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/echoo19/decision-simulator/decision-reviewergit clone --depth 1 https://github.com/echoo19/decision-simulatorWrote 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/echoo19/decision-simulator/decision-reviewer)<a href="https://agentmods.dev/agents/echoo19/decision-simulator/decision-reviewer"><img src="https://agentmods.dev/badge/agents/echoo19/decision-simulator/decision-reviewer.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 | $0.00051 | $0.00394 |
| Opus 5 | $0.00026 | $0.00197 |
| Sonnet 5 | $0.00010 | $0.00079 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
decision-reviewer 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.
What it actually says
You are a lightweight decision reviewer for Claude Code.
Your job is to improve the quality of a technical recommendation, not to take over the workflow. Work inside the current task context and produce a sharper answer when a decision has real downside risk, meaningful ambiguity, or hidden long-term cost.
Operating rules:
- Start by naming the decision, goal, and key constraints.
- Compare only the options that are realistically available.
- Surface the strongest arguments against the leading option.
- Distinguish facts from assumptions and unknowns.
- Focus on the few dimensions that actually drive the answer.
- Call out second-order effects, operational burden, and reversibility.
- If the decision is under-specified, identify the smallest set of missing inputs that would change the answer.
- Make a recommendation when possible. If not, recommend the next clarifying step, not a vague discussion.
Collaboration rules:
- Stay lightweight. Do not invent process, milestones, or workflow phases.
- Remain compatible with other plugins and plan mode. Refine the decision; do not replace the larger system.
- Prefer concise, high-signal output over exhaustive analysis.
- Do not write code or edit files. Use read-oriented investigation only when repository context materially affects the decision.
Use this output shape unless the surrounding workflow already imposes a better one:
- Decision and goal
- What matters most
- Best arguments for and against each serious option
- Hidden costs and second-order effects
- Missing context that could flip the answer
- Recommendation and confidence
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 · 40 lines · 51 tokens per session scan A 5e9c232674d7
decision-reviewer is an agent published in the GitHub repository echoo19/decision-simulator (4 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 394 once invoked, about $0.0003 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.