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 yuusakuri/agent-skills --skill prioritize-assumptionsgit clone --depth 1 https://github.com/yuusakuri/agent-skillsWrote 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/yuusakuri/agent-skills/prioritize-assumptions)<a href="https://agentmods.dev/skills/yuusakuri/agent-skills/prioritize-assumptions"><img src="https://agentmods.dev/badge/skills/yuusakuri/agent-skills/prioritize-assumptions/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/yuusakuri/agent-skills/prioritize-assumptions"><img src="https://agentmods.dev/badge/skills/yuusakuri/agent-skills/prioritize-assumptions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.00507 |
| Opus 5.5 | $0.00018 | $0.00203 |
| Sonnet 5.5 | $0.00009 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
prioritize-assumptions 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 2mo 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.
This is a copy
100% identical to prioritize-assumptions — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prioritize Assumptions
Triage assumptions using an Impact × Risk matrix and suggest targeted experiments.
Context
You are helping prioritize assumptions for $ARGUMENTS.
If the user provides files with assumptions or research data, read them first.
Domain Context
ICE works well for assumption prioritization: Impact (Opportunity Score × # Customers) × Confidence (1–10) × Ease (1–10). Opportunity Score = Importance × (1 − Satisfaction), normalized to 0–1 (Dan Olsen). RICE splits Impact into Reach × Impact separately: (R × I × C) / E. See the prioritization-frameworks skill for full formulas and templates.
Instructions
The user will provide a list of assumptions to prioritize. Apply the following framework:
-
For each assumption, evaluate two dimensions:
- Impact: The value created by validating this assumption AND the number of customers affected (in ICE: Impact = Opportunity Score × # Customers)
- Risk: Defined as (1 - Confidence) × Effort
-
Categorize each assumption using the Impact × Risk matrix:
- Low Impact, Low Risk → Defer testing until higher-priority assumptions are addressed
- High Impact, Low Risk → Proceed to implementation (low risk, high reward)
- Low Impact, High Risk → Reject the idea (not worth the investment)
- High Impact, High Risk → Design an experiment to test it
-
For each assumption requiring testing, suggest an experiment that:
- Maximizes validated learning with minimal effort
- Measures actual behavior, not opinions
- Has a clear success metric and threshold
-
Present results as a prioritized matrix or table.
Think step by step. Save as markdown if the output is substantial.
Further Reading
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.
- 2mo ago First seen · 49 lines · 44 tokens per session scan A 18160a0138c7
prioritize-assumptions is a skill published in the GitHub repository yuusakuri/agent-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 44 tokens to every session and 507 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to prioritize-assumptions, differing in 0 lines, and is treated as a copy.
prioritize-assumptions compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prioritize-assumptionsyuusakuri/agent-skills | Skill | 2 | 14d ago | MIT | A | 44 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |