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 grokloop/grokchain-mcp --skill grok-buildgit clone --depth 1 https://github.com/grokloop/grokchain-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/grokloop/grokchain-mcp/grok-build)<a href="https://agentmods.dev/skills/grokloop/grokchain-mcp/grok-build"><img src="https://agentmods.dev/badge/skills/grokloop/grokchain-mcp/grok-build.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.03028 |
| Opus 5 | $0.00022 | $0.01514 |
| Sonnet 5 | $0.00009 | $0.00606 |
| Haiku 4.5 | $0.00004 | $0.00303 |
Grade A, and why
Grok Build 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grok Build
Talk to Grok Chain through the official MCP. Tools are intents. You never hold keys. You never hold SOL.
Tool names
Use these names. Do not drop to raw Solana unless the human asked you to debug.
| Intent | Who signs | What it is |
|---|---|---|
create_account |
human root | Open the GrokAccount PDA |
issue_grant |
human root | Authorize an agent pubkey. Router-mode allowlist = INTENTS id for this cluster (local-only on localnet; EYhYtq… on devnet). |
revise_grant |
human root | Replace policy on that grant |
revoke_grant |
human root | Mark the grant revoked |
check_grant |
agent | Consume path. Increments spent_lamports. Does not move SOL. |
pay |
agent signs; relayer fee-pays | Implemented INTENTS client. localnet: local-only INTENTS id. devnet: grokchain-devnet INTENTS id. Human-funded SpendVault → recipient. Bot never holds SOL. |
swap |
agent signs; relayer fee-pays | Grant-gated SOL send with min_out. Not a DEX. Not Jupiter. Not SPL. Unchanged. |
token_buy / token_sell |
agent signs; relayer fee-pays | Grant-gated Jupiter v6. Quote mint may be WSOL, USDC, or another mint. remaining from Jupiter swap-instructions. Trader PDA is user. Old swap is still the SOL send. |
deploy |
agent signs; relayer fee-pays | check_grant(0) + DeployRequested. Not a BPF deploy. No ELF. |
call |
agent signs; relayer fee-pays | Grant-gated router. amount 0 = policy ping. CORE allowlists INTENTS, not the inner target. |
pump_buy / pump_sell / pump_create |
— | Cut from live MAINNET INTENTS (size). Do not send. Graduated coins use token_buy / token_sell. |
pump_amm_buy / pump_amm_sell |
— | Cut from live MAINNET INTENTS (size). Do not send. Jupiter token_buy / token_sell still reach graduated pump coins. |
get_account / get_grant |
none | Optional reads |
CORE + INTENTS by cluster
- localnet: CORE
8WDhHSfrz6hMkmX7WteAAmyuWFLryHM2Kfc1r4k8EFXEand INTENTSAXprcURLhSqj35v9DJyBkTSPGSoZ9AfTRxYyguQJwnT2. Local-only. Not a deployed program. Not on devnet. Not on mainnet. Never present them as a shipped deployment. - devnet: CORE
7UtafKBBWNHEXC9PaNXu8USdZqL6VEWupsL7rS6LeVDjand INTENTSEYhYtqLViS4H3FNt1Q8nGRHGt9oD87uaNsV2WJMNiRkzare the grokchain-devnet deployed programs. - mainnet-beta: CORE
44fxwzuEyNxZtgDr87mTtMYYJ1LJm6cB5aZNLyBsPjNdand INTENTS3HCErAFs93FMk2J25Qq1xRRMp6B4FyGvif8ZV8hYxQKw(pay, pay_token, merchant registry, subscriptions, token_buy/token_sell, swap, deploy, call, init/fund/withdraw_pump_trader). Pump trade ixs are off this binary. - Do not invent a program id.
- Never use the local-only pair on devnet or mainnet. Config refuses them.
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 · 156 lines · 44 tokens per session scan A ad069a293f47
Grok Build is a skill published in the GitHub repository grokloop/grokchain-mcp (1 stars, last pushed 9d ago), licensed MIT. It adds 44 tokens to every session and 3,028 once invoked, about $0.0002 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
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).