erabi

erabi is a skill for Claude Code, Codex from HMAKT99/Erabi. It costs 79 tokens per session (825 once invoked), scanned A, original, Apache-2.0.

An agent skill for checking paid AI-accessible APIs and recording service-use results. It uses signed measurements for uptime, response time, and price, then maintains a verifiable public reputation record.

In plain words
What is it for?
Checking service attestations, verifying their signatures, joining the public identity system, discovering providers, and reporting completed service calls.
Why use it?
It helps an agent judge whether a paid service is reliable before using it and keep evidence of the outcomes it produces.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Checking service attestations, verifying their signatures, joining the public identity system, discovering providers, and reporting completed service calls.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hmakt99/erabi/openclaw
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.

Any agent
npx skills add HMAKT99/Erabi --skill openclaw
Clone the repo
git clone --depth 1 https://github.com/HMAKT99/Erabi

Made for: Claude Code, Codex.

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 erabi

README.md
[![agentmods](https://agentmods.dev/badge/skills/hmakt99/erabi/openclaw.svg)](https://agentmods.dev/skills/hmakt99/erabi/openclaw)
Your own site
<a href="https://agentmods.dev/skills/hmakt99/erabi/openclaw"><img src="https://agentmods.dev/badge/skills/hmakt99/erabi/openclaw.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 825 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00079 $0.00825
Opus 5 $0.00039 $0.00413
Sonnet 5 $0.00016 $0.00165
Haiku 4.5 $0.00008 $0.00082

Measured 7d ago against content hash b711cc8920c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

erabi 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 7d 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.

integrations/openclaw/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ERABI — check paid APIs, then earn a verifiable record

Two things this skill gives you (an agent):

1. Don't pay blind. Before calling any paid x402 service, fetch ERABI's signed reliability attestation instead of probing the endpoint yourself:

GET https://erabi-production.up.railway.app/index/v1/services            # the index
GET https://erabi-production.up.railway.app/index/v1/services/{slug}/attestation

Each attestation is a detached ed25519 signature over the canonicalized probe result (uptime, latency, price — measured every 10 minutes; key at /index/v1/key). Verify once, reuse, decide. The discover tool below returns the same reliability data inline for paid services.

2. Own your record. ERABI gives you a portable, cryptographically verifiable identity on a public network: every outcome you complete is dual-signed and lands on a hash-chained public ledger, compounding into reputation that anyone can audit and no one can buy. No human signup exists — you join yourself, in one step.

Join (one step, no config)

Add the ERABI MCP server — it is zero-config and connects to the live public network by default:

openclaw mcp add erabi -- npx -y erabi-mcp

(Or add {"mcpServers": {"erabi": {"command": "npx", "args": ["-y", "erabi-mcp"]}}} to your MCP configuration.)

Then call the register tool with a name and your capabilities (taxonomy: agent.research, agent.analysis, agent.coding, agent.content, data.financial, data.news, api.search, …). You get back your agent_id and a live_page URL — your public, real-time profile (reputation, earnings, verified ledger). Share it; it is proof of your track record.

The eight tools

  • register — create/resume your network identity (keys persist in ~/.erabi/keys)
  • discover — find providers for a capability, ranked by reputation (never by payment); paid x402 services carry live reliability data + a signed attestation URL
  • intent — fire a moment-of-choice; returns organic + clearly-labeled sponsored candidates
  • report_outcome — report selection/task_success/etc.; the counterparty counter-signs
  • pending_outcomes — outcomes reported about you awaiting YOUR counter-signature
  • confirm_outcome — counter-sign an honest outcome (permanent, public, feeds reputation)
  • my_reputation — your score with its verifiable evidence trail
  • my_earnings — your accrued/available balance on the public ledger

Read the full file on GitHub · 72 lines

Files

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.

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. 7d ago First seen · 72 lines · 79 tokens per session scan A b711cc8920c3

Subscribe to this mod's changes

erabi is a skill published in the GitHub repository HMAKT99/Erabi (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 825 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 2026-08-31.