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 agentmods add skills/quiknode-labs/blockchain-skills/quicknode-skillnpx skills add quiknode-labs/blockchain-skills --skill quicknode-skillgit clone --depth 1 https://github.com/quiknode-labs/blockchain-skillsWhat 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 | $0.00093 | $0.11998 |
| Opus 5 | $0.00046 | $0.05999 |
| Sonnet 5 | $0.00019 | $0.02400 |
| Haiku 4.5 | $0.00009 | $0.01200 |
Grade B, and why
quicknode-skill scanned grade B with 2 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 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const response = await client.fetch("https://x402.quicknode.com/ethereum-mainnet", { method: "POST", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST 'https://api.quicknode.com/sql/rest/v1/query' \ How it starts
The opening of the file, as written. The whole thing — 1,141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quicknode Blockchain Infrastructure
Intake Questions
- Which chain and network should Quicknode target?
- Is this read-only or should I create infrastructure (streams, webhooks, IPFS writes)?
- Does this require real-time streaming (Solana gRPC/Blazar WSS/HyperCore gRPC) or standard RPC?
- What endpoint or API key should I use (default:
QUICKNODE_RPC_URL, optionalQUICKNODE_WSS_URL/QUICKNODE_API_KEY)? - If no API key exists, does the agent want pay-per-request access (x402, MPP) or a wallet-paid Quicknode account via Agent Subscriptions?
- Any constraints (latency, regions, throughput, destinations)?
Safety Defaults
- Default to testnet/devnet when a network is not specified.
- Prefer read-only operations and dry runs before creating resources.
- Never ask for or accept private keys or secret keys.
Confirm Before Write
- Require explicit confirmation before creating or modifying Streams, Webhooks, or IPFS uploads.
- Require explicit confirmation before creating an Agent Subscription, topping up credits, or any action that spends real funds via x402 or MPP.
- If confirmation is missing, return the exact API payload for review.
Quick Reference
Infrastructure
| Product | Description | Use Case |
|---|---|---|
| Core RPC API | High-performance blockchain access for 80+ chains | dApp backend, wallet interactions |
| Dedicated Clusters | Dedicated private node clusters | High-throughput production, compliance isolation |
| IPFS | Decentralized file storage | NFT metadata, asset hosting |
Real-Time Data
| Product | Description | Use Case |
|---|---|---|
| Streams | Real-time & historical blockchain data pipelines | Event monitoring, analytics, indexing |
| Streams Backfills | On-demand historical data backfill into Streams | Gap recovery, historical re-indexing |
| Webhooks | Event-driven notifications | Alerts, transaction monitoring |
| Solana gRPC | Solana Geyser streaming — included on Scale/Business, add-on on Build/Accelerate | Real-time account, transaction, slot data |
| Blazar WSS | Quicknode-built Solana WebSocket engine — all plans, free | Fast block, account, transaction, and slot subscriptions |
| HyperCore gRPC | gRPC streaming for Hyperliquid L1 — included on all paid plans | Trades, order book diffs, events, blocks in real time |
What ships with it
24 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.
- PRODUCT_CATALOG.md 10 KB
- references/addons.md 4.4 KB
- references/admin-api-reference.md 15 KB
- references/agent-identity-reference.md 6.1 KB
- references/agent-subscriptions-reference.md 5.9 KB
- references/blockbook-reference.md 4.6 KB
- references/cli-reference.md 21 KB
- references/hypercore-hyperliquid-reference.md 18 KB
- references/ipfs-reference.md 9.1 KB
- references/kv-reference.md 4.2 KB
- references/mcp-reference.md 6.3 KB
- references/metaplex-das-reference.md 13 KB
- references/mpp-reference.md 12 KB
- references/ordinals-runes-reference.md 6.1 KB
- references/rpc-reference.md 24 KB
- references/sdk-reference.md 15 KB
- references/solana-das-api-reference.md 16 KB
- references/solana-grpc-reference.md 15 KB
- references/sql-explorer.md 83 KB
- references/streams-backfills-reference.md 4.2 KB
- references/streams-reference.md 11 KB
- references/swap-api-reference.md 9.0 KB
- references/webhooks-reference.md 12 KB
- references/x402-reference.md 13 KB
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 First seen · 1,141 lines · 93 tokens per session scan B 2e2b3a961854
quicknode-skill is a skill published in the GitHub repository quiknode-labs/blockchain-skills (18 stars, last pushed 20d ago), licensed MIT. It adds 93 tokens to every session and 11,998 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
run-evals
Run a full eval round on stellar-raven-codemode from Codex, Claude Code, or another CLI agent — pick the right instruments (routing gate, QA headline, agentic, plan, live-data), distinguish the orchestrating agent from the spawned answering and judge agents, record results, review every answer/verdict, triage failures…
live-drift-resolution
Resolve a "Live service drift detected" issue — the daily CI that diffs the committed catalog against the live upstream surfaces (Lumenloop, Stellar Light/Scout, Stellar Docs). Regenerate the artifacts, classify the drift, decide whether it needs a policy or routing-baseline change or is a clean mechanical bump…
cloudflare-observability-review
Investigate live Cloudflare Workers observability for stellar-raven-codemode. Use when reviewing production MCP request logs, playground/demo telemetry, traces, Ray IDs, request headers, telemetry query results, eval observability, agent-run forensics, or whether Cloudflare metadata is enough without app-level…
golden-truth
Change the golden Q→A corpus without codifying lies: classify the truth domain, triangulate across independent source classes, encode disputed or unverifiable facts honestly, and land provenance-bearing edits to the owned per-case corpus. Use when editing eval golden answers, key facts, avoid clauses, sources, grader…
improvements-pipeline
Maintain the improvements/ upstream-findings pipeline for stellar-raven-codemode. Use when filing or updating service-improvement findings, resolving intake targets, maintaining improvements/intake.json, interpreting improvements lint failures, running recurrence probes, regenerating improvements/INDEX.md, reviewing…
truth-maintenance
Coordinate a full truth-maintenance pass for stellar-raven-codemode across live drift, evals, golden questions/answers, and improvements/issues/PR follow-up. Use when asked to ensure repo truth is current, review the current state of upstream findings or PRs the repo opened, run a multi-lane maintenance round, or…