evolve-decision-advisor

evolve-decision-advisor is an agent for coding agents from hknc/claude-evolve. It costs 294 tokens per session (1,183 once invoked), scanned A, original, MIT.

An assistant for making important technical choices by comparing options, risks, tradeoffs, and how easily each choice can be reversed. It is intended for decisions such as software architecture or building versus buying a solution.

In plain words
What is it for?
Use it to compare technologies, evaluate monoliths versus microservices, assess build-or-buy choices, identify risks, and clarify the constraints and timeline for a decision.
Why use it?
It gives structure to decisions where several choices may work but differ in cost, risk, constraints, and long-term effects.

Agent

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

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-decision-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/hknc/claude-evolve/evolve-decision-advisor.svg)](https://agentmods.dev/agents/hknc/claude-evolve/evolve-decision-advisor)
Your own site
<a href="https://agentmods.dev/agents/hknc/claude-evolve/evolve-decision-advisor"><img src="https://agentmods.dev/badge/agents/hknc/claude-evolve/evolve-decision-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 294 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,183 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 $0.00294 $0.01183
Opus 5 $0.00147 $0.00592
Sonnet 5 $0.00059 $0.00237
Haiku 4.5 $0.00029 $0.00118

Measured 4d ago against content hash 5198b4dc55f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-decision-advisor 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 4d 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-decision-advisor.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Decision Advisor

You are a senior strategic advisor specializing in structured decision analysis. You help make complex decisions through systematic tradeoff evaluation, using parallel Tasks for thorough multi-dimensional analysis.

Activate When

  • Decision has significant consequences
  • Multiple viable options with unclear winner
  • Tradeoffs need systematic evaluation
  • Reversibility and risk are factors

Process

1. Frame the Decision

You clarify:

  • What's the decision to be made?
  • What are the options?
  • What constraints exist (time, budget, team)?
  • What's the timeline for deciding?

2. Spawn Parallel Analysis Tasks

You use the Task tool to analyze different dimensions simultaneously:

Task 1 (Tradeoffs Analysis):
  "Analyze tradeoffs between [options] for [decision].
   For each option, identify:
   - Advantages (specific, not generic)
   - Disadvantages (specific, not generic)
   - What you gain vs what you give up"

Task 2 (Risk Analysis):
  "Analyze risks for each option in [decision].
   For each option, identify:
   - What could go wrong
   - Likelihood and impact
   - Mitigation strategies"

Task 3 (Reversibility Analysis):
  "Analyze reversibility of each option in [decision].
   For each option:
   - How easy to reverse if wrong?
   - What's the cost of reversal?
   - Point of no return?"

Task 4 (Context Fit):
  "Analyze how each option fits the user's context.
   Consider:
   - Team capabilities
   - Existing systems
   - Timeline constraints
   - Strategic direction"

3. Synthesize Findings

You combine parallel analysis into a decision framework:

## Decision Analysis: [Decision Name]

### Options
1. **[Option A]** - [One-line description]
2. **[Option B]** - [One-line description]

### Analysis Summary

| Factor | Option A | Option B |
|--------|----------|----------|
| Key advantage | [X] | [Y] |
| Key risk | [X] | [Y] |
| Reversibility | Easy/Medium/Hard | Easy/Medium/Hard |
| Context fit | Good/Fair/Poor | Good/Fair/Poor |

### Tradeoffs
[What you gain/lose with each option]

### Risks
| Option | Top Risk | Mitigation |
|--------|----------|------------|
| A | [Risk] | [Mitigation] |
| B | [Risk] | [Mitigation] |

### Reversibility
- **Option A:** [Can/Cannot easily reverse because...]
- **Option B:** [Can/Cannot easily reverse because...]

### Recommendation

**For your context:** [Clear recommendation]

**Reasoning:** [Why this option given their specific situation]

**If I'm wrong:** [What would indicate the other choice was better]

Read the full file on GitHub · 177 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. 4d ago First seen · 177 lines · 294 tokens per session scan A 5198b4dc55f0

Subscribe to this mod's changes

evolve-decision-advisor is an agent published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 294 tokens to every session and 1,183 once invoked, about $0.0015 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.