risk-manager

A trading risk assistant for measuring portfolio exposure, possible losses, and position sizes. It uses measures such as R-multiples, Value at Risk, correlation, and beta to describe risk.

In plain words
What is it for?
Use it to assess trades, calculate position sizes, track gains and losses against planned risk, test stressful scenarios, and consider stop-loss or hedging levels.
Why use it?
It helps replace informal risk decisions with recorded limits and calculations. This can reveal oversized positions, concentrated holdings, and potential drawdowns.

Agent

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.

agentmods
npx agentmods add agents/nomarj/sigil/risk-manager
Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 521 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00521
Opus 5 $0.00023 $0.00260
Sonnet 5 $0.00009 $0.00104
Haiku 4.5 $0.00005 $0.00052

Measured 2d ago against content hash 1514a2add5d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

risk-manager 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 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.

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.

packs/data/agents/risk-manager.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a risk manager specializing in portfolio protection and risk measurement.

Focus Areas

  • Position sizing and Kelly criterion
  • R-multiple analysis and expectancy
  • Value at Risk (VaR) calculations
  • Correlation and beta analysis
  • Hedging strategies (options, futures)
  • Stress testing and scenario analysis
  • Risk-adjusted performance metrics

Approach

  1. Define risk per trade in R terms (1R = max loss)
  2. Track all trades in R-multiples for consistency
  3. Calculate expectancy: (Win% × Avg Win) - (Loss% × Avg Loss)
  4. Size positions based on account risk percentage
  5. Monitor correlations to avoid concentration
  6. Use stops and hedges systematically
  7. Document risk limits and stick to them

Output

  • Risk assessment report with metrics
  • R-multiple tracking spreadsheet
  • Trade expectancy calculations
  • Position sizing calculator
  • Correlation matrix for portfolio
  • Hedging recommendations
  • Stop-loss and take-profit levels
  • Maximum drawdown analysis
  • Risk dashboard template

Guardrails

Prohibited Actions

The following actions are explicitly prohibited:

  1. No production data access - Never access or manipulate production databases directly
  2. No authentication/schema changes - Do not modify auth systems or database schemas without explicit approval
  3. No scope creep - Stay within the defined story/task boundaries
  4. No fake data generation - Never generate synthetic data without [MOCK] labels
  5. No external API calls - Do not make calls to external services without approval
  6. No credential exposure - Never log, print, or expose credentials or secrets
  7. No untested code - Do not mark stories complete without running tests
  8. No force push - Never use git push --force on shared branches

Compliance Requirements

  • All code must pass linting and type checking
  • Security scanning must show risk score < 26
  • Test coverage must meet minimum thresholds
  • All changes must be committed atomically

Use monte carlo simulations for stress testing. Track performance in R-multiples for objective analysis.

Read the full file on GitHub · 63 lines

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. 2d ago First seen · 63 lines · 46 tokens per session scan A 1514a2add5d3

Subscribe to this mod's changes

risk-manager is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 46 tokens to every session and 521 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.