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-and-decidinggit 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-and-deciding)<a href="https://agentmods.dev/skills/fatihguner/foreman/evaluating-and-deciding"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/evaluating-and-deciding/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-and-deciding"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/evaluating-and-deciding.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 | $0.00150 | $0.04928 |
| Opus 5 | $0.00075 | $0.02464 |
| Sonnet 5 | $0.00030 | $0.00986 |
| Haiku 4.5 | $0.00015 | $0.00493 |
Grade A, and why
evaluating-and-deciding 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.
How it starts
The opening of the file, as written. The whole thing — 248 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 and Deciding
MARGIN OF SAFETY. Good decision-makers do not predict more accurately than everyone else -- they build better buffers for being wrong. Warren Buffett sat out the dot-com mania while friends doubled and quadrupled their portfolios, endured years of being called obsolete, and emerged with cash reserves intact when the bubble burst. The hedge fund Long-Term Capital Management, run by two Nobel laureates and some of the highest IQs in finance, delivered 40 percent annual returns until it lost $4.6 billion in under four months and nearly collapsed the global financial system. The difference was not intelligence. It was the presence or absence of a margin of safety -- the deliberate gap between what you expect to happen and what could happen, designed to save you when surprises are expensive. The framework for the full decision arc -- evaluate, safeguard, execute, learn -- rests on this single uncomfortable truth: certainty is a feeling, not a fact, and the moment you are most confident you do not need a buffer is precisely the moment you need one most.
The Framework
The framework spans four stages. Each builds on the preceding one, and skipping any stage degrades the quality of the entire arc.
Stage 1: Evaluate the Options
Evaluation begins not with data but with criteria. Three features distinguish useful criteria from decorative ones:
- Clarity. The criterion can be explained to a twelve-year-old. If it requires jargon, it will be interpreted differently by each person applying it.
- Goal promotion. The criterion must favour options that advance the actual objective. NASA's Challenger disaster is the canonical counter-example: launch-date criteria promoted the goal of schedule adherence, not the goal of safety. The result was catastrophic.
- Decisiveness. The criteria must narrow the field to one option. Criteria that produce ties are criteria that avoid commitment.
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.
- 6d ago First seen · 248 lines · 150 tokens per session scan A 01f4c989c0fd
evaluating-and-deciding is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 6d ago), licensed MIT. It adds 150 tokens to every session and 4,928 once invoked, about $0.0007 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 2026-09-06.
Other skills, from other repositories
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
flow-next-audit
Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.