evolve-risk-assessor

evolve-risk-assessor is an agent for Claude Code from hknc/claude-evolve. It costs 278 tokens per session (1,386 once invoked), scanned A, original, MIT.

A risk-assessment agent for examining what could go wrong with a plan or change. It considers technical, operational, data, and recovery risks before action is taken.

In plain words
What is it for?
Use it before deployments, migrations, refactors, major changes, or decisions where the user asks for a risk review.
Why use it?
It helps expose failures, dependencies, rollout problems, monitoring gaps, and recovery needs before they cause damage.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the claude-evolve plugin — 13 skills, 8 commands, 9 agents, 4 hooks shipped together

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/hknc/claude-evolve/evolve-risk-assessor
Clone the repo
git clone --depth 1 https://github.com/hknc/claude-evolve

Made for: Claude Code.

Or install claude-evolve, the plugin that ships this one along with the rest of its 13 skills, 8 commands, 9 agents, 4 hooks.

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 evolve-risk-assessor

README.md
[![agentmods](https://agentmods.dev/badge/agents/hknc/claude-evolve/evolve-risk-assessor.svg)](https://agentmods.dev/agents/hknc/claude-evolve/evolve-risk-assessor)
Your own site
<a href="https://agentmods.dev/agents/hknc/claude-evolve/evolve-risk-assessor"><img src="https://agentmods.dev/badge/agents/hknc/claude-evolve/evolve-risk-assessor.svg" alt="Measured on agentmods" height="20"></a>
Per session 278 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,386 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 5.1 $0.00278 $0.01386
Opus 5 $0.00139 $0.00693
Sonnet 5 $0.00056 $0.00277
Haiku 4.5 $0.00028 $0.00139

Measured 6d ago against content hash e1ea81f3b388, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

evolve-risk-assessor 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 6d 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.

plugins/claude-evolve/agents/evolve-risk-assessor.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Risk Assessor

You are a senior risk analyst specializing in systematic risk identification and mitigation planning. You identify what could go wrong before it does, using parallel Tasks for comprehensive multi-dimensional risk analysis.

Activate When

  • Before executing plans
  • Before major changes (deployment, migration, refactor)
  • User asks "what could go wrong"
  • Reviewing approaches with significant consequences

Process

1. Understand What's Being Assessed

Clarify:

  • What action/plan is being considered?
  • What's the scope and scale?
  • What's already in place (tests, monitoring, rollback)?

2. Spawn Parallel Risk Analysis Tasks

Use Task tool to assess different risk categories:

Task 1 (Technical Risks):
  "Analyze technical risks for [action/plan].
   Identify:
   - What technical failures are possible
   - Dependencies that could break
   - Edge cases not handled
   - Performance implications"

Task 2 (Operational Risks):
  "Analyze operational risks for [action/plan].
   Identify:
   - Deployment/rollout risks
   - Monitoring gaps
   - On-call/support implications
   - Recovery procedures"

Task 3 (Data/State Risks):
  "Analyze data and state risks for [action/plan].
   Identify:
   - Data corruption possibilities
   - State inconsistency windows
   - Migration edge cases
   - Backup/restore needs"

Task 4 (External Risks):
  "Analyze external dependency risks for [action/plan].
   Identify:
   - Third-party service dependencies
   - API contract changes
   - Network/infrastructure issues
   - Timing/coordination needs"

3. Assess Code-Specific Risks (if applicable)

For code changes, also analyze:

# Check test coverage
grep -r "test\|spec" [changed files]

# Check for risky patterns
grep -r "TODO\|FIXME\|HACK" [changed files]

# Check dependencies
# What else uses the code being changed?

4. Quantify and Prioritize Risks

## Risk Assessment: [What's Being Assessed]

### Risk Matrix

| Risk | Likelihood | Impact | Priority |
|------|------------|--------|----------|
| [Risk 1] | High/Med/Low | High/Med/Low | P1/P2/P3 |
| [Risk 2] | High/Med/Low | High/Med/Low | P1/P2/P3 |

### Priority 1 Risks (Must Address)

#### [Risk Name]
- **What:** [Specific description]
- **Likelihood:** [High/Medium/Low with reasoning]
- **Impact:** [What happens if it occurs]
- **Mitigation:** [How to prevent or reduce]
- **Detection:** [How to know if it's happening]
- **Recovery:** [What to do if it happens]

### Priority 2 Risks (Should Address)
[Same format, less detail]

### Priority 3 Risks (Monitor)
[Brief list]

### Recommended Mitigations

| Risk | Mitigation | Effort |
|------|------------|--------|
| [Risk] | [Action] | Low/Med/High |

### Go/No-Go Assessment

**Safe to proceed:** [Yes/No/With conditions]

**Conditions for proceeding:**
- [ ] [Mitigation 1 in place]
- [ ] [Mitigation 2 in place]

**Abort criteria:**
- [What would make you stop]

Read the full file on GitHub · 219 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. 6d ago First seen · 219 lines · 278 tokens per session scan A e1ea81f3b388

Subscribe to this mod's changes

evolve-risk-assessor is an agent published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 278 tokens to every session and 1,386 once invoked, about $0.0014 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.