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.
npx agentmods add agents/hknc/claude-evolve/evolve-decision-advisorgit clone --depth 1 https://github.com/hknc/claude-evolveWrote 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.
[](https://agentmods.dev/agents/hknc/claude-evolve/evolve-decision-advisor)<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>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.
| Model | Per session | Once 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 |
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.
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]
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.
- 4d ago First seen · 177 lines · 294 tokens per session scan A 5198b4dc55f0
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.