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 skills add fatihguner/foreman --skill evaluating-optionsgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/skills/fatihguner/foreman/evaluating-options)<a href="https://agentmods.dev/skills/fatihguner/foreman/evaluating-options"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/evaluating-options/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fatihguner/foreman/evaluating-options"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/evaluating-options.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00162 | $0.05422 |
| Opus 5.5 | $0.00065 | $0.02169 |
| Sonnet 5.5 | $0.00032 | $0.01084 |
| Haiku 4.5 | $0.00016 | $0.00542 |
Grade A, and why
evaluating-options 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 24d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Evaluating Options
PROS-CONS TRAP. The pros-and-cons list is the most widely used decision tool in the world -- and it is fundamentally misleading, because it treats all factors as equal and all items as comparable. Benjamin Franklin popularised the method in 1772, and the business world has not materially improved upon it in the intervening 250 years. A list that places "strong brand fit" next to "high implementation cost" as if both carry identical weight, and then counts items on each side like ballots, is not analysis. It is arithmetic applied to incommensurable quantities. High-stakes decisions -- the kind that determine whether a company enters a market, acquires a competitor, or pivots its product -- demand evaluation methods that account for unequal weights, incomparable dimensions, and the structural biases that distort human judgment even when the data is sound. This skill assembles six such methods, each designed for a different evaluation challenge.
The Toolkit
Tool 1: Joint Evaluation
Research by Basu and Savani demonstrates that people are, on average, twenty-two percent more likely to choose the objectively best option when they evaluate all alternatives simultaneously rather than one at a time. The effect is robust across simple consumer choices and complex managerial decisions.
The mechanism is straightforward: when options are presented side by side, the mind compares directly across dimensions. When options are presented sequentially, the mind forms a holistic impression of each and then attempts to compare impressions -- a lossy process that discards the dimensional detail where differences actually live.
Practical application:
- When evaluating job candidates, lay all resumes on the table simultaneously rather than reviewing one, forming an opinion, and moving to the next
- When comparing vendors or partners, use a spreadsheet that displays all options in columns with attributes in rows -- never evaluate a vendor in isolation
- When assessing strategic alternatives, present all options in a single consequences table before any discussion begins
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.
- 24d ago First seen · 264 lines · 162 tokens per session scan A f06124761a97
evaluating-options is a skill published in the GitHub repository fatihguner/foreman (53 stars, last pushed 25d ago), licensed MIT. It adds 162 tokens to every session and 5,422 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-06.
Other skills, from other repositories
compare-two-products-fairly
Compare two products against the same requirements, pricing assumptions, limitations, and evidence.
adr-documentation
Architecture Decision Records (ADR) documentation practice. Use when documenting architectural decisions, recording technical trade-offs, creating decision logs, or establishing architectural patterns. Trigger keywords - "ADR", "architecture decision", "decision record", "trade-offs", "architectural decision"…
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…