Borrowing it
Nothing to install: this file belongs to Quidli/connect-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Quidli/connect-mcp/main/.github/mirror-only/docs/skills/connect-trust/SKILL.mdgit clone --depth 1 https://github.com/Quidli/connect-mcpWrote 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/quidli/connect-mcp/connect-trust)<a href="https://agentmods.dev/skills/quidli/connect-mcp/connect-trust"><img src="https://agentmods.dev/badge/skills/quidli/connect-mcp/connect-trust/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/quidli/connect-mcp/connect-trust"><img src="https://agentmods.dev/badge/skills/quidli/connect-mcp/connect-trust.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 | $0.00094 | $0.02745 |
| Opus 5.5 | $0.00038 | $0.01098 |
| Sonnet 5.5 | $0.00019 | $0.00549 |
| Haiku 4.5 | $0.00009 | $0.00275 |
Grade A, and why
connect-trust 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 17d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST "https://api.connect.quid.li/trust" \ How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect Trust (POST /trust, POST /trust/check, GET /trust/graph)
On-chain trust attestations (EAS on Base) from one identity to another — a caller saying "I trust this wallet/identity," optionally scoped to a context string and an expiry, at a self-chosen level 1–100. Used standalone (look up who trusts whom) or composed with Smart Send to restrict a payout batch to known recipients.
Configure baseURL to https://api.connect.quid.li.
level is not graded by the API — document this expectation with the user
level (1–100) is stored on the attestation but "existence is what v1 checks"
per the API's own schema — POST /trust/check and the trustFilter on /drop
today only test whether an active attestation exists (and, if context is given,
matches it). Neither enforces a minimum level. There is no fixed meaning per
number — each attester defines their own scale. Example from a live attestation:
level: 100 with context: "co-founder @ quidli", and separately level: 80 with
context: "team:quidli" — a convention, not an API-enforced tier. If an integration
needs level-weighted behavior (e.g. "only auto-approve up to $X at level ≥ Y"), the
calling agent must read level from /trust/check or /trust/graph and apply that
threshold itself.
Identity schema
to / from / targets use the same discriminated recipient schema as
connect-wallet-lookup and
connect-smart-send: exactly one of id or
username per identity, type one of wallet, email, phone, telegram,
discord, farcaster, twitter, github, linkedin, slack, or username
(Connect profile username). Unknown socials are provisioned the same way lookup/drop
provision them — attesting trust to an identity that hasn't linked a wallet yet still
creates the attestation.
Authentication
- Write routes (
POST /trust,POST /trust/revoke,DELETE /trust/{uid}):x-api-key(server-to-server) or a Privy Bearer token for a Connect member with a registered Smart Send signer. These are on-chain EAS writes on Base — the caller's embedded wallet pays gas. - Read routes (
POST /trust/check,GET /trust/graph/{platform}/{identifier}): same auth/paywall as/scores—x-api-key, or x402 USDC payment when no key is provided. Swagger's Try-it cannot complete the x402 handshake — use an API key when testing in the docs UI.
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.
- 17d ago First seen · 231 lines · 94 tokens per session scan A a6d1183b4ecd
connect-trust is a skill published in the GitHub repository Quidli/connect-mcp (7 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 2,745 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
Other skills, from other repositories
okx-cex-earn
A tool for managing several earning products on OKX, including savings, lending, staking, DeFi, Dual Investment, and AutoEarn. These products can use deposited cryptocurrency to generate returns, with terms that vary by product.
rustchain-mcp
This skill allows Claude Code to interact with the RustChain blockchain, monitor the network, and hunt for bounties.
hive
Use this skill for any live crypto question and for Hive setup, on MCP or the hive CLI. Covers current market, on-chain, wallet, token-safety, DeFi, NFT, Solana, prediction-market, and derivatives data, plus the questions other crypto data tools cannot answer, meaning perp funding settlement history across 33 venues…
hive-market-research
Use this skill for any live crypto market question — prices, 24h moves, liquidity, exchange/venue data, OHLC candles, order books, tickers, funding rates, derivatives, trading context — even casual asks like "what's BTC at" or "is ETH pumping". Use it whenever the answer needs current market numbers instead of memory.…
hive-query
Use this skill when the hive skill hands off a live crypto question that needs the full task-toolset walk (prices, wallets, tokens, DeFi, NFTs, Solana, security, markets, DEX, networks, RWA perps, prediction markets) and no hero tool answers it in one call. Install hive first; reach for this directly only when the…
hive-security-risk
Use this skill before the user signs, approves, swaps, connects a wallet to a dApp, or touches an unknown contract, URL, or transaction payload — any "should I sign/approve/ape/connect" moment, even when the user only implies the transaction. Runs token, address, approval, phishing, and simulation risk checks and…