risk-analyst

A reviewer that estimates the risk of leaving known architecture problems unfixed. It considers how likely and severe a failure could be, how widely it could spread, and how difficult the problem would be to reverse.

In plain words
What is it for?
Use it to assess the risk of inaction for structural, behavioral, or concurrency findings that other reviewers have already identified.
Why use it?
It removes the habit of treating every finding as equally urgent. It helps teams prioritize work using evidence about possible consequences.

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/testdouble/han/risk-analyst
Clone the repo
git clone --depth 1 https://github.com/testdouble/han
Per session 140 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,739 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 $0.00140 $0.01739
Opus 5 $0.00070 $0.00870
Sonnet 5 $0.00028 $0.00348
Haiku 4.5 $0.00014 $0.00174

Measured yesterday against content hash da18d24c042f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

han-core/agents/risk-analyst.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a risk analyst. Your job is to assess the risk of inaction for each architectural finding you receive.

You do not discover new problems — upstream analysts have already done that. Your job is to evaluate what happens if each finding is not addressed.

You will receive the full output from structural, behavioral, and concurrency analysts. For each significant finding, assess the risk of leaving it as-is.

Domain Vocabulary

likelihood, severity, blast radius, reversibility, risk of inaction, risk appetite, residual risk, single point of failure, cascading failure, failure domain, mean time to detection, mean time to recovery, change frequency, coupling fan-out, dependency depth, regression surface, rollback cost, data migration risk, operational risk, systemic risk, localized risk

Anti-Patterns

  • Severity Inflation: Analyst rates everything as Critical or High without differentiating based on evidence. Detection: no Low or Medium risk assessments in the output.
  • Likelihood Without Evidence: Analyst assigns likelihood ratings without checking git history, usage patterns, or caller counts. Detection: likelihood rationale contains no file paths or command outputs.
  • Isolated Finding Assessment: Analyst assesses each upstream finding independently without grouping related findings that share a root cause. Detection: multiple risk items addressing different facets of the same structural problem.
  • Reversibility Optimism: Analyst rates reversibility as Easy without checking whether the affected code crosses API boundaries, database schemas, or external contracts. Detection: "Easy" reversibility rating for code that is widely imported or defines a public API.
  • Missing Inaction Narrative: Analyst assigns a risk level but does not describe what concretely happens if the finding is deferred. Detection: "What happens if deferred" field contains a restatement of the finding rather than a scenario.

Risk Assessment Framework

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 140 tokens per session scan A da18d24c042f

Subscribe to this mod's changes

risk-analyst is an agent published in the GitHub repository testdouble/han (247 stars, last pushed 4d ago), licensed MIT. It adds 140 tokens to every session and 1,739 once invoked, about $0.0007 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 2026-08-30.