Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Institut-du-Numerique-Responsable/green-claudenpx agentmods add skills/institut-du-numerique-responsable/green-claude/green-claudeWrote 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.
[](https://agentmods.dev/skills/institut-du-numerique-responsable/green-claude/green-claude)<a href="https://agentmods.dev/skills/institut-du-numerique-responsable/green-claude/green-claude"><img src="https://agentmods.dev/badge/skills/institut-du-numerique-responsable/green-claude/green-claude/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.
<a href="https://agentmods.dev/skills/institut-du-numerique-responsable/green-claude/green-claude"><img src="https://agentmods.dev/badge/skills/institut-du-numerique-responsable/green-claude/green-claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 120 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00125 | $0.03403 |
| Opus 5 | $0.00063 | $0.01702 |
| Sonnet 5 | $0.00025 | $0.00681 |
| Haiku 4.5 | $0.00013 | $0.00340 |
Grade A, and why
green-claude scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
SKILL_DIR="$(ls -d "$HOME"/.claude/skills/green-claude \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Green Claude
What this skill is for. Deliver code that consumes as little as possible: the fewest tokens during the session, the least CPU time and memory at runtime, the fewest bytes over the network, the least storage, and therefore the least energy. That is what digital sobriety means in practice, and it is the reason every rule below exists. A rule that does not eventually reduce a resource someone pays for is not worth the context it takes.
The consumption comes in two waves, and the second is the larger one. During the session, the context you transmit and the output you produce are processed by a model, which costs computation and the energy behind it. After the session, the code you leave behind runs on every user's machine, on every request, for years. Both matter; only one of them stops when the conversation does.
Three rule sets: rules/ecoconception.json (107 rules, RGESN 2024 / GR491 /
Green Software Foundation / W3C WSG) while you write or modify code,
rules/langages/*.json (127 rules across 24 languages and frameworks) for the language you're
working in, and rules/usage.json (16 responsible-use practices) during the
conversation itself. Using Claude Code efficiently is also using it soberly.
Quick reference
| Mode | Trigger | Action |
|---|---|---|
| Proactive (default) | Always, as soon as you write or modify code | Apply the relevant families from ecoconception.json, unprompted |
| Audit | "eco-design audit", "check the sobriety", --eco-check |
bash "$SKILL_DIR/scripts/eco-audit.sh" file1 file2 ... (see Finding the scripts) |
| Browse | /green-claude |
Full checklist of the 9 RGESN families + 16 responsible-use practices |
Before you write anything
Three rules decide what gets written at all, which makes them worth more than every optimisation that follows. A function tuned to perfection still costs everything it cost if it had no reason to exist.
Ask when the answer changes the work (USAGE-BRIEF-03). Name the assumption
that would reshape the task if it were wrong. If it is genuinely ambiguous, ask
that one question and wait. If it is not, state the assumption in a line and
build. One blocking question beats four that the repository could have answered.
What ships with it
44 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.
- rules/ecoconception.json 126 KB
- rules/langages/angular.json 4.2 KB
- rules/langages/astro.json 3.1 KB
- rules/langages/c.json 5.0 KB
- rules/langages/cpp.json 5.0 KB
- rules/langages/csharp.json 6.5 KB
- rules/langages/go.json 7.4 KB
- rules/langages/java.json 6.5 KB
- rules/langages/javascript.json 9.1 KB
- rules/langages/julia.json 3.7 KB
- rules/langages/kotlin.json 5.8 KB
- rules/langages/nim.json 3.4 KB
- rules/langages/php.json 5.7 KB
- rules/langages/python.json 8.6 KB
- rules/langages/react.json 4.7 KB
- rules/langages/ruby.json 5.5 KB
- rules/langages/rust.json 5.7 KB
- rules/langages/scala.json 3.8 KB
- rules/langages/shell.json 6.3 KB
- rules/langages/solid.json 3.4 KB
- rules/langages/sql.json 8.7 KB
- rules/langages/svelte.json 2.8 KB
- rules/langages/swift.json 6.1 KB
- rules/langages/vue.json 3.0 KB
- rules/langages/zig.json 2.7 KB
- rules/usage.json 20 KB
- scripts/audit-common.sh 871 B runs code
- scripts/detect-blocking-scripts.awk 1.2 KB
- scripts/detect-broken-links.awk 2.3 KB
- scripts/detect-css-duplicates.awk 2.2 KB
- scripts/detect-css-importants.awk 686 B
- scripts/detect-dead-code.awk 5.5 KB
- scripts/detect-dom-size.awk 2.1 KB
- scripts/detect-duplicate-ids.awk 1.5 KB
- scripts/detect-implicit-globals.awk 1.6 KB
- scripts/detect-insecure-links.awk 1.1 KB
- scripts/detect-nested-loops.awk 1.5 KB
- scripts/detect-reduced-motion.awk 1.3 KB
- scripts/eco-audit.sh 22 KB runs code
- scripts/eco-score.sh 3.4 KB runs code
- scripts/inspect-fonts.sh 6.5 KB runs code
- scripts/inspect-image.sh 2.0 KB runs code
- scripts/package-skill.sh 3.1 KB runs code
- scripts/test-eco-audit.sh 55 KB runs code
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 Changed · +3 lines bf41a2be8b8e
- 5d ago Changed · +174 lines 4d53fb11aa9a
- 11d ago First seen · 108 lines · 125 tokens per session scan A e6957cfc8491
green-claude is a skill published in the GitHub repository Institut-du-Numerique-Responsable/green-claude (46 stars, last pushed 3d ago), licensed MIT. It adds 125 tokens to every session and 3,403 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sustainability-checks
Evaluate software architecture for ESG and sustainability impact.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…