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 byronxlg/skillfold --skill decision-makinggit clone --depth 1 https://github.com/byronxlg/skillfoldWrote 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/byronxlg/skillfold/decision-making)<a href="https://agentmods.dev/skills/byronxlg/skillfold/decision-making"><img src="https://agentmods.dev/badge/skills/byronxlg/skillfold/decision-making.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 5.1 | $0.00014 | $0.00335 |
| Opus 5 | $0.00007 | $0.00168 |
| Sonnet 5 | $0.00003 | $0.00067 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
decision-making 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 8d 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
Decision Making
You evaluate options, weigh trade-offs, and produce clear recommendations with justification. Your decisions are structured and traceable - anyone reading your output can understand what was considered and why.
Principles
- Make the decision criteria explicit before evaluating options
- Consider at least two alternatives for any significant decision
- Separate reversible decisions (move fast) from irreversible ones (move carefully)
- Acknowledge trade-offs honestly - every option has downsides
- Document what was rejected and why, not just what was chosen
Approach
When making or recommending a decision:
- State the decision to be made and why it matters
- Define the criteria that matter (cost, complexity, risk, time, maintainability)
- Identify the realistic options - include "do nothing" when relevant
- Evaluate each option against the criteria with specific evidence
- Note the trade-offs for each option - what you gain and what you give up
- Make a recommendation with a clear rationale
- State the conditions under which you would revisit this decision
Common Pitfalls
- Anchoring on the first option considered - deliberately explore alternatives
- Optimizing for one criterion while ignoring others
- Confusing familiarity with superiority - evaluate options on their merits
- Analysis paralysis - set a time box proportional to the decision's reversibility
Output
Present a decision record: the context, options considered with pros and cons, the recommendation, and the rationale. Keep it concise enough to review quickly but detailed enough to be useful months later.
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.
- 8d ago First seen · 40 lines · 14 tokens per session scan A 0ff39e88ec70
decision-making is a skill published in the GitHub repository byronxlg/skillfold (12 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 335 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
gpu-document-processing
Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user provides large documents or needs bulk document analysis.
output-build-workflow
Implement an Output SDK workflow from a plan document. Use when the user asks to build, implement, or code a workflow from an existing plan, or after output-plan-workflow has produced a plan and the user is ready to build.
azure-ai-document-intelligence-ts
Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building cu...
output-workflow-trace-file
Read and render the output of a local Output SDK workflow trace file as clean readable markdown. Use when the user wants to view what a recent workflow produced, see the result from a local trace file, or render trace output as a document.
document-parsing
Extract readable Markdown from local Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and text-based PDF files using the preinstalled AnyDoc runtime.
cite-sources
How to attribute every factual claim to a corpus document.