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 | $0.00067 | $0.00737 |
| Sonnet 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 8d 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.
- 8d 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 28d ago), licensed Apache-2.0. It adds 134 tokens to every session and 1,473 once invoked, about $0.0007 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.
Other skills, from other repositories
fastmcp-client-cli
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.
observal
Operates the Observal CLI for authentication, configuration, setup diagnosis, teamspaces, inbox work, scans, update checks, and authenticated API access. Use when the user wants to log in, configure Observal, inspect local harness setup, manage a teamspace or invitation, process inbox items, check installed registry…
observal-admin
Administers Observal users, settings, diagnostics, review queues, security events, audit logs, SAML, SCIM, local server services, upgrades, rollback, and database migrations. Use when the user needs privileged governance, submission decisions, identity configuration, security investigation, or server operations.
observal-agents
Creates, authors, validates, publishes, updates, versions, pulls, archives, restores, transfers, and manages co-authors for Observal Agents. Use when the user wants to build or install an Agent, change an Agent definition, publish a draft, release a version, or manage Agent ownership.
observal-registry
Searches, recommends, bulk-submits, installs, edits, versions, archives, restores, transfers, and manages co-authors for Observal MCP servers, skills, hooks, prompts, and sandboxes. Use when the user wants to find components, publish one or many they control, install them into a harness, or manage their lifecycle.
observal-advanced
Recovers Observal session ingestion, manages CLI upgrades, downgrades and rollback, and performs explicit local Agent fallback when the server is unavailable. Use when the user asks to reconcile missed sessions, repair CLI version state, or continue locally after a confirmed connection or configuration failure.