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 kazdenc/builder-skills --skill prioritizegit clone --depth 1 https://github.com/kazdenc/builder-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/kazdenc/builder-skills/prioritize)<a href="https://agentmods.dev/skills/kazdenc/builder-skills/prioritize"><img src="https://agentmods.dev/badge/skills/kazdenc/builder-skills/prioritize/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/kazdenc/builder-skills/prioritize"><img src="https://agentmods.dev/badge/skills/kazdenc/builder-skills/prioritize.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 | $0.00068 | $0.01282 |
| Opus 5 | $0.00034 | $0.00641 |
| Sonnet 5 | $0.00014 | $0.00256 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
prioritize 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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Score and rank features or initiatives so teams build the highest-value things first.
Step 1: Gather the List
Collect the items to prioritize. If the user hasn't provided them, ask. Each item needs a clear, concise name and a one-sentence description of what it delivers.
Don't prioritize fewer than 3 items (just pick the best one) or more than 25 (split into themes first, then prioritize within each).
Step 2: Choose a Framework
Pick one based on what the team actually has available:
| If you have... | Use | Why |
|---|---|---|
| Usage data, reach estimates, engineering sizing | RICE | Rigorous, accounts for confidence in your estimates |
| JTBD need statements with importance/satisfaction data | Opportunity scoring | Finds underserved needs directly |
| A large list and need a quick first pass | Impact/Effort matrix | Fast triage, no math required |
| Limited data but reasonable intuition | ICE | Lighter-weight RICE, moves fast |
If unsure, default to Impact/Effort matrix for triage, then apply RICE to the top-right quadrant.
Step 3: Score Each Item
RICE
Score each item on four dimensions, then calculate:
RICE Score = (Reach x Impact x Confidence) / Effort
| Dimension | What it measures | Scale |
|---|---|---|
| Reach | How many users/accounts affected per quarter | Actual number (e.g., 500 users/quarter) |
| Impact | How much this moves the needle per user | 3 = massive, 2 = high, 1 = medium, 0.5 = low, 0.25 = minimal |
| Confidence | How sure you are about the above estimates | 100% = high, 80% = medium, 50% = low. Below 50% means you need research, not prioritization |
| Effort | Person-months of work | Actual estimate (e.g., 2 person-months) |
Opportunity Scoring
For each need identified through JTBD work:
Opportunity Score = Importance + max(Importance - Satisfaction, 0)
| Dimension | Scale |
|---|---|
| Importance | 1-10: How important is this need to the job performer? |
| Satisfaction | 1-10: How well do current solutions satisfy this need? |
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.
- 9d ago First seen · 134 lines · 68 tokens per session scan A 2abcebfba928
prioritize is a skill published in the GitHub repository kazdenc/builder-skills (45 stars, last pushed 6mo ago), licensed MIT. It adds 68 tokens to every session and 1,282 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 2026-08-30.
Other skills, from other repositories
commercial-opportunity-review
Review Product, offering, catalog, quote, and sale evidence for commercial opportunities.
demand-triage
Prepare classification, evidence gaps, and score inputs for product demand without crossing the funding boundary.
investment-preparation
Prepare an evidence-linked product investment packet while preserving the governed funding decision.
outcome-review
Review whether a funded product bet changed its intended outcome and append evidence-backed learning.
product-line-performance-review
Roll real Product evidence into a ProductLine review without changing the canonical reporting boundary.
roadmap-refresh
Refresh Now, Next, and Later from funded demand, objectives, dependencies, and delivery evidence.