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.
npx skills add Vitalini/ebb-ai --skill openclaw-skillgit clone --depth 1 https://github.com/Vitalini/ebb-aiWrote 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/vitalini/ebb-ai/openclaw-skill)<a href="https://agentmods.dev/skills/vitalini/ebb-ai/openclaw-skill"><img src="https://agentmods.dev/badge/skills/vitalini/ebb-ai/openclaw-skill/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/vitalini/ebb-ai/openclaw-skill"><img src="https://agentmods.dev/badge/skills/vitalini/ebb-ai/openclaw-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00134 | $0.01473 |
| Opus 5.5 | $0.00054 | $0.00589 |
| Sonnet 5.5 | $0.00027 | $0.00295 |
| Haiku 4.5 | $0.00013 | $0.00147 |
Grade A, and why
ebb-ai 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ebb-ai — Carbon-aware scheduling
This skill connects OpenClaw to a local @ebb-ai/mcp server that
schedules AI tasks to run during the cleanest available electricity-grid
window inside a user-supplied deadline.
When to invoke
Use this skill when the user wants to:
- Defer a non-urgent AI task to run later for environmental or
cost reasons. Examples:
- "Summarize these 50 articles by tomorrow morning, run it overnight."
- "Don't do it now — wait for when the grid is clean."
- "Schedule the GitHub digest for 3 AM."
- Inspect grid carbon intensity before deciding whether to run a
task. Examples:
- "Is now a good time to run an expensive batch?"
- "When will the California grid be cleanest in the next 12 hours?"
- Audit the carbon cost of recent agent activity. Examples:
- "How much CO₂ did my agents use today?"
- "Show me the carbon receipt for that last summary."
Do not invoke this skill for:
- Tasks the user wants done immediately.
- Tasks where the user has no preference about timing.
- General climate / energy questions unrelated to AI compute.
Prerequisites
The @ebb-ai/mcp server must be registered as an MCP server in
OpenClaw. See scripts/install.sh for a one-shot installer that does
this. Manual install:
- Build the server:
cd /path/to/ebb-ai && pnpm install && pnpm build - Add to
~/.openclaw/mcp.json:{ "mcpServers": { "ebb-ai": { "command": "node", "args": ["/abs/path/to/ebb-ai/packages/mcp-server/dist/server.js"], "env": { "EBB_ELECTRICITY_MAPS_API_KEY": "optional", "EBB_DEFAULT_REGION": "US-CAL-CISO" } } } } - Restart OpenClaw.
Tools available
Once the MCP server is connected, three tools become callable:
get_grid_forecast(region, hours?)
Returns hourly carbon intensity for the next 1-72 hours. Use this to answer "when is the cleanest window?" questions.
What ships with it
1 file 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.
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.
- 2mo ago First seen · 153 lines · 134 tokens per session scan A 9c9cf47a00ab
ebb-ai is a skill published in the GitHub repository Vitalini/ebb-ai (1 stars, last pushed 24d ago), licensed Apache-2.0. It adds 134 tokens to every session and 1,473 once invoked, about $0.0005 per session on Opus 5.5. 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.
ebb-ai compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ebb-aiVitalini/ebb-ai | Skill | 1 | 24d ago | Apache-2.0 | A | 134 | Claude Code, Codex |
| fastmcp-client-cliPrefectHQ/fastmcp | Skill | 28k | today | Apache-2.0 | A | 46 | Claude Code, Codex |
| code-reviewPrefectHQ/fastmcp | Skill | 28k | today | Apache-2.0 | A | 13 | Claude Code, Codex |
| observal-adminObserval/Observal | Skill | 4.3k | today | Apache-2.0 | A | 92 | Claude Code, Codex |
| beaconing-reviewVigil-SOC/vigil | Skill | 426 | today | Apache-2.0 | A | 51 | Claude Code, Codex |
| phishing-triageVigil-SOC/vigil | Skill | 426 | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| rdp-lateral-movementVigil-SOC/vigil | Skill | 426 | today | Apache-2.0 | A | 57 | Claude Code, Codex |