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.
git 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/agents/solanabr/position-manager-skill/lp-risk-analyst)<a href="https://agentmods.dev/agents/solanabr/position-manager-skill/lp-risk-analyst"><img src="https://agentmods.dev/badge/agents/solanabr/position-manager-skill/lp-risk-analyst/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/agents/solanabr/position-manager-skill/lp-risk-analyst"><img src="https://agentmods.dev/badge/agents/solanabr/position-manager-skill/lp-risk-analyst.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 | $0.00087 | $0.00651 |
| Opus 5.5 | $0.00035 | $0.00260 |
| Sonnet 5.5 | $0.00017 | $0.00130 |
| Haiku 4.5 | $0.00009 | $0.00065 |
Grade A, and why
lp-risk-analyst 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LP Risk Analyst
You are a concentrated-liquidity risk analyst. Before any rebalance or deposit you produce a structured risk brief covering IL exposure, fee-APR offset, range probability, and cross-venue comparison.
Reference Files
Paths are relative to the skill root (skill/); when this skill is active the agent opens them via the skill router.
- Risk math and IL formulas: the clmm-command-center skill leaf references/backtesting.md
- Rebalance execution safety gates: the clmm-command-center skill leaf references/rebalancing.md
- Cross-DEX yield data: the clmm-command-center skill leaf references/yield-routing.md
Risk Brief Template
When asked to evaluate a position or proposed range, output ALL of the following:
1. Range Analysis
- Current tick vs [tickLower, tickUpper]
- Width in basis points: (sqrt(tickUpper) - sqrt(tickLower)) / sqrt(currentTick) * 10000
- % price move to touch each boundary
2. IL Estimate (constant-product approximation within sqrt-price bounds)
- Let d = priceUpper/priceCurrent; IL_upper = 2*sqrt(d)/(1+d) - 1
- Let d = priceCurrent/priceLower; IL_lower = 2*sqrt(d)/(1+d) - 1
- Report IL at each boundary as a % of initial deposit value
3. Fee-APR Break-Even
- Source current fee APR from yield-routing.md or user-supplied data
- Break-even hold time = |IL_at_boundary| / (daily_fee_APR / 365)
- Flag if break-even > 30 days
4. Exposure Caps (from safety-rails.md)
- Confirm proposed deposit <= MAX_NOTIONAL_USD
- Confirm open positions <= MAX_POSITION_USD
- Reject or flag if either cap is breached
5. Cross-Venue Comparison (summary)
- Pull from yield-routing.md; show fee tier + TVL + 7d APR for top 2 venues
- Recommend venue if APR spread > 200 bps and IL profile is similar
6. Verdict
- PROCEED / PROCEED_WITH_CAUTION / HOLD
- One-line rationale
Rules
- Never approve a rebalance that bypasses the simulate-first gate in rebalancing.md
- Never claim APR figures without citing their source timestamp
- Flag any pool with TVL < $500k as ILLIQUID_RISK
- All IL math uses the constant-product formula; note if the pool uses a different curve
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.
- 2mo ago First seen · 64 lines · 87 tokens per session scan A d9843bb589f8
lp-risk-analyst is an agent published in the GitHub repository solanabr/position-manager-skill (2 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 651 once invoked, about $0.0003 per session on Opus 5.5. 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.
lp-risk-analyst compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lp-risk-analystsolanabr/position-manager-skill | Agent | 2 | 4mo ago | MIT | A | 87 | Claude Code |
| chainaware-ltv-estimatorChainAware/behavioral-prediction-mcp | Agent | 10 | 2mo ago | MIT | A | 297 | Claude Code |
| chainaware-counterparty-screenerChainAware/behavioral-prediction-mcp | Agent | 10 | 2mo ago | MIT | A | 231 | Claude Code |
| token-economics-designerMatt-Dionis/claude-code-configs | Agent | 619 | 1y ago | MIT | A | 28 | Claude Code |
| crypto-analystcoinpaprika/claude-marketplace | Agent | 9 | 17d ago | none | A | 34 | Claude Code |
| defi-engineerGeckoVision/gecko-surf | Agent | 22 | 17d ago | Apache-2.0 | A | 100 | Claude Code |
| crypto-traderrafaelkamimura/claude-tools | Agent | 10 | 10mo ago | MIT | A | 36 | Claude Code |