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 commands/solanabr/position-manager-skill/clmm-comparegit clone --depth 1 https://github.com/solanabr/position-manager-skillWrote 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/commands/solanabr/position-manager-skill/clmm-compare)<a href="https://agentmods.dev/commands/solanabr/position-manager-skill/clmm-compare"><img src="https://agentmods.dev/badge/commands/solanabr/position-manager-skill/clmm-compare.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 | $0.00022 | $0.00882 |
| Opus 5 | $0.00011 | $0.00441 |
| Sonnet 5 | $0.00004 | $0.00176 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
clmm-compare 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 5d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/clmm-compare
Fetches and compares fee APR, TVL, and tick-range characteristics for a token pair across all supported venues, then recommends the highest-yield option.
Steps
-
Set environment (compareYields uses venue REST APIs, so no RPC is required for the comparison itself; RPC is only needed if you then read your own positions):
export SOLANA_RPC_URL="https://your-rpc-endpoint" # optional (position reads only) export OWNER_ADDRESS="YourWallet111..." # optional (current-position context) -
Run comparison (pass token MINT addresses, not symbols):
npx tsx -e " import { compareYields } from './skill/templates/yield-compare'; // mintA / mintB are base58 token mints (not symbols). const rows = await compareYields({ mintA: 'So11111111111111111111111111111111111111112', // wSOL mintB: 'EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v', // USDC topN: 5, }); // rows are ranked by feeApr24h descending (rank 1 = best). for (const r of rows) { const apr7 = r.feeApr7d != null ? r.feeApr7d.toFixed(1) + '%' : '--'; console.log(\`#\${r.rank} \${r.venue} \${r.feeBps}bps | 24h APR \${r.feeApr24h.toFixed(1)}% | 7d \${apr7} | TVL \$\${r.tvlUsd.toLocaleString()}\`); } " -
Example output:
#1 meteora 5bps | 24h APR 51.7% | 7d -- | TVL $4,200,000 #2 orca 4bps | 24h APR 42.3% | 7d 40.0% | TVL $18,240,000 #3 kamino 0bps | 24h APR 39.8% | 7d 41.0% | TVL $22,000,000 #4 raydium 5bps | 24h APR 38.1% | 7d 36.0% | TVL $9,100,000 -
Interpret results:
- TVL < $500k -> flag ILLIQUID_RISK; spread may be unreliable
- APR spread > 200 bps between venues with similar IL profile -> migrate
- Meteora DLMM dynamic-fee pools can show elevated short-window APR during high volatility; verify with 30d APR if available
- Kamino APR includes auto-compounding; add ~10-15% effective boost vs manual
-
Act on results:
- To rebalance into the winning venue:
/clmm-rebalance - To assess IL risk first:
/agent lp-risk-analyst - To see current positions:
/clmm-watchor queryfetchPositionsdirectly
- To rebalance into the winning venue:
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.
- 5d ago First seen · 72 lines · 22 tokens per session scan A 9ff592d1e471
clmm-compare is a command published in the GitHub repository solanabr/position-manager-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 882 once invoked, about $0.0001 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 commands, from other repositories
hyperliquid-risk
Mission-critical real-time risk monitoring system with automated alerts, circuit breakers, and emergency shutdown for live Hyperliquid trading by ae.ltd.
swap-quote
Get swap quotes and execute token swaps — same-chain and cross-chain via the Amber aggregator with 10+ DEX/bridge providers (1inch, Jupiter, KyberSwap, THORChain, Stargate, etc.). Use this whenever someone wants to swap tokens, bridge between chains, get a swap quote, compare DEX rates, or execute any kind of token…
global-flags
Cryptocurrency wallet for trading for Bitcoin, Bitcoin cash, Ethereum, ERC20, XRP Leger (Ripple).
swap
Command "swap" from Swap-API/swap-api, covering step 1: gather inputs, step 2: fetch quote, step 3: parse and present, step 4: pre-flight checks and step 5: show execution.
pay
Universal Crypto MCP API Reference v1.0.0.
crypto_price_check_agent_prompt
You are a simple cryptocurrency price checker focused on retrieving current prices for specific cryptocurrencies.