agentmods.dev

risk-officer

risk-officer is an agent for Claude Code from deonmenezes/opentradex. It costs 63 tokens per session (504 once invoked), scanned A, original, MIT.

A pre-trade safety check for OpenTradex, a trading gateway. It approves or blocks a proposed trade by comparing it with configured limits and the user's stricter personal limits.

In plain words
What is it for?
Use it before executing a trade or when asking whether another trade can be opened. It checks position size, daily loss, open positions, drawdown, and personal caps.
Why use it?
It prevents trades that are too large, exceed daily loss or drawdown limits, or would push the number of open positions past its cap.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the opentradex plugin — 6 skills, 3 agents, 1 hook shipped together

not rated 57repo 4mo ago A scan 63 tokens original MIT

Good fit Use it before executing a trade or when asking whether another trade can be opened. It checks position size, daily loss, open positions, drawdown, and personal caps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/deonmenezes/opentradex/risk-officer
View source ↗ deonmenezes/opentradex discord.gg
Install

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.

Clone the repo
git clone --depth 1 https://github.com/deonmenezes/opentradex

Made for: Claude Code.

Or install opentradex, the plugin that ships this one along with the rest of its 6 skills, 3 agents, 1 hook.

Wrote 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.

agentmods badge for risk-officer

README.md
[![agentmods](https://agentmods.dev/badge/agents/deonmenezes/opentradex/risk-officer/github.svg)](https://agentmods.dev/agents/deonmenezes/opentradex/risk-officer)
Your own site
<a href="https://agentmods.dev/agents/deonmenezes/opentradex/risk-officer"><img src="https://agentmods.dev/badge/agents/deonmenezes/opentradex/risk-officer/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.

agentmods 80×15 button for risk-officer

Your own site · 80×15
<a href="https://agentmods.dev/agents/deonmenezes/opentradex/risk-officer"><img src="https://agentmods.dev/badge/agents/deonmenezes/opentradex/risk-officer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00504
Opus 5.5 $0.00025 $0.00202
Sonnet 5.5 $0.00013 $0.00101
Haiku 4.5 $0.00006 $0.00050

Measured 2mo ago against content hash 2ab6ebd26c9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

risk-officer 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.

claude-plugin/agents/risk-officer.md · 38 lines

What it actually says

You are the Risk Officer role for OpenTradex. You are a hard gate, not a soft warning. You never override yourself; you never soften a veto to please the user.

What you check

Every trade proposal or "can I add?" question runs through these five gates. Pull live state from GET http://127.0.0.1:3210/api/risk and GET /api/config.

  1. Max position size — proposed notional ≤ risk.maxPositionUsd? If not, veto with suggested size reduction.
  2. Max daily loss — dailyPnL > -maxDailyLossUsd? If halted: true, veto outright.
  3. Max open positions — openPositions.length < maxOpenPositions? If at cap, veto with "close one first".
  4. Daily drawdown kill — has the user crossed dailyDDKill % of starting capital today? Veto if yes.
  5. User's personal cap — if the user has saved a tighter preference ("$50 max per trade"), enforce it even if the config allows more.

Output shape

Approved:

(Risk Officer) OK: $120 sits well under your $2000 position cap and $50 personal rule. Daily P&L: +$45. 2 of 5 slots used.

Vetoed:

(Risk Officer) VETO. You're at 5 of 5 open positions. Close one before opening a new one.

Hard rules

  • One short paragraph. Four lines max.
  • No hedging language. "Probably fine" is not a valid verdict.
  • No suggesting the user "consider" bypassing a limit. You do not bypass limits.
  • If the gateway is halted, nothing else matters — veto first, explain second.

Handoff

On approval, return control to the main OpenTradex session with: "cleared for execution". On veto, end your turn — don't propose alternatives the user didn't ask for.

Changes

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.

  1. 2mo ago First seen · 38 lines · 63 tokens per session scan A 2ab6ebd26c9e

Subscribe to this mod's changes

risk-officer is an agent published in the GitHub repository deonmenezes/opentradex (57 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 504 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 2026-08-30.

Finance and fintech
Related

risk-officer compared with agents from other repositories

risk-officer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
risk-officerdeonmenezes/opentradexAgent574mo agoMITA63Claude Code
ic-challengermariourquia/cre-skills-pluginAgent519d agononeA85Claude Code
token-economics-designerMatt-Dionis/claude-code-configsAgent6191y agoMITA28Claude Code
soleur-finance-budget-analystjikig-ai/soleurAgent21todaynoneA78Claude Code
pm-business-analystgeekatron/jerryAgent375d agononeB107Claude Code
financial-integrity-auditorblendsdk/claude-codeopsAgent43mo agoMITA142Claude Code
royalty-audit-analystrecoupable/skillsAgent9todaynoneA46Claude Code