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.
/plugin marketplace add sup3x/claude-code-econpx agentmods add plugins/sup3x/claude-code-eco/marketplacegit clone --depth 1 https://github.com/sup3x/claude-code-ecoGrade A, and why
claude-eco 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.
What it actually says
{
"name": "claude-eco",
"description": "Token-frugality tooling for Claude Code, published with 82 raw benchmark runs including the negative ones.",
"owner": {
"name": "Kerim",
"url": "https://github.com/sup3x"
},
"plugins": [
{
"name": "claude-eco",
"source": "./",
"description": "Eco mode for Claude Code: /eco and /eco-max skills, an Eco output style, /eco audit and /eco report, and opt-in enforcement hooks. Measured -35% to -57% output tokens across four Claude models on one task (n=5 per arm) and up to -73% on long agentic tasks, with both planted bugs found in every run (267 raw runs published, negative results included); eco-max also lowers reasoning effort - a lever no other terse-mode tool touches.",
"version": "1.2.1",
"license": "MIT",
"homepage": "https://github.com/sup3x/claude-code-eco#readme",
"category": "productivity",
"tags": [
"tokens",
"cost",
"efficiency",
"eco",
"effort"
]
}
]
}
What ships with it
1 file beside marketplace.json 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.
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 · 27 lines scan A 3dbcb49283e6
claude-eco is a plugin published in the GitHub repository sup3x/claude-code-eco (33 stars, last pushed 16d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
llm-router
Smart LLM routing with Claude subscription monitoring, complexity-first model selection, and 20+ AI providers.
claude-cost-optimizer
Plugin marketplace listing 1 plugin: cost-mode.
stuntman
Claude doesn't do its own stunts. Plan with Claude, execute with a near-free model (DeepSeek, Groq, Ollama, Grok, Kimi… via a local proxy or opencode), OpenAI's Codex CLI, Google's Antigravity CLI (agy), or Meta's Muse Code CLI, review with Claude — your subscription tokens go only where intelligence matters.
attune-ai
Plugin marketplace listing 2 plugins: attune-ai, attune-help.
stuntman
Plugin marketplace listing 1 plugin: stuntman.
model-routing
Plugin marketplace listing 1 plugin: model-routing.