hole) while working, say so in one line even if it wasn't asked about — that is the one thing you always volunteer. Suppress noise, never warnings.

Replies (output tokens are the costliest)

  • Lead with the answer. No preamble, no restating the request, no closing recap.
  • Aim for ≤6 lines of prose (code excluded); expand only when correctness or clarity requires it, or the user asks for detail. Never pad, never repeat yourself.
  • Never paste back content you just wrote with Edit/Write; cite path:line instead. When discussing code, quote at most ~5 lines.
  • One recommended solution, not a menu of alternatives. No headers/tables/bullet ceremony for short answers. Skip task-list ceremony for small tasks.
  • In long sessions: no unprompted progress recaps or running summaries — report once, at the end.

Read the full file on GitHub · 49 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. 4d ago First seen · 49 lines · 71 tokens per session scan A 6a9cfd1d232d

Subscribe to this mod's changes

eco-max is a skill published in the GitHub repository sup3x/claude-code-eco (33 stars, last pushed 19d ago), licensed MIT. It adds 71 tokens to every session and 946 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 2026-08-30.

Related

Other skills, from other repositories

lynkr

Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.

Fast-Editor/Lynkr · 50 tokens

uncommonroute-release

Use when publishing UncommonRoute. A release is only complete after all required steps are done: version sync, validation, GitHub push/tag/release, PyPI publish, and npm publish.

CommonstackAI/UncommonRoute · 44 tokens

elicit

Form-driven Socratic discovery — batch independent decision dimensions into one multi-select-capable form instead of N button-turns. Triggers on: scope this, discovery form, ask me everything at once, multi-select question.

Smart-AI-Memory/attune-ai · 48 tokens

roundtable

Convene the multi-LLM round table — Claude, Antigravity, and Codex deliberate a question; the user chairs promotion. Triggers on: roundtable, round table, convene the table, ask the table, what do the other models think, deliberate.

Smart-AI-Memory/attune-ai · 59 tokens

spec

Spec Ladders — goal-driven spec development: brainstorm, plan, review, and execute a gated task ladder with recorded approvals. Triggers on: spec, spec ladders, brainstorm and build, plan and execute, idea to code, build from scratch.

Smart-AI-Memory/attune-ai · 54 tokens

author-feature

Author a single-source feature page — a code-verified master that projects to .help kinds + docs pages, no API credits. Triggers on: author a feature page, single-source doc, new feature master, draft docs without an api.

Smart-AI-Memory/attune-ai · 52 tokens